[
{
"path": ".github/workflows/ci.yml",
"content": "# This workflow will build a Swift project\n# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-swift\n\nname: CI tests\n\non:\n push:\n branches: [ \"main\" ]\n pull_request:\n branches: [ \"main\" ]\n\njobs:\n build_and_test_macos:\n runs-on: macos-latest\n steps:\n - uses: actions/checkout@v4\n - name: Get swift version\n run: swift --version\n - name: Build\n run: swift build -q\n - name: Run tests\n run: swift test -q\n\n build_and_test_linux:\n runs-on: ubuntu-latest\n container:\n image: swift:6.0.1-jammy\n steps:\n - name: Install dependencies\n run: |\n apt-get update\n apt-get install -y curl git\n - uses: actions/checkout@v4\n - name: Get swift version\n run: swift --version\n - name: Build\n run: swift build -q\n - name: Run tests\n run: swift test -q\n\n lint:\n runs-on: macos-latest\n steps:\n - uses: actions/checkout@v4\n - name: Set up Homebrew\n id: set-up-homebrew\n uses: Homebrew/actions/setup-homebrew@master\n - name: Install swiftformat\n run: brew install swiftformat\n - name: Check formatting\n run: swiftformat --config rules.swiftformat --lint ."
},
{
"path": ".gitignore",
"content": ".DS_Store\n/.build\n/Packages\nxcuserdata/\nDerivedData/\n.swiftpm/configuration/registries.json\n.swiftpm/xcode/package.xcworkspace/contents.xcworkspacedata\n.netrc\nPackage.resolved\n\n# Xcode Swift Package Manager\n**/xcshareddata/swiftpm/\n**/project.xcworkspace/xcshareddata/swiftpm/\n**/xcshareddata/IDEWorkspaceChecks.plist\n"
},
{
"path": "CONTRIBUTING.md",
"content": "\n### Linting:\n```bash\nbrew install swiftformat\nswiftformat --config rules.swiftformat .\n```"
},
{
"path": "Examples/RealtimeExample/README.md",
"content": "# OpenAI Realtime API Example\n\nThis example demonstrates how to use SwiftOpenAI's Realtime API for bidirectional voice conversations with OpenAI's GPT-4o models.\n\n## Features\n\n- Real-time bidirectional audio streaming\n- Voice Activity Detection (VAD) for automatic turn-taking\n- Audio transcription of both user and AI speech\n- Function calling support\n- Interrupt handling when user starts speaking\n\n## Requirements\n\n- iOS 15+, macOS 12+, watchOS 9+\n- Microphone permissions\n- OpenAI API key\n\n## Setup\n\n### 1. Add Microphone Permission\n\nAdd the following to your `Info.plist`:\n\n```xml\nNSMicrophoneUsageDescription\nWe need access to your microphone for voice conversations with AI\n```\n\n### 2. macOS Sandbox Configuration\n\nIf targeting macOS, enable the following in your target's Signing & Capabilities:\n\n- **App Sandbox**:\n - Outgoing Connections (Client) ✓\n - Audio Input ✓\n- **Hardened Runtime**:\n - Audio Input ✓\n\n## Usage\n\n### Basic Example\n\n```swift\nimport SwiftUI\nimport OpenAI\n\nstruct ContentView: View {\n let realtimeManager = RealtimeManager()\n @State private var isActive = false\n\n var body: some View {\n Button(isActive ? \"Stop\" : \"Start\") {\n isActive.toggle()\n if isActive {\n Task {\n try? await realtimeManager.startConversation()\n }\n } else {\n Task {\n await realtimeManager.stopConversation()\n }\n }\n }\n }\n}\n\n@RealtimeActor\nfinal class RealtimeManager {\n private var session: OpenAIRealtimeSession?\n private var audioController: AudioController?\n\n func startConversation() async throws {\n // Initialize service\n let service = OpenAIServiceFactory.service(apiKey: \"your-api-key\")\n\n // Configure session\n let config = OpenAIRealtimeSessionConfiguration(\n inputAudioFormat: .pcm16,\n inputAudioTranscription: .init(model: \"whisper-1\"),\n instructions: \"You are a helpful assistant\",\n modalities: [.audio, .text],\n outputAudioFormat: .pcm16,\n voice: \"shimmer\"\n )\n\n // Create session\n session = try await service.realtimeSession(\n model: \"gpt-4o-mini-realtime-preview-2024-12-17\",\n configuration: config\n )\n\n // Setup audio\n audioController = try await AudioController(modes: [.playback, .record])\n\n // Handle microphone input\n Task {\n let micStream = try audioController!.micStream()\n for await buffer in micStream {\n if let base64Audio = AudioUtils.base64EncodeAudioPCMBuffer(from: buffer) {\n await session?.sendMessage(\n OpenAIRealtimeInputAudioBufferAppend(audio: base64Audio)\n )\n }\n }\n }\n\n // Handle AI responses\n Task {\n for await message in session!.receiver {\n switch message {\n case .responseAudioDelta(let audio):\n audioController?.playPCM16Audio(base64String: audio)\n case .inputAudioBufferSpeechStarted:\n audioController?.interruptPlayback()\n default:\n break\n }\n }\n }\n }\n\n func stopConversation() {\n audioController?.stop()\n session?.disconnect()\n }\n}\n```\n\n## Configuration Options\n\n### Voice Options\n\n- `alloy` - Neutral and balanced\n- `echo` - Friendly and warm\n- `shimmer` - Gentle and calming\n\n### Turn Detection\n\n#### Server VAD (Voice Activity Detection)\n\n```swift\nturnDetection: .init(type: .serverVAD(\n prefixPaddingMs: 300, // Audio to include before speech\n silenceDurationMs: 500, // Silence duration to detect end\n threshold: 0.5 // Activation threshold (0.0-1.0)\n))\n```\n\n#### Semantic VAD\n\n```swift\nturnDetection: .init(type: .semanticVAD(\n eagerness: .medium // .low, .medium, or .high\n))\n```\n\n### Modalities\n\n```swift\nmodalities: [.audio, .text] // Both audio and text\nmodalities: [.text] // Text only (disables audio)\n```\n\n## Handling Different Events\n\n```swift\nfor await message in session.receiver {\n switch message {\n case .error(let error):\n print(\"Error: \\(error ?? \"Unknown\")\")\n\n case .sessionCreated:\n print(\"Session started\")\n\n case .sessionUpdated:\n // Trigger first response if AI speaks first\n await session.sendMessage(OpenAIRealtimeResponseCreate())\n\n case .responseAudioDelta(let base64Audio):\n audioController.playPCM16Audio(base64String: base64Audio)\n\n case .inputAudioBufferSpeechStarted:\n // User started speaking, interrupt AI\n audioController.interruptPlayback()\n\n case .responseTranscriptDone(let transcript):\n print(\"AI said: \\(transcript)\")\n\n case .inputAudioTranscriptionCompleted(let transcript):\n print(\"User said: \\(transcript)\")\n\n case .responseFunctionCallArgumentsDone(let name, let args, let callId):\n print(\"Function \\(name) called with: \\(args)\")\n // Handle function call and return result\n\n default:\n break\n }\n}\n```\n\n## Function Calling\n\nAdd tools to your configuration:\n\n```swift\nlet config = OpenAIRealtimeSessionConfiguration(\n tools: [\n .init(\n name: \"get_weather\",\n description: \"Get the current weather for a location\",\n parameters: [\n \"type\": \"object\",\n \"properties\": [\n \"location\": [\n \"type\": \"string\",\n \"description\": \"City name\"\n ]\n ],\n \"required\": [\"location\"]\n ]\n )\n ],\n toolChoice: .auto\n)\n```\n\nHandle function calls in the message loop:\n\n```swift\ncase .responseFunctionCallArgumentsDone(let name, let args, let callId):\n // Parse arguments and execute function\n let result = handleFunction(name: name, args: args)\n\n // Return result to OpenAI\n await session.sendMessage(\n OpenAIRealtimeConversationItemCreate(\n item: .init(role: \"function\", text: result)\n )\n )\n```\n\n## Troubleshooting\n\n### No Audio Output\n\n- Check that `.playback` mode is included in AudioController initialization\n- Verify audio permissions are granted\n- Ensure `outputAudioFormat` is set to `.pcm16`\n\n### No Microphone Input\n\n- Check that `.record` mode is included in AudioController initialization\n- Verify microphone permissions in Info.plist\n- Check System Settings > Privacy & Security > Microphone\n\n### WebSocket Connection Fails\n\n- Verify API key is correct\n- Check that `openai-beta: realtime=v1` header is included (SwiftOpenAI handles this automatically)\n- Ensure you're using a compatible model (gpt-4o-mini-realtime-preview or newer)\n\n## Resources\n\n- [OpenAI Realtime API Documentation](https://platform.openai.com/docs/api-reference/realtime)\n- [SwiftOpenAI GitHub](https://github.com/jamesrochabrun/SwiftOpenAI)\n"
},
{
"path": "Examples/RealtimeExample/RealtimeExample.swift",
"content": "//\n// RealtimeExample.swift\n// SwiftOpenAI\n//\n// Example implementation of OpenAI Realtime API for bidirectional voice conversation\n//\n\nimport AVFoundation\nimport OpenAI\nimport SwiftUI\n\n// MARK: - RealtimeExampleView\n\nstruct RealtimeExampleView: View {\n let realtimeManager = RealtimeManager()\n\n var body: some View {\n VStack {\n Button(isRealtimeActive ? \"Stop OpenAI Realtime\" : \"Start OpenAI Realtime\") {\n isRealtimeActive.toggle()\n }\n }\n }\n\n @State private var isRealtimeActive = false {\n willSet {\n if newValue {\n startRealtime()\n } else {\n stopRealtime()\n }\n }\n }\n\n private func startRealtime() {\n Task {\n do {\n try await realtimeManager.startConversation()\n } catch {\n print(\"Could not start OpenAI realtime: \\(error.localizedDescription)\")\n }\n }\n }\n\n private func stopRealtime() {\n Task {\n await realtimeManager.stopConversation()\n }\n }\n\n}\n\n// MARK: - RealtimeManager\n\n@RealtimeActor\nfinal class RealtimeManager {\n nonisolated init() { }\n\n func startConversation() async throws {\n // Initialize the OpenAI service with your API key\n let service = OpenAIServiceFactory.service(apiKey: \"your-api-key-here\")\n\n // Set to false if you want your user to speak first\n let aiSpeaksFirst = true\n\n let audioController = try await AudioController(modes: [.playback, .record])\n let micStream = try audioController.micStream()\n\n // Configure the realtime session\n let configuration = OpenAIRealtimeSessionConfiguration(\n inputAudioFormat: .pcm16,\n inputAudioTranscription: .init(model: \"whisper-1\"),\n instructions: \"You are a helpful, witty, and friendly AI assistant. \" +\n \"Your voice and personality should be warm and engaging, \" +\n \"with a lively and playful tone. Talk quickly.\",\n maxResponseOutputTokens: .int(4096),\n modalities: [.audio, .text],\n outputAudioFormat: .pcm16,\n temperature: 0.7,\n turnDetection: .init(\n type: .semanticVAD(eagerness: .medium)),\n voice: \"shimmer\")\n\n // Create the realtime session\n let realtimeSession = try await service.realtimeSession(\n model: \"gpt-4o-mini-realtime-preview-2024-12-17\",\n configuration: configuration)\n\n // Send audio from the microphone to OpenAI once OpenAI is ready for it\n var isOpenAIReadyForAudio = false\n Task {\n for await buffer in micStream {\n if\n isOpenAIReadyForAudio,\n let base64Audio = AudioUtils.base64EncodeAudioPCMBuffer(from: buffer)\n {\n await realtimeSession.sendMessage(\n OpenAIRealtimeInputAudioBufferAppend(audio: base64Audio))\n }\n }\n }\n\n // Listen for messages from OpenAI\n Task {\n for await message in realtimeSession.receiver {\n switch message {\n case .error(let errorMessage):\n print(\"Received error from OpenAI: \\(errorMessage ?? \"Unknown error\")\")\n realtimeSession.disconnect()\n\n case .sessionUpdated:\n if aiSpeaksFirst {\n await realtimeSession.sendMessage(OpenAIRealtimeResponseCreate())\n } else {\n isOpenAIReadyForAudio = true\n }\n\n case .responseAudioDelta(let base64String):\n audioController.playPCM16Audio(base64String: base64String)\n\n case .inputAudioBufferSpeechStarted:\n // User started speaking, interrupt AI playback\n audioController.interruptPlayback()\n\n case .responseCreated:\n isOpenAIReadyForAudio = true\n\n case .responseTranscriptDone(let transcript):\n print(\"AI said: \\(transcript)\")\n\n case .inputAudioTranscriptionCompleted(let transcript):\n print(\"User said: \\(transcript)\")\n\n case .responseFunctionCallArgumentsDone(let name, let arguments, let callId):\n print(\"Function call: \\(name) with args: \\(arguments)\")\n // Handle function calls here\n\n default:\n break\n }\n }\n }\n\n self.realtimeSession = realtimeSession\n self.audioController = audioController\n }\n\n func stopConversation() {\n audioController?.stop()\n realtimeSession?.disconnect()\n audioController = nil\n realtimeSession = nil\n }\n\n private var realtimeSession: OpenAIRealtimeSession?\n private var audioController: AudioController?\n\n}\n\n// MARK: - Basic Usage Example\n\n// To use the Realtime API:\n//\n// 1. Add NSMicrophoneUsageDescription to your Info.plist:\n// NSMicrophoneUsageDescription\n// We need access to your microphone for voice conversations with AI\n//\n// 2. On macOS, enable the following in your target's Signing & Capabilities:\n// - App Sandbox > Outgoing Connections (client)\n// - App Sandbox > Audio Input\n// - Hardened Runtime > Audio Input\n//\n// 3. Initialize the service with your API key:\n// let service = OpenAIServiceFactory.service(apiKey: \"your-api-key\")\n//\n// 4. Create a session configuration:\n// let config = OpenAIRealtimeSessionConfiguration(\n// inputAudioFormat: .pcm16,\n// instructions: \"You are a helpful assistant\",\n// modalities: [.audio, .text],\n// outputAudioFormat: .pcm16,\n// voice: \"shimmer\"\n// )\n//\n// 5. Create the realtime session:\n// let session = try await service.realtimeSession(\n// model: \"gpt-4o-mini-realtime-preview-2024-12-17\",\n// configuration: config\n// )\n//\n// 6. Set up audio controller:\n// let audioController = try await AudioController(modes: [.playback, .record])\n//\n// 7. Stream microphone audio to OpenAI:\n// for await buffer in try audioController.micStream() {\n// if let base64Audio = AudioUtils.base64EncodeAudioPCMBuffer(from: buffer) {\n// await session.sendMessage(\n// OpenAIRealtimeInputAudioBufferAppend(audio: base64Audio)\n// )\n// }\n// }\n//\n// 8. Listen for and play responses:\n// for await message in session.receiver {\n// switch message {\n// case .responseAudioDelta(let base64Audio):\n// audioController.playPCM16Audio(base64String: base64Audio)\n// default:\n// break\n// }\n// }\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/AIProxyIntroView.swift",
"content": "//\n// AIProxyIntroView.swift\n// SwiftOpenAIExample\n//\n// Created by Lou Zell on 3/27/24.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct AIProxyIntroView: View {\n var body: some View {\n NavigationStack {\n VStack {\n Spacer()\n VStack(spacing: 24) {\n TextField(\"Enter partial key\", text: $partialKey)\n TextField(\"Enter your service's URL\", text: $serviceURL)\n }\n .padding()\n .textFieldStyle(.roundedBorder)\n\n Text(\"You receive a partial key and service URL when you configure an app in the AIProxy dashboard\")\n .font(.caption)\n\n NavigationLink(destination: OptionsListView(\n openAIService: aiproxyService,\n options: OptionsListView.APIOption.allCases.filter { $0 != .localChat }))\n {\n Text(\"Continue\")\n .padding()\n .padding(.horizontal, 48)\n .foregroundColor(.white)\n .background(\n Capsule()\n .foregroundColor(canProceed ? Color(red: 64 / 255, green: 195 / 255, blue: 125 / 255) : .gray.opacity(0.2)))\n }\n .disabled(!canProceed)\n Spacer()\n Group {\n Text(\n \"AIProxy keeps your OpenAI API key secure. To configure AIProxy for your project, or to learn more about how it works, please see the docs at \") +\n Text(\"[this link](https://www.aiproxy.pro/docs).\")\n }\n .font(.caption)\n }\n .padding()\n .navigationTitle(\"AIProxy Configuration\")\n }\n }\n\n @State private var partialKey = \"\"\n @State private var serviceURL = \"\"\n\n private var canProceed: Bool {\n !(partialKey.isEmpty || serviceURL.isEmpty)\n }\n\n private var aiproxyService: OpenAIService {\n OpenAIServiceFactory.service(\n aiproxyPartialKey: partialKey,\n aiproxyServiceURL: serviceURL != \"\" ? serviceURL : nil)\n }\n}\n\n#Preview {\n ApiKeyIntroView()\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ApiKeyIntroView.swift",
"content": "//\n// ApiKeyIntroView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/19/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct ApiKeyIntroView: View {\n var body: some View {\n NavigationStack {\n VStack {\n Spacer()\n VStack(spacing: 24) {\n TextField(\"Enter API Key\", text: $apiKey)\n TextField(\"Enter Organization ID (Optional)\", text: $organizationIdentifier)\n .onChange(of: organizationIdentifier) { _, newValue in\n if !newValue.isEmpty {\n localOrganizationID = newValue\n }\n }\n }\n .padding()\n .textFieldStyle(.roundedBorder)\n NavigationLink(destination: OptionsListView(\n openAIService: OpenAIServiceFactory.service(apiKey: apiKey, organizationID: localOrganizationID, debugEnabled: true),\n options: OptionsListView.APIOption.allCases.filter { $0 != .localChat }))\n {\n Text(\"Continue\")\n .padding()\n .padding(.horizontal, 48)\n .foregroundColor(.white)\n .background(\n Capsule()\n .foregroundColor(apiKey.isEmpty ? .gray.opacity(0.2) : Color(red: 64 / 255, green: 195 / 255, blue: 125 / 255)))\n }\n .disabled(apiKey.isEmpty)\n Spacer()\n Group {\n Text(\"If you don't have a valid API KEY yet, you can visit \") +\n Text(\"[this link](https://platform.openai.com/account/api-keys)\") + Text(\" to get started.\")\n }\n .font(.caption)\n }\n .padding()\n .navigationTitle(\"Enter OpenAI API KEY\")\n }\n }\n\n @State private var apiKey = \"\"\n @State private var organizationIdentifier = \"\"\n @State private var localOrganizationID: String? = nil\n}\n\n#Preview {\n ApiKeyIntroView()\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Assets.xcassets/AccentColor.colorset/Contents.json",
"content": "{\n \"colors\" : [\n {\n \"idiom\" : \"universal\"\n }\n ],\n \"info\" : {\n \"author\" : \"xcode\",\n \"version\" : 1\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Assets.xcassets/AppIcon.appiconset/Contents.json",
"content": "{\n \"images\" : [\n {\n \"idiom\" : \"universal\",\n \"platform\" : \"ios\",\n \"size\" : \"1024x1024\"\n },\n {\n \"idiom\" : \"mac\",\n \"scale\" : \"1x\",\n \"size\" : \"16x16\"\n },\n {\n \"idiom\" : \"mac\",\n \"scale\" : \"2x\",\n \"size\" : \"16x16\"\n },\n {\n \"idiom\" : \"mac\",\n \"scale\" : \"1x\",\n \"size\" : \"32x32\"\n },\n {\n \"idiom\" : \"mac\",\n \"scale\" : \"2x\",\n \"size\" : \"32x32\"\n },\n {\n \"idiom\" : \"mac\",\n \"scale\" : \"1x\",\n \"size\" : \"128x128\"\n },\n {\n \"idiom\" : \"mac\",\n \"scale\" : \"2x\",\n \"size\" : \"128x128\"\n },\n {\n \"idiom\" : \"mac\",\n \"scale\" : \"1x\",\n \"size\" : \"256x256\"\n },\n {\n \"idiom\" : \"mac\",\n \"scale\" : \"2x\",\n \"size\" : \"256x256\"\n },\n {\n \"idiom\" : \"mac\",\n \"scale\" : \"1x\",\n \"size\" : \"512x512\"\n },\n {\n \"idiom\" : \"mac\",\n \"scale\" : \"2x\",\n \"size\" : \"512x512\"\n }\n ],\n \"info\" : {\n \"author\" : \"xcode\",\n \"version\" : 1\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Assets.xcassets/Contents.json",
"content": "{\n \"info\" : {\n \"author\" : \"xcode\",\n \"version\" : 1\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Assistants/AssistantConfigurationDemoView.swift",
"content": "//\n// AssistantConfigurationDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/17/23.\n//\n\nimport Foundation\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - AssistantFunctionCallDefinition\n\nenum AssistantFunctionCallDefinition: String, CaseIterable {\n case createImage = \"create_image\"\n\n var functionTool: AssistantObject.Tool {\n switch self {\n case .createImage:\n .init(type: .function, function: .init(\n name: rawValue,\n strict: nil,\n description: \"call this function if the request asks to generate an image\",\n parameters: .init(\n type: .object,\n properties: [\n \"prompt\": .init(type: .string, description: \"The exact prompt passed in.\"),\n \"count\": .init(type: .integer, description: \"The number of images requested\"),\n ],\n required: [\"prompt\", \"count\"])))\n }\n }\n}\n\n// MARK: - AssistantConfigurationDemoView\n\nstruct AssistantConfigurationDemoView: View {\n init(service: OpenAIService) {\n self.service = service\n _provider = State(initialValue: AssistantConfigurationProvider(service: service))\n }\n\n var isCodeInterpreterOn: Binding {\n Binding(\n get: {\n parameters.tools.contains { $0.displayToolType == .codeInterpreter } == true\n },\n set: { newValue in\n if newValue {\n parameters.tools.append(AssistantObject.Tool(type: .codeInterpreter))\n } else {\n parameters.tools.removeAll { $0.displayToolType == .codeInterpreter }\n }\n })\n }\n\n var isDalleToolOn: Binding {\n Binding(\n get: {\n parameters.tools.contains { $0.displayToolType == .function } == true\n },\n set: { newValue in\n if newValue {\n parameters.tools.append(AssistantFunctionCallDefinition.createImage.functionTool)\n } else {\n parameters.tools.removeAll { $0.displayToolType == .function }\n }\n })\n }\n\n var isFileSearchOn: Binding {\n Binding(\n get: {\n parameters.tools.contains { $0.displayToolType == .fileSearch } == true\n },\n set: { newValue in\n if newValue {\n parameters.tools.append(AssistantObject.Tool(type: .fileSearch))\n } else {\n parameters.tools.removeAll { $0.displayToolType == .fileSearch }\n }\n })\n }\n\n var body: some View {\n ScrollView {\n VStack(spacing: 16) {\n avatarView\n inputViews\n capabilities\n footerActions\n knowledge\n }\n .padding()\n }.sheet(isPresented: $showAvatarFlow) {\n AssistantsListDemoView(assistants: provider.assistants, service: service)\n }\n }\n\n var footerActions: some View {\n HStack {\n Button(\"Save\") {\n Task {\n try await provider.createAssistant(parameters: parameters)\n }\n }\n Button(\"Delete\") {\n Task {\n for assistant in provider.assistants {\n try await provider.deleteAssistant(id: assistant.id)\n }\n }\n }\n Button(\"Show Assistants\") {\n Task {\n try await provider.listAssistants()\n showAvatarFlow = true\n }\n }\n }\n .buttonStyle(.borderedProminent)\n }\n\n @ViewBuilder\n var avatarView: some View {\n if isAvatarLoading {\n Circle()\n .stroke(.gray, style: StrokeStyle(lineWidth: 1, dash: [5, 5]))\n .frame(width: 100, height: 100)\n .overlay(\n Image(systemName: \"rays\")\n .resizable()\n .frame(width: 20, height: 20)\n .tint(.gray)\n .symbolEffect(.variableColor.iterative.dimInactiveLayers))\n } else if let avatarURL = provider.avatarURL {\n URLImageView(url: avatarURL)\n .clipShape(Circle())\n .overlay(Circle().stroke(Color.white, lineWidth: 1))\n .shadow(radius: 10)\n } else {\n Circle()\n .stroke(.gray, style: StrokeStyle(lineWidth: 1, dash: [5, 5]))\n .frame(width: 100, height: 100)\n .overlay(\n Menu(content: {\n Button {\n Task {\n isAvatarLoading = true\n defer { isAvatarLoading = false } // ensure isLoading is set to false when the\n let prompt = parameters.description ?? \"Some random image for an avatar\"\n try await provider.createAvatar(prompt: prompt)\n }\n } label: {\n Text(\"Use DALL·E\")\n }\n }, label: {\n Image(systemName: \"plus\")\n .resizable()\n .frame(width: 20, height: 20)\n .tint(.gray)\n }))\n }\n }\n\n var inputViews: some View {\n VStack(spacing: 16) {\n InputView(title: \"Name\") {\n TextField(\"\", text: $parameters.name.orEmpty, axis: .vertical)\n }\n InputView(title: \"Description\") {\n TextField(\"\", text: $parameters.description.orEmpty, axis: .vertical)\n }\n InputView(title: \"Instructions\") {\n ZStack {\n RoundedRectangle(cornerRadius: 4)\n .stroke(.gray.opacity(0.3))\n TextEditor(text: $parameters.instructions.orEmpty)\n .foregroundStyle(.primary)\n .clipShape(RoundedRectangle(cornerRadius: 4))\n .frame(minHeight: 100)\n }\n }\n }\n .textFieldStyle(.roundedBorder)\n }\n\n var capabilities: some View {\n InputView(title: \"Capabilities\") {\n VStack(spacing: 16) {\n CheckboxRow(title: \"Code interpreter\", isChecked: isCodeInterpreterOn)\n CheckboxRow(title: \"File Search\", isChecked: isFileSearchOn)\n CheckboxRow(title: \"DALL·E Image Generation\", isChecked: isDalleToolOn)\n }\n }\n .inputViewStyle(.init(verticalPadding: 16.0))\n }\n\n // TODO: Add a demo to create a vector store and add files in to it.\n var knowledge: some View {\n FilesPicker(\n service: service,\n sectionTitle: \"Knowledge\",\n actionTitle: \"Upload files\",\n fileIDS: $fileIDS,\n actions: $filePickerInitialActions)\n }\n\n @State private var provider: AssistantConfigurationProvider\n @State private var parameters = AssistantParameters(action: .create(model: Model.gpt41106Preview.value))\n @State private var isAvatarLoading = false\n @State private var showAvatarFlow = false\n @State private var fileIDS = [String]()\n /// Used mostly to display already uploaded files if any.\n @State private var filePickerInitialActions = [FilePickerAction]()\n\n private let service: OpenAIService\n}\n\nextension Binding where Value == String? {\n var orEmpty: Binding {\n Binding(\n get: { self.wrappedValue ?? \"\" },\n set: { self.wrappedValue = $0 })\n }\n}\n\n#Preview {\n AssistantConfigurationDemoView(service: OpenAIServiceFactory.service(apiKey: \"\"))\n}\n\n// MARK: - InputView\n\nstruct InputView: View {\n let content: Content\n let title: String\n\n init(title: String, @ViewBuilder content: () -> Content) {\n self.title = title\n self.content = content()\n }\n\n var body: some View {\n VStack(alignment: .leading, spacing: style.verticalPadding) {\n Text(title)\n .font(.headline)\n content\n }\n }\n\n @Environment(\\.inputViewStyle) private var style: InputViewStyle\n}\n\n// MARK: - InputViewStyle\n\nstruct InputViewStyle {\n let verticalPadding: CGFloat\n\n init(verticalPadding: CGFloat = 8.0) {\n self.verticalPadding = verticalPadding\n }\n}\n\n// MARK: - InputViewStyleKey\n\nstruct InputViewStyleKey: EnvironmentKey {\n static let defaultValue = InputViewStyle()\n}\n\nextension EnvironmentValues {\n var inputViewStyle: InputViewStyle {\n get { self[InputViewStyleKey.self] }\n set { self[InputViewStyleKey.self] = newValue }\n }\n}\n\nextension View {\n func inputViewStyle(_ style: InputViewStyle) -> some View {\n environment(\\.inputViewStyle, style)\n }\n}\n\n// MARK: - CheckboxView\n\nstruct CheckboxView: View {\n @Binding var isChecked: Bool\n\n var body: some View {\n Button(action: {\n withAnimation {\n isChecked.toggle()\n }\n }) {\n Image(systemName: isChecked ? \"checkmark.square\" : \"square\")\n }\n .buttonStyle(PlainButtonStyle())\n }\n}\n\n// MARK: - CheckboxRow\n\nstruct CheckboxRow: View {\n let title: String\n @Binding var isChecked: Bool\n\n var body: some View {\n HStack {\n CheckboxView(isChecked: $isChecked)\n Text(title)\n Spacer()\n }\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Assistants/AssistantConfigurationProvider.swift",
"content": "//\n// AssistantConfigurationProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/17/23.\n//\n\nimport Foundation\nimport SwiftOpenAI\n\n@Observable\nclass AssistantConfigurationProvider {\n // MARK: - Initializer\n\n init(service: OpenAIService) {\n self.service = service\n }\n\n var assistant: AssistantObject?\n var assistants = [AssistantObject]()\n var avatarURL: URL?\n var assistantDeletionStatus: DeletionStatus?\n\n func listAssistants()\n async throws\n {\n do {\n let assistants = try await service.listAssistants(limit: nil, order: nil, after: nil, before: nil)\n self.assistants = assistants.data\n } catch {\n debugPrint(\"\\(error)\")\n }\n }\n\n func deleteAssistant(\n id: String)\n async throws\n {\n do {\n assistantDeletionStatus = try await service.deleteAssistant(id: id)\n } catch {\n debugPrint(\"\\(error)\")\n }\n }\n\n func createAssistant(\n parameters: AssistantParameters)\n async throws\n {\n do {\n assistant = try await service.createAssistant(parameters: parameters)\n } catch {\n debugPrint(\"\\(error)\")\n }\n }\n\n func createAvatar(\n prompt: String)\n async throws\n {\n do {\n let avatarURLs = try await service.createImages(parameters: .init(prompt: prompt, model: .dallE3)).data?.compactMap(\\.url)\n avatarURL = URL(string: avatarURLs?.first ?? \"\")\n } catch {\n debugPrint(\"\\(error)\")\n }\n }\n\n // TODO: Create demo for this.\n func createVStore() async throws {\n _ = try await service.createVectorStore(parameters: .init(name: \"Personal Data\"))\n }\n\n // MARK: - Private Properties\n\n private let service: OpenAIService\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Assistants/AssistantStreamDemoScreen.swift",
"content": "//\n// AssistantStreamDemoScreen.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 3/19/24.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - AssistantStartThreadScreen\n\npublic struct AssistantStartThreadScreen: View {\n init(assistant: AssistantObject, service: OpenAIService) {\n self.assistant = assistant\n self.service = service\n _threadProvider = State(initialValue: AssistantThreadConfigurationProvider(service: service))\n }\n\n public var body: some View {\n ScrollView {\n VStack {\n Text(assistant.name ?? \"No name\")\n .font(.largeTitle).bold()\n Text(\"For function call demo type: Create an image of a cow.\")\n .font(.caption)\n switch tutorialStage {\n case .crateThread:\n createThreadView\n\n case .createMessage(let threadID):\n createMessageView(threadID: threadID)\n\n case .createRunAndStream(let message):\n createRunAndStreamView(threadID: message.threadID)\n\n case .showStream(let threadID):\n showStreamView(threadID: threadID)\n }\n }\n .padding()\n }\n }\n\n enum TutorialState {\n case crateThread\n case createMessage(threadID: String)\n case createRunAndStream(message: MessageObject)\n case showStream(threadID: String)\n }\n\n let assistant: AssistantObject\n let service: OpenAIService\n\n var createThreadView: some View {\n Button {\n Task {\n try await threadProvider.createThread()\n if let threadID = threadProvider.thread?.id {\n tutorialStage = .createMessage(threadID: threadID)\n }\n }\n } label: {\n Text(\"Step 1: Create a thread\")\n }\n }\n\n func createMessageView(threadID: String) -> some View {\n VStack(alignment: .leading, spacing: 20) {\n Text(\"Nice! Thread created id:\")\n .font(.title).bold()\n Text(\"\\(threadID)\")\n Text(\"Step 2: Create a message in the text field and press the button ✈️\").font(.title)\n Text(\"eg: Briefly explain SwiftUI state.\")\n HStack(spacing: 4) {\n TextField(\"Enter prompt\", text: $prompt, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n Button {\n Task {\n try await threadProvider.createMessage(\n threadID: threadID,\n parameters: .init(role: .user, content: .stringContent(prompt)))\n if let message = threadProvider.message {\n tutorialStage = .createRunAndStream(message: message)\n }\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n }\n }\n .padding()\n }\n\n func createRunAndStreamView(threadID: String) -> some View {\n VStack(spacing: 20) {\n Text(\"Nice! Message created with id:\")\n .font(.title2).bold()\n Text(\"\\(threadID)\")\n .font(.body)\n Text(\"Step 3: Run and Stream the message\")\n .font(.title2)\n\n Button {\n Task {\n tutorialStage = .showStream(threadID: threadID)\n try await threadProvider.createRunAndStreamMessage(\n threadID: threadID,\n parameters: .init(assistantID: assistant.id))\n }\n } label: {\n Text(\"Run and Stream the message\")\n }\n .buttonStyle(.borderedProminent)\n ChatStreamView(provider: threadProvider, prompt: prompt, assistantName: assistant.name)\n }\n }\n\n func showStreamView(threadID: String) -> some View {\n VStack {\n TextField(\"Enter prompt\", text: $prompt, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n Button {\n Task {\n try await threadProvider.createMessage(\n threadID: threadID,\n parameters: .init(role: .user, content: .stringContent(prompt)))\n threadProvider.messageText = \"\"\n threadProvider.toolOuptutMessage = \"\"\n try await threadProvider.createRunAndStreamMessage(\n threadID: threadID,\n parameters: .init(assistantID: assistant.id))\n }\n } label: {\n Text(\"Run and Stream the message\")\n }\n .buttonStyle(.borderedProminent)\n ChatStreamView(provider: threadProvider, prompt: prompt, assistantName: assistant.name)\n }\n }\n\n @State private var threadProvider: AssistantThreadConfigurationProvider\n @State private var prompt = \"\"\n\n @State private var tutorialStage = TutorialState.crateThread\n}\n\n// MARK: - ChatStreamView\n\nstruct ChatStreamView: View {\n let provider: AssistantThreadConfigurationProvider\n let prompt: String\n let assistantName: String?\n\n var body: some View {\n VStack(spacing: 24) {\n VStack(alignment: .leading, spacing: 16) {\n Text(\"User:\")\n .font(.title2)\n .bold()\n Text(prompt)\n }\n .frame(maxWidth: .infinity, alignment: .leading)\n\n VStack(alignment: .leading, spacing: 16) {\n Text(\"\\(assistantName ?? \"Assistant\"):\")\n .font(.title2)\n .bold()\n if !provider.toolOuptutMessage.isEmpty {\n Text(\"Code Intepreter\")\n .foregroundColor(.mint)\n .fontDesign(.monospaced)\n .bold()\n .font(.title3)\n Text(LocalizedStringKey(provider.toolOuptutMessage))\n .fontDesign(.monospaced)\n }\n if !provider.messageText.isEmpty {\n Text(\"Message\")\n .font(.title3)\n .foregroundColor(.mint)\n .fontDesign(.monospaced)\n .bold()\n Text(provider.messageText)\n .font(.body)\n }\n if !provider.functionCallOutput.isEmpty {\n Text(\"Function Call\")\n .font(.title3)\n .foregroundColor(.pink)\n .fontDesign(.monospaced)\n .bold()\n Text(provider.functionCallOutput)\n .font(.body)\n }\n }\n .frame(maxWidth: .infinity, alignment: .leading)\n }\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Assistants/AssistantThreadConfigurationProvider.swift",
"content": "//\n// AssistantThreadConfigurationProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 3/19/24.\n//\n\nimport Foundation\nimport SwiftOpenAI\n\n@Observable\nclass AssistantThreadConfigurationProvider {\n // MARK: - Initializer\n\n init(service: OpenAIService) {\n self.service = service\n }\n\n var thread: ThreadObject?\n var message: MessageObject?\n var runObject: RunObject?\n var messageText = \"\"\n var toolOuptutMessage = \"\"\n var functionCallOutput = \"\"\n\n func createThread()\n async throws\n {\n do {\n thread = try await service.createThread(parameters: .init())\n } catch {\n print(\"THREAD ERROR: \\(error)\")\n }\n }\n\n func createMessage(\n threadID: String,\n parameters: MessageParameter)\n async throws\n {\n do {\n message = try await service.createMessage(threadID: threadID, parameters: parameters)\n } catch {\n print(\"THREAD ERROR: \\(error)\")\n }\n }\n\n func createRunAndStreamMessage(\n threadID: String,\n parameters: RunParameter)\n async throws\n {\n do {\n let stream = try await service.createRunStream(threadID: threadID, parameters: parameters)\n for try await result in stream {\n switch result {\n case .threadMessageDelta(let messageDelta):\n let content = messageDelta.delta.content.first\n switch content {\n case .imageFile, .imageUrl, nil:\n break\n case .text(let textContent):\n messageText += textContent.text.value\n }\n\n case .threadRunStepDelta(let runStepDelta):\n let toolCall = runStepDelta.delta.stepDetails.toolCalls?.first?.toolCall\n switch toolCall {\n case .codeInterpreterToolCall(let toolCall):\n toolOuptutMessage += toolCall.input ?? \"\"\n case .fileSearchToolCall(let toolCall):\n print(\"PROVIDER: File search tool call \\(toolCall)\")\n case .functionToolCall(let toolCall):\n functionCallOutput += toolCall.arguments\n case nil:\n print(\"PROVIDER: tool call nil\")\n }\n\n case .threadRunCompleted(let runObject):\n print(\"PROVIDER: the run is completed - \\(runObject)\")\n\n default: break\n }\n }\n } catch {\n print(\"THREAD ERROR: \\(error)\")\n }\n }\n\n // MARK: - Private Properties\n\n private let service: OpenAIService\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Assistants/AssistantsListDemoView.swift",
"content": "//\n// AssistantsListDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 3/19/24.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - AssistantObject + Identifiable\n\nextension AssistantObject: Identifiable { }\n\n// MARK: - AssistantsListDemoView\n\npublic struct AssistantsListDemoView: View {\n public var body: some View {\n NavigationView {\n ForEach(assistants) { assistant in\n NavigationLink(destination: AssistantStartThreadScreen(assistant: assistant, service: service)) {\n VStack(alignment: .leading) {\n Text(assistant.name ?? \"No name\")\n .font(.title).bold()\n Text(assistant.description ?? \"No Description\")\n .font(.subheadline).fontWeight(.medium)\n Text(assistant.id)\n .font(.caption).fontWeight(.bold)\n }\n .padding()\n .frame(maxWidth: .infinity, alignment: .leading)\n .background {\n RoundedRectangle(cornerRadius: 25.0)\n .fill(.mint)\n }\n .padding()\n }\n }\n }\n }\n\n let assistants: [AssistantObject]\n let service: OpenAIService\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/AudioDemo/AudioDemoView.swift",
"content": "//\n// AudioDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/19/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct AudioDemoView: View {\n init(service: OpenAIService) {\n _audioProvider = State(initialValue: AudioProvider(service: service))\n }\n\n var textArea: some View {\n HStack(spacing: 4) {\n TextField(\"Enter message to convert to speech\", text: $prompt, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n Button {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n try await audioProvider.speech(parameters: .init(model: .tts1, input: prompt, voice: .shimmer))\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n }\n .padding()\n }\n\n var transcriptionView: some View {\n VStack {\n Text(\"Tap this button to use the transcript API, a `m4a` file has been added to the app's bundle.\")\n .font(.callout)\n .padding()\n Button(\"Transcript\") {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the function exits\n /// ['flac', 'm4a', 'mp3', 'mp4', 'mpeg', 'mpga', 'oga', 'ogg', 'wav', 'webm'] (supported formats)\n let data = try contentLoader.loadBundledContent(fromFileNamed: \"narcos\", ext: \"m4a\")\n try await audioProvider.transcript(parameters: .init(fileName: \"narcos.m4a\", file: data))\n }\n }\n .buttonStyle(.borderedProminent)\n Text(audioProvider.transcription)\n .padding()\n }\n }\n\n var translationView: some View {\n VStack {\n Text(\"Tap this button to use the translationView API, a `m4a` file in German has been added to the app's bundle.\")\n .font(.callout)\n .padding()\n Button(\"Translate\") {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the function exits\n /// ['flac', 'm4a', 'mp3', 'mp4', 'mpeg', 'mpga', 'oga', 'ogg', 'wav', 'webm'] (supported formats)\n let data = try contentLoader.loadBundledContent(fromFileNamed: \"german\", ext: \"m4a\")\n try await audioProvider.translate(parameters: .init(fileName: \"german.m4a\", file: data))\n }\n }\n .buttonStyle(.borderedProminent)\n Text(audioProvider.translation)\n .padding()\n }\n }\n\n var body: some View {\n ScrollView {\n VStack {\n VStack {\n Text(\"Add a text to convert to speech\")\n textArea\n }\n transcriptionView\n .padding()\n Divider()\n translationView\n .padding()\n }\n }.overlay(\n Group {\n if isLoading {\n ProgressView()\n } else {\n EmptyView()\n }\n })\n .safeAreaPadding()\n }\n\n @State private var audioProvider: AudioProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n\n private let contentLoader = ContentLoader()\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/AudioDemo/AudioProvider.swift",
"content": "//\n// AudioProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/19/23.\n//\n\nimport AVFoundation\nimport SwiftOpenAI\nimport SwiftUI\n\n@Observable\nclass AudioProvider {\n init(service: OpenAIService) {\n self.service = service\n }\n\n var transcription = \"\"\n var translation = \"\"\n var speechErrorMessage = \"\"\n var audioPlayer: AVAudioPlayer?\n\n func transcript(\n parameters: AudioTranscriptionParameters)\n async throws\n {\n do {\n transcription = try await service.createTranscription(parameters: parameters).text\n } catch {\n transcription = \"\\(error)\"\n }\n }\n\n func translate(\n parameters: AudioTranslationParameters)\n async throws\n {\n do {\n translation = try await service.createTranslation(parameters: parameters).text\n } catch {\n translation = \"\\(error)\"\n }\n }\n\n func speech(\n parameters: AudioSpeechParameters)\n async throws\n {\n do {\n let speech = try await service.createSpeech(parameters: parameters).output\n playAudio(from: speech)\n } catch let error as APIError {\n speechErrorMessage = error.displayDescription\n } catch {\n speechErrorMessage = \"\\(error)\"\n }\n }\n\n private let service: OpenAIService\n\n private func playAudio(from data: Data) {\n do {\n // Initialize the audio player with the data\n audioPlayer = try AVAudioPlayer(data: data)\n audioPlayer?.prepareToPlay()\n audioPlayer?.play()\n } catch {\n // Handle errors\n print(\"Error playing audio: \\(error.localizedDescription)\")\n }\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatDemo/ChatDemoView.swift",
"content": "//\n// ChatDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/19/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct ChatDemoView: View {\n init(service: OpenAIService, customModel: String? = nil) {\n self.customModel = customModel\n _chatProvider = State(initialValue: ChatProvider(service: service))\n }\n\n enum ChatConfig {\n case chatCompletion\n case chatCompeltionStream\n }\n\n let customModel: String?\n\n var body: some View {\n ScrollView {\n VStack {\n picker\n textArea\n Text(chatProvider.errorMessage)\n .foregroundColor(.red)\n switch selectedSegment {\n case .chatCompeltionStream:\n streamedChatResultView\n case .chatCompletion:\n chatCompletionResultView\n }\n }\n }\n .overlay(\n Group {\n if isLoading {\n ProgressView()\n } else {\n EmptyView()\n }\n })\n }\n\n var picker: some View {\n Picker(\"Options\", selection: $selectedSegment) {\n Text(\"Chat Completion\").tag(ChatConfig.chatCompletion)\n Text(\"Chat Completion stream\").tag(ChatConfig.chatCompeltionStream)\n }\n .pickerStyle(SegmentedPickerStyle())\n .padding()\n }\n\n var textArea: some View {\n HStack(spacing: 4) {\n TextField(\"Enter prompt\", text: $prompt, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n Button {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n\n let content = ChatCompletionParameters.Message.ContentType.text(prompt)\n prompt = \"\"\n let model: Model =\n if let customModel, !customModel.isEmpty {\n .custom(customModel)\n } else {\n .gpt4o\n }\n\n let parameters = ChatCompletionParameters(\n messages: [.init(\n role: .user,\n content: content)],\n model: model)\n switch selectedSegment {\n case .chatCompletion:\n try await chatProvider.startChat(parameters: parameters)\n case .chatCompeltionStream:\n try await chatProvider.startStreamedChat(parameters: parameters)\n }\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n }\n .padding()\n }\n\n /// stream = `false`\n var chatCompletionResultView: some View {\n ForEach(Array(chatProvider.messages.enumerated()), id: \\.offset) { _, val in\n VStack(spacing: 0) {\n Text(\"\\(val)\")\n }\n }\n }\n\n /// stream = `true`\n var streamedChatResultView: some View {\n VStack {\n Button(\"Cancel stream\") {\n chatProvider.cancelStream()\n }\n Text(chatProvider.message)\n }\n }\n\n @State private var chatProvider: ChatProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n @State private var selectedSegment = ChatConfig.chatCompeltionStream\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatDemo/ChatProvider.swift",
"content": "//\n// ChatProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/19/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n@Observable\nclass ChatProvider {\n init(service: OpenAIService) {\n self.service = service\n }\n\n var messages = [String]()\n var errorMessage = \"\"\n var message = \"\"\n var usage: ChatUsage?\n\n func startChat(\n parameters: ChatCompletionParameters)\n async throws\n {\n do {\n let response = try await service.startChat(parameters: parameters)\n let choices = response.choices\n let chatUsage = response.usage\n let logprobs = choices?.compactMap(\\.logprobs)\n dump(logprobs)\n messages = choices?.compactMap(\\.message?.content) ?? []\n dump(chatUsage)\n usage = chatUsage\n } catch APIError.responseUnsuccessful(let description, let statusCode) {\n self.errorMessage = \"Network error with status code: \\(statusCode) and description: \\(description)\"\n } catch {\n errorMessage = error.localizedDescription\n }\n }\n\n func startStreamedChat(\n parameters: ChatCompletionParameters)\n async throws\n {\n streamTask = Task {\n do {\n let stream = try await service.startStreamedChat(parameters: parameters)\n for try await result in stream {\n let content = result.choices?.first?.delta?.content ?? \"\"\n self.message += content\n }\n } catch APIError.responseUnsuccessful(let description, let statusCode) {\n self.errorMessage = \"Network error with status code: \\(statusCode) and description: \\(description)\"\n } catch {\n self.errorMessage = error.localizedDescription\n }\n }\n }\n\n func cancelStream() {\n streamTask?.cancel()\n }\n\n private let service: OpenAIService\n private var streamTask: Task?\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatFunctionsCall/ChatMessageDisplayModel.swift",
"content": "//\n// ChatMessageDisplayModel.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/13/23.\n//\n\nimport Foundation\nimport SwiftOpenAI\n\nstruct ChatMessageDisplayModel: Identifiable {\n init(\n id: UUID = UUID(),\n content: DisplayContent,\n origin: MessageOrigin)\n {\n self.id = id\n self.content = content\n self.origin = origin\n }\n\n enum DisplayContent: Equatable {\n case content(DisplayMessageType)\n case error(String)\n\n static func ==(lhs: DisplayContent, rhs: DisplayContent) -> Bool {\n switch (lhs, rhs) {\n case (.content(let a), .content(let b)):\n a == b\n case (.error(let a), .error(let b)):\n a == b\n default:\n false\n }\n }\n\n struct DisplayMessageType: Equatable {\n var text: String?\n var urls: [URL]? = nil\n }\n }\n\n enum MessageOrigin {\n case received(ReceivedSource)\n case sent\n\n enum ReceivedSource {\n case gpt\n case dalle\n }\n }\n\n let id: UUID\n var content: DisplayContent\n let origin: MessageOrigin\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatFunctionsCall/ChatMessageView.swift",
"content": "//\n// ChatMessageView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/13/23.\n//\n\nimport Foundation\nimport SwiftUI\n\nstruct ChatMessageView: View {\n let message: ChatMessageDisplayModel\n\n @ViewBuilder\n var header: some View {\n switch message.origin {\n case .received(let source):\n switch source {\n case .gpt:\n headerWith(\"wand.and.stars\", title: \"CHATGPT\")\n case .dalle:\n EmptyView()\n }\n\n case .sent:\n headerWith(\"person.circle\", title: \"USER\")\n }\n }\n\n var body: some View {\n VStack(alignment: .leading, spacing: 8) {\n header\n Group {\n switch message.content {\n case .content(let mediaType):\n VStack(alignment: .leading, spacing: Sizes.spacingMedium) {\n imagesFrom(urls: mediaType.urls ?? [])\n chatMessageViewWith(mediaType.text)\n }\n .transition(.opacity)\n\n case .error(let error):\n Text(error)\n .padding()\n .font(.callout)\n .background(\n RoundedRectangle(cornerRadius: 20)\n .foregroundColor(.red.opacity(0.7)))\n }\n }\n .padding(.leading, 23)\n }\n }\n\n @ViewBuilder\n func chatMessageViewWith(\n _ text: String?)\n -> some View\n {\n if let text {\n if text.isEmpty {\n LoadingView()\n } else {\n Text(text)\n .font(.body)\n }\n } else {\n EmptyView()\n }\n }\n\n func headerWith(\n _ systemImageName: String,\n title: String)\n -> some View\n {\n HStack {\n Image(systemName: systemImageName)\n .resizable()\n .frame(width: 16, height: 16)\n Text(title)\n .font(.caption2)\n }\n .foregroundColor(.gray.opacity(0.9))\n }\n\n func imagesFrom(\n urls: [URL])\n -> some View\n {\n ScrollView(.horizontal, showsIndicators: false) {\n HStack(spacing: 8) {\n ForEach(urls, id: \\.self) { url in\n URLImageView(url: url)\n }\n }\n }\n }\n}\n\n#Preview {\n VStack {\n ChatMessageView(message: .init(\n content: .content(.init(text: \"What is the capital of Peru? and what is the population\")),\n origin: .sent))\n ChatMessageView(message: .init(content: .content(.init(text: \"Lima, an its 28 million habitants.\")), origin: .received(.gpt)))\n ChatMessageView(message: .init(\n content: .content(.init(\n text: \"The image you requested is ready 🐱\",\n urls: [\n URL(\n string: \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\")!,\n ])),\n origin: .received(.dalle)))\n ChatMessageView(message: .init(content: .content(.init(text: \"\")), origin: .received(.gpt)))\n }\n .padding()\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatFunctionsCall/Completion/ChatFunctionCallDemoView.swift",
"content": "//\n// ChatFunctionCallDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/14/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct ChatFunctionCallDemoView: View {\n init(service: OpenAIService, customModel: String? = nil) {\n self.customModel = customModel\n _chatProvider = State(initialValue: ChatFunctionCallProvider(service: service, customModel: customModel))\n }\n\n let customModel: String?\n\n var body: some View {\n ScrollViewReader { proxy in\n VStack {\n List(chatProvider.chatDisplayMessages) { message in\n ChatMessageView(message: message)\n .listRowSeparator(.hidden)\n }\n .listStyle(.plain)\n .onChange(of: chatProvider.chatDisplayMessages.last?.content) {\n let lastMessage = chatProvider.chatDisplayMessages.last\n if let id = lastMessage?.id {\n proxy.scrollTo(id, anchor: .bottom)\n }\n }\n textArea\n }\n }\n }\n\n var textArea: some View {\n HStack(spacing: 0) {\n VStack(alignment: .leading, spacing: 0) {\n textField\n .padding(.vertical, Sizes.spacingExtraSmall)\n .padding(.horizontal, Sizes.spacingSmall)\n }\n .padding(.vertical, Sizes.spacingExtraSmall)\n .padding(.horizontal, Sizes.spacingExtraSmall)\n .background(\n RoundedRectangle(cornerRadius: 20)\n .stroke(.gray, lineWidth: 1))\n .padding(.horizontal, Sizes.spacingMedium)\n textAreSendButton\n }\n .padding(.horizontal)\n .disabled(isLoading)\n }\n\n var textField: some View {\n TextField(\n \"How Can I help you today?\",\n text: $prompt,\n axis: .vertical)\n }\n\n var textAreSendButton: some View {\n Button {\n Task {\n /// Loading UI\n isLoading = true\n defer { isLoading = false }\n // Clears text field.\n let userPrompt = prompt\n prompt = \"\"\n try await chatProvider.startChat(prompt: userPrompt)\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n .tint(ThemeColor.tintColor)\n .disabled(prompt.isEmpty)\n }\n\n @State private var chatProvider: ChatFunctionCallProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatFunctionsCall/Completion/ChatFunctionCallProvider.swift",
"content": "//\n// ChatFunctionCallProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/14/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - FunctionCallDefinition\n\nenum FunctionCallDefinition: String, CaseIterable {\n case createImage = \"create_image\"\n\n // Add more functions if needed, parallel function calling is supported.\n\n var functionTool: ChatCompletionParameters.Tool {\n switch self {\n case .createImage:\n .init(function: .init(\n name: rawValue,\n strict: nil,\n description: \"call this function if the request asks to generate an image\",\n parameters: .init(\n type: .object,\n properties: [\n \"prompt\": .init(type: .string, description: \"The exact prompt passed in.\"),\n \"count\": .init(type: .integer, description: \"The number of images requested\"),\n ],\n required: [\"prompt\", \"count\"])))\n }\n }\n}\n\n// MARK: - ChatFunctionCallProvider\n\n@Observable\nclass ChatFunctionCallProvider {\n init(service: OpenAIService, customModel: String? = nil) {\n self.service = service\n self.customModel = customModel\n }\n\n // MARK: - Initializer\n\n let customModel: String?\n\n // MARK: - Public Properties\n\n /// To be used for UI purposes.\n var chatDisplayMessages = [ChatMessageDisplayModel]()\n\n @MainActor\n func generateImage(arguments: String) async throws -> String {\n let dictionary = arguments.toDictionary()!\n let prompt = dictionary[\"prompt\"] as! String\n\n let assistantMessage = ChatMessageDisplayModel(\n content: .content(.init(text: \"Generating images...\")),\n origin: .received(.gpt))\n updateLastAssistantMessage(assistantMessage)\n\n let urls = try await service.createImages(parameters: .init(prompt: prompt, model: .dallE3)).data?.compactMap(\\.url)\n .compactMap { URL(string: $0) } ?? []\n\n let dalleAssistantMessage = ChatMessageDisplayModel(\n content: .content(.init(text: nil, urls: urls)),\n origin: .received(.dalle))\n updateLastAssistantMessage(dalleAssistantMessage)\n\n return prompt\n }\n\n // MARK: - Public Methods\n\n func startChat(\n prompt: String)\n async throws\n {\n defer {\n chatMessageParameters = []\n }\n\n await startNewUserDisplayMessage(prompt)\n\n await startNewAssistantEmptyDisplayMessage()\n\n /// # Step 1: send the conversation and available functions to the model\n let userMessage = createUserMessage(prompt)\n chatMessageParameters.append(userMessage)\n\n let tools = FunctionCallDefinition.allCases.map(\\.functionTool)\n\n let model: Model =\n if let customModel, !customModel.isEmpty {\n .custom(customModel)\n } else {\n .gpt41106Preview\n }\n\n let parameters = ChatCompletionParameters(\n messages: chatMessageParameters,\n model: model,\n toolChoice: ToolChoice.auto,\n tools: tools)\n\n do {\n let chat = try await service.startChat(parameters: parameters)\n\n guard let assistantMessage = chat.choices?.first?.message else { return }\n\n let content = assistantMessage.content ?? \"\"\n\n await updateLastAssistantMessage(.init(content: .content(.init(text: content)), origin: .received(.gpt)))\n\n /// # Step 2: check if the model wanted to call a function\n if let toolCalls = assistantMessage.toolCalls {\n /// # Step 3: call the function\n availableFunctions = [.createImage: generateImage(arguments:)]\n // Append the `assistantMessage` in to the `chatMessageParameters` to extend the conversation\n let parameterAssistantMessage = ChatCompletionParameters.Message(\n role: .assistant,\n content: .text(content), toolCalls: assistantMessage.toolCalls)\n\n chatMessageParameters.append(parameterAssistantMessage)\n\n /// # Step 4: send the info for each function call and function response to the model\n for toolCall in toolCalls {\n let name = toolCall.function.name\n let id = toolCall.id\n let functionToCall = availableFunctions[FunctionCallDefinition(rawValue: name!)!]!\n let arguments = toolCall.function.arguments\n let content = try await functionToCall(arguments)\n let toolMessage = ChatCompletionParameters.Message(\n role: .tool,\n content: .text(content),\n name: name,\n toolCallID: id)\n chatMessageParameters.append(toolMessage)\n }\n\n /// # get a new response from the model where it can see the function response\n await continueChat()\n }\n\n } catch let error as APIError {\n // If an error occurs, update the UI to display the error message.\n await updateLastAssistantMessage(.init(content: .error(\"\\(error.displayDescription)\"), origin: .received(.gpt)))\n }\n }\n\n func continueChat() async {\n let systemMessage = ChatCompletionParameters.Message(\n role: .system,\n content: .text(\n \"You are an artist powered by AI, if the messages has a tool message you will weight that bigger in order to create a response, and you are providing me an image, you always respond in readable language and never providing URLs of images, most of the times you add an emoji on your responses if makes sense, do not describe the image. also always offer more help\"))\n\n chatMessageParameters.insert(systemMessage, at: 0)\n\n let model: Model =\n if let customModel, !customModel.isEmpty {\n .custom(customModel)\n } else {\n .gpt41106Preview\n }\n\n let paramsForChat = ChatCompletionParameters(\n messages: chatMessageParameters,\n model: model)\n do {\n let chat = try await service.startChat(parameters: paramsForChat)\n guard let assistantMessage = chat.choices?.first?.message else { return }\n await updateLastAssistantMessage(.init(content: .content(.init(text: assistantMessage.content)), origin: .received(.gpt)))\n } catch {\n // If an error occurs, update the UI to display the error message.\n await updateLastAssistantMessage(.init(content: .error(\"\\(error)\"), origin: .received(.gpt)))\n }\n }\n\n func createUserMessage(\n _ prompt: String)\n -> ChatCompletionParameters.Message\n {\n .init(role: .user, content: .text(prompt))\n }\n\n // MARK: - Private Properties\n\n private let service: OpenAIService\n private var lastDisplayedMessageID: UUID?\n /// To be used for a new request\n private var chatMessageParameters = [ChatCompletionParameters.Message]()\n private var availableFunctions = [FunctionCallDefinition: @MainActor (String) async throws -> String]()\n\n // MARK: - Private Methods\n\n @MainActor\n private func startNewUserDisplayMessage(_ prompt: String) {\n let startingMessage = ChatMessageDisplayModel(\n content: .content(.init(text: prompt)),\n origin: .sent)\n addMessage(startingMessage)\n }\n\n @MainActor\n private func startNewAssistantEmptyDisplayMessage() {\n let newMessage = ChatMessageDisplayModel(\n content: .content(.init(text: \"\")),\n origin: .received(.gpt))\n addMessage(newMessage)\n }\n\n @MainActor\n private func updateLastAssistantMessage(\n _ message: ChatMessageDisplayModel)\n {\n guard let id = lastDisplayedMessageID, let index = chatDisplayMessages.firstIndex(where: { $0.id == id }) else { return }\n\n var lastMessage = chatDisplayMessages[index]\n\n switch message.content {\n case .content(let newMedia):\n switch lastMessage.content {\n case .content(let lastMedia):\n var updatedMedia = lastMedia\n if\n let newText = newMedia.text,\n var lastMediaText = lastMedia.text\n {\n lastMediaText += newText\n updatedMedia.text = lastMediaText\n } else {\n updatedMedia.text = \"\"\n }\n if let urls = newMedia.urls {\n updatedMedia.urls = urls\n }\n lastMessage.content = .content(updatedMedia)\n\n case .error:\n break\n }\n\n case .error:\n lastMessage.content = message.content\n }\n\n chatDisplayMessages[index] = ChatMessageDisplayModel(\n id: id,\n content: lastMessage.content,\n origin: message.origin)\n }\n\n @MainActor\n private func addMessage(_ message: ChatMessageDisplayModel) {\n let newMessageId = message.id\n lastDisplayedMessageID = newMessageId\n withAnimation {\n chatDisplayMessages.append(message)\n }\n }\n}\n\nextension String {\n fileprivate func toDictionary() -> [String: Any]? {\n guard let jsonData = data(using: .utf8) else {\n print(\"Failed to convert JSON string to Data.\")\n return nil\n }\n\n do {\n return try JSONSerialization.jsonObject(with: jsonData, options: []) as? [String: Any]\n } catch {\n print(\"Failed to deserialize JSON: \\(error.localizedDescription)\")\n return nil\n }\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatFunctionsCall/Stream/ChatFunctionsCallStreamProvider.swift",
"content": "//\n// ChatFunctionsCallStreamProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/6/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - FunctionCallStreamedResponse\n\n/// This is a demo in how to implement parallel function calling when using the completion API stream = true\n\nstruct FunctionCallStreamedResponse {\n let name: String\n let id: String\n let toolCall: ToolCall\n var argument: String\n}\n\n// MARK: - ChatFunctionsCallStreamProvider\n\n@Observable\nclass ChatFunctionsCallStreamProvider {\n init(service: OpenAIService, customModel: String? = nil) {\n self.service = service\n self.customModel = customModel\n }\n\n // MARK: - Initializer\n\n let customModel: String?\n\n // MARK: - Public Properties\n\n /// To be used for UI purposes.\n var chatDisplayMessages = [ChatMessageDisplayModel]()\n\n @MainActor\n func generateImage(arguments: String) async throws -> String {\n let dictionary = arguments.toDictionary()!\n let prompt = dictionary[\"prompt\"] as! String\n let count = (dictionary[\"count\"] as? Int) ?? 1\n\n // TODO: Improve the loading state\n let assistantMessage = ChatMessageDisplayModel(\n content: .content(.init(text: \"Generating images...\")),\n origin: .received(.gpt))\n updateLastAssistantMessage(assistantMessage)\n\n let urls = try await service.legacyCreateImages(\n parameters: .init(prompt: prompt, model: .dalle2(.small), numberOfImages: count)).data.compactMap(\\.url)\n\n let dalleAssistantMessage = ChatMessageDisplayModel(\n content: .content(.init(text: nil, urls: urls)),\n origin: .received(.dalle))\n updateLastAssistantMessage(dalleAssistantMessage)\n\n return prompt\n }\n\n // MARK: - Public Methods\n\n func chat(\n prompt: String)\n async throws\n {\n defer {\n functionCallsMap = [:]\n chatMessageParameters = []\n }\n\n await startNewUserDisplayMessage(prompt)\n\n await startNewAssistantEmptyDisplayMessage()\n\n let systemMessage = ChatCompletionParameters.Message(\n role: .system,\n content: .text(\n \"You are an artist powered by AI, if the messages has a tool message you will weight that bigger in order to create a response, and you are providing me an image, you always respond in readable language and never providing URLs of images, most of the times you add an emoji on your responses if makes sense, do not describe the image. also always offer more help\"))\n chatMessageParameters.append(systemMessage)\n\n /// # Step 1: send the conversation and available functions to the model\n let userMessage = createUserMessage(prompt)\n chatMessageParameters.append(userMessage)\n\n let tools = FunctionCallDefinition.allCases.map(\\.functionTool)\n\n let model: Model =\n if let customModel, !customModel.isEmpty {\n .custom(customModel)\n } else {\n .gpt35Turbo1106\n }\n\n let parameters = ChatCompletionParameters(\n messages: chatMessageParameters,\n model: model,\n toolChoice: ToolChoice.auto,\n tools: tools)\n\n do {\n // Begin the chat stream with the updated parameters.\n let stream = try await service.startStreamedChat(parameters: parameters)\n for try await result in stream {\n // Extract the first choice from the stream results, if none exist, exit the loop.\n if let choice = result.choices?.first {\n /// Because we are using the stream API we need to wait to populate\n /// the needed values that comes from the streamed API to construct a valid tool call response.\n /// This is not needed if the stream is set to false in the API completion request.\n /// # Step 2: check if the model wanted to call a function\n if let toolCalls = choice.delta?.toolCalls {\n /// # Step 3: Define the available functions to be called\n availableFunctions = [.createImage: generateImage(arguments:)]\n\n mapStreamedToolCallsResponse(toolCalls)\n }\n\n /// The streamed content to display\n if let newContent = choice.delta?.content {\n await updateLastAssistantMessage(.init(\n content: .content(.init(text: newContent)),\n origin: .received(.gpt)))\n }\n }\n }\n // # extend conversation with assistant's reply\n // Append the `assistantMessage` in to the `chatMessageParameters` to extend the conversation\n if !functionCallsMap.isEmpty {\n let assistantMessage = createAssistantMessage()\n chatMessageParameters.append(assistantMessage)\n /// # Step 4: send the info for each function call and function response to the model\n let toolMessages = try await createToolsMessages()\n chatMessageParameters.append(contentsOf: toolMessages)\n\n // Lastly call the chat again\n await continueChat()\n }\n\n // TUTORIAL\n } catch {\n // If an error occurs, update the UI to display the error message.\n await updateLastAssistantMessage(.init(content: .error(\"\\(error)\"), origin: .received(.gpt)))\n }\n }\n\n func mapStreamedToolCallsResponse(\n _ toolCalls: [ToolCall])\n {\n for toolCall in toolCalls {\n // Intentionally force unwrapped to catch errrors quickly on demo. // This should be properly handled.\n let function = FunctionCallDefinition.allCases[toolCall.index!]\n if var streamedFunctionCallResponse = functionCallsMap[function] {\n streamedFunctionCallResponse.argument += toolCall.function.arguments\n functionCallsMap[function] = streamedFunctionCallResponse\n } else {\n let streamedFunctionCallResponse = FunctionCallStreamedResponse(\n name: toolCall.function.name!,\n id: toolCall.id!,\n toolCall: toolCall,\n argument: toolCall.function.arguments)\n functionCallsMap[function] = streamedFunctionCallResponse\n }\n }\n }\n\n func createUserMessage(\n _ prompt: String)\n -> ChatCompletionParameters.Message\n {\n .init(role: .user, content: .text(prompt))\n }\n\n func createAssistantMessage() -> ChatCompletionParameters.Message {\n var toolCalls = [ToolCall]()\n for (_, functionCallStreamedResponse) in functionCallsMap {\n let toolCall = functionCallStreamedResponse.toolCall\n // Intentionally force unwrapped to catch errrors quickly on demo. // This should be properly handled.\n let messageToolCall = ToolCall(\n id: toolCall.id!,\n function: .init(arguments: toolCall.function.arguments, name: toolCall.function.name!))\n toolCalls.append(messageToolCall)\n }\n return .init(role: .assistant, content: .text(\"\"), toolCalls: toolCalls)\n }\n\n func createToolsMessages() async throws\n -> [ChatCompletionParameters.Message]\n {\n var toolMessages = [ChatCompletionParameters.Message]()\n for (key, functionCallStreamedResponse) in functionCallsMap {\n let name = functionCallStreamedResponse.name\n let id = functionCallStreamedResponse.id\n let functionToCall = availableFunctions[key]!\n let arguments = functionCallStreamedResponse.argument\n let content = try await functionToCall(arguments)\n let toolMessage = ChatCompletionParameters.Message(\n role: .tool,\n content: .text(content),\n name: name,\n toolCallID: id)\n toolMessages.append(toolMessage)\n }\n return toolMessages\n }\n\n func continueChat() async {\n let paramsForChat = ChatCompletionParameters(\n messages: chatMessageParameters,\n model: .gpt41106Preview)\n do {\n // Begin the chat stream with the updated parameters.\n let stream = try await service.startStreamedChat(parameters: paramsForChat)\n for try await result in stream {\n // Extract the first choice from the stream results, if none exist, exit the loop.\n guard let choice = result.choices?.first else { return }\n\n /// The streamed content to display\n if let newContent = choice.delta?.content {\n await updateLastAssistantMessage(.init(content: .content(.init(text: newContent)), origin: .received(.gpt)))\n }\n }\n } catch {\n // If an error occurs, update the UI to display the error message.\n await updateLastAssistantMessage(.init(content: .error(\"\\(error)\"), origin: .received(.gpt)))\n }\n }\n\n // MARK: - Private Properties\n\n private let service: OpenAIService\n private var lastDisplayedMessageID: UUID?\n /// To be used for a new request\n private var chatMessageParameters = [ChatCompletionParameters.Message]()\n private var functionCallsMap = [FunctionCallDefinition: FunctionCallStreamedResponse]()\n private var availableFunctions = [FunctionCallDefinition: @MainActor (String) async throws -> String]()\n\n // MARK: - Private Methods\n\n @MainActor\n private func startNewUserDisplayMessage(_ prompt: String) {\n let startingMessage = ChatMessageDisplayModel(\n content: .content(.init(text: prompt)),\n origin: .sent)\n addMessage(startingMessage)\n }\n\n @MainActor\n private func startNewAssistantEmptyDisplayMessage() {\n let newMessage = ChatMessageDisplayModel(\n content: .content(.init(text: \"\")),\n origin: .received(.gpt))\n addMessage(newMessage)\n }\n\n @MainActor\n private func updateLastAssistantMessage(\n _ message: ChatMessageDisplayModel)\n {\n guard let id = lastDisplayedMessageID, let index = chatDisplayMessages.firstIndex(where: { $0.id == id }) else { return }\n\n var lastMessage = chatDisplayMessages[index]\n\n switch message.content {\n case .content(let newMedia):\n switch lastMessage.content {\n case .content(let lastMedia):\n var updatedMedia = lastMedia\n if\n let newText = newMedia.text,\n var lastMediaText = lastMedia.text\n {\n lastMediaText += newText\n updatedMedia.text = lastMediaText\n } else {\n updatedMedia.text = \"\"\n }\n if let urls = newMedia.urls {\n updatedMedia.urls = urls\n }\n lastMessage.content = .content(updatedMedia)\n\n case .error:\n break\n }\n\n case .error:\n lastMessage.content = message.content\n }\n\n chatDisplayMessages[index] = ChatMessageDisplayModel(\n id: id,\n content: lastMessage.content,\n origin: message.origin)\n }\n\n @MainActor\n private func addMessage(_ message: ChatMessageDisplayModel) {\n let newMessageId = message.id\n lastDisplayedMessageID = newMessageId\n withAnimation {\n chatDisplayMessages.append(message)\n }\n }\n}\n\nextension String {\n fileprivate func toDictionary() -> [String: Any]? {\n guard let jsonData = data(using: .utf8) else {\n print(\"Failed to convert JSON string to Data.\")\n return nil\n }\n\n do {\n return try JSONSerialization.jsonObject(with: jsonData, options: []) as? [String: Any]\n } catch {\n print(\"Failed to deserialize JSON: \\(error.localizedDescription)\")\n return nil\n }\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatFunctionsCall/Stream/ChatFunctionsCalllStreamDemoView.swift",
"content": "//\n// ChatFunctionsCalllStreamDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/6/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct ChatFunctionsCalllStreamDemoView: View {\n init(service: OpenAIService, customModel: String? = nil) {\n self.customModel = customModel\n _chatProvider = State(initialValue: ChatFunctionsCallStreamProvider(service: service, customModel: customModel))\n }\n\n let customModel: String?\n\n var body: some View {\n ScrollViewReader { proxy in\n VStack {\n List(chatProvider.chatDisplayMessages) { message in\n ChatMessageView(message: message)\n .listRowSeparator(.hidden)\n }\n .listStyle(.plain)\n .onChange(of: chatProvider.chatDisplayMessages.last?.content) {\n let lastMessage = chatProvider.chatDisplayMessages.last\n if let id = lastMessage?.id {\n proxy.scrollTo(id, anchor: .bottom)\n }\n }\n textArea\n }\n }\n }\n\n var textArea: some View {\n HStack(spacing: 0) {\n VStack(alignment: .leading, spacing: 0) {\n textField\n .padding(.vertical, Sizes.spacingExtraSmall)\n .padding(.horizontal, Sizes.spacingSmall)\n }\n .padding(.vertical, Sizes.spacingExtraSmall)\n .padding(.horizontal, Sizes.spacingExtraSmall)\n .background(\n RoundedRectangle(cornerRadius: 20)\n .stroke(.gray, lineWidth: 1))\n .padding(.horizontal, Sizes.spacingMedium)\n textAreSendButton\n }\n .padding(.horizontal)\n .disabled(isLoading)\n }\n\n var textField: some View {\n TextField(\n \"How Can I help you today?\",\n text: $prompt,\n axis: .vertical)\n }\n\n var textAreSendButton: some View {\n Button {\n Task {\n /// Loading UI\n isLoading = true\n defer { isLoading = false }\n // Clears text field.\n let userPrompt = prompt\n prompt = \"\"\n try await chatProvider.chat(prompt: userPrompt)\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n .tint(ThemeColor.tintColor)\n .disabled(prompt.isEmpty)\n }\n\n @State private var isLoading = false\n @State private var prompt = \"\"\n @State private var chatProvider: ChatFunctionsCallStreamProvider\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatStreamFluidConversationDemo/ChatFluidConversationProvider.swift",
"content": "//\n// ChatFluidConversationProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/4/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n@Observable\nclass ChatFluidConversationProvider {\n init(service: OpenAIService, customModel: String? = nil) {\n self.service = service\n self.customModel = customModel\n }\n\n // MARK: - Initializer\n\n let customModel: String?\n\n // MARK: - Public Properties\n\n /// A collection of messages for display in the UI, representing the conversation.\n var chatMessages = [ChatDisplayMessage]()\n\n // MARK: - Public Methods\n\n func startStreamedChat(\n parameters: ChatCompletionParameters,\n prompt: String)\n async throws\n {\n // Displays the user message in the UI\n await startNewUserDisplayMessage(prompt)\n // Start a new assistant message that is initially empty.\n await startNewAssistantEmptyDisplayMessage()\n\n // Copy the provided parameters and update the messages for the chat stream.\n var localParameters = parameters\n localParameters.messages = parameterMessages\n\n do {\n // Begin the chat stream with the updated parameters.\n let stream = try await service.startStreamedChat(parameters: localParameters)\n for try await result in stream {\n // Extract the first choice from the stream results, if none exist, exit the loop.\n guard let choice = result.choices?.first else { return }\n\n // Store initial `role` and `functionCall` data from the first `choice.delta` for UI display.\n // This information is essential for maintaining context in the conversation and for updating\n // the chat UI with proper role attributions for each message.\n var newDelta = ChatDisplayMessage.Delta(role: \"\", content: \"\")\n if let firstDelta = firstChatMessageResponseDelta[result.id ?? \"\"] {\n // If we have already stored the first delta for this result ID, reuse its role.\n newDelta.role = firstDelta.role!\n } else {\n // Otherwise, store the first delta received for future reference.\n firstChatMessageResponseDelta[result.id ?? \"\"] = choice.delta\n }\n // Assign the content received in the current message to the newDelta.\n newDelta.content = temporalReceivedMessageContent\n // Update the UI with the latest assistant message and the corresponding delta.\n updateLastAssistantMessage(content: choice.delta?.content ?? \"\", delta: newDelta)\n\n // Evaluate the `finishReason` to determine if the conversation has reached a logical end.\n // If so, package the accumulated data into a new message parameter that will be used\n // to enrich context in subsequent API calls, leading to better conversation continuity.\n if let finishReason = choice.finishReason {\n debugPrint(\"FINISH_REASON \\(finishReason)\")\n // Construct a new message parameter with the role and content derived from the delta.\n // Intentionally force unwrapped, if fails is programming error.\n let newMessage = ChatCompletionParameters.Message(\n role: .init(rawValue: newDelta.role)!,\n content: .text(newDelta.content))\n // Append the new message parameter to the collection for future requests.\n updateParameterMessagesArray(newMessage)\n }\n }\n } catch {\n // If an error occurs, update the UI to display the error message.\n updateLastDisplayedMessage(.init(content: .error(\"\\(error)\"), type: .received, delta: nil))\n }\n }\n\n /// Defines the maximum number of parameter messages to retain for context. A larger history can enrich\n /// the language model's responses but be mindful as it will also increase the number of tokens sent in each request,\n /// thus affecting API consumption. A balance is required; a count of 5 is a reasonable starting point.\n private static var parameterMessagesMaxStorageCount = 5\n\n // MARK: - Private Properties\n\n private let service: OpenAIService\n\n /// Accumulates the streamed message content for real-time display updates in the UI.\n private var temporalReceivedMessageContent = \"\"\n /// Tracks the identifier of the last message displayed, enabling updates in the from the streaming API response.\n private var lastDisplayedMessageID: UUID?\n /// Stores the initial chat message's delta, which uniquely includes metadata like `role`.\n private var firstChatMessageResponseDelta = [String: ChatCompletionChunkObject.ChatChoice.Delta]()\n /// Builds a history of messages sent and received, enhancing the chat's context for future requests.\n private var parameterMessages = [ChatCompletionParameters.Message]()\n\n // MARK: - Private Methods\n\n @MainActor\n private func startNewUserDisplayMessage(_ prompt: String) {\n // Updates the UI with\n let startingMessage = ChatDisplayMessage(\n content: .text(prompt),\n type: .sent, delta: nil)\n addMessage(startingMessage)\n // Stores a new\n let newParameterMessage = ChatCompletionParameters.Message(role: .user, content: .text(prompt))\n updateParameterMessagesArray(newParameterMessage)\n }\n\n @MainActor\n private func startNewAssistantEmptyDisplayMessage() {\n firstChatMessageResponseDelta = [:]\n temporalReceivedMessageContent = \"\"\n let newMessage = ChatDisplayMessage(content: .text(temporalReceivedMessageContent), type: .received, delta: nil)\n let newMessageId = newMessage.id\n lastDisplayedMessageID = newMessageId\n addMessage(newMessage)\n }\n\n private func updateLastAssistantMessage(\n content: String,\n delta: ChatDisplayMessage.Delta)\n {\n temporalReceivedMessageContent += content\n guard let id = lastDisplayedMessageID, let index = chatMessages.firstIndex(where: { $0.id == id }) else { return }\n chatMessages[index] = ChatDisplayMessage(\n id: id,\n content: .text(temporalReceivedMessageContent),\n type: .received,\n delta: delta)\n }\n\n @MainActor\n private func addMessage(_ message: ChatDisplayMessage) {\n withAnimation {\n chatMessages.append(message)\n }\n }\n\n private func updateParameterMessagesArray(_ message: ChatCompletionParameters.Message) {\n parameterMessages.append(message)\n debugPrint(\"NEWCOUNT \\(parameterMessages.count) message \\(message)\")\n if parameterMessages.count > Self.parameterMessagesMaxStorageCount {\n debugPrint(\"NEWCOUNT \\(parameterMessages.count) removed message \\(parameterMessages[0])\")\n parameterMessages.removeFirst()\n }\n }\n\n private func updateLastDisplayedMessage(_ message: ChatDisplayMessage) {\n chatMessages[chatMessages.count - 1] = message\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatStreamFluidConversationDemo/ChatStreamFluidConversationDemoView.swift",
"content": "//\n// ChatStreamFluidConversationDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/4/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct ChatStreamFluidConversationDemoView: View {\n init(service: OpenAIService, customModel: String? = nil) {\n self.customModel = customModel\n _chatProvider = State(initialValue: ChatFluidConversationProvider(service: service, customModel: customModel))\n }\n\n enum GPTModel: String, CaseIterable {\n case gpt3dot5 = \"GPT-3.5\"\n case gpt4 = \"GPT-4\"\n }\n\n let customModel: String?\n\n var body: some View {\n ScrollViewReader { proxy in\n VStack {\n picker\n List(chatProvider.chatMessages) { message in\n ChatDisplayMessageView(message: message)\n .listRowSeparator(.hidden)\n }\n .listStyle(.plain)\n .onChange(of: chatProvider.chatMessages.last?.content) {\n let lastMessage = chatProvider.chatMessages.last\n if let id = lastMessage?.id {\n proxy.scrollTo(id, anchor: .bottom)\n }\n }\n textArea\n }\n }\n }\n\n var picker: some View {\n Picker(\"\", selection: $selectedModel) {\n ForEach(GPTModel.allCases, id: \\.self) { model in\n Text(model.rawValue)\n .font(.title)\n .tag(model)\n }\n }\n .pickerStyle(.segmented)\n .padding()\n }\n\n var textArea: some View {\n HStack(spacing: 0) {\n TextField(\n \"How Can I help you today?\",\n text: $prompt,\n axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n textAreButton\n }\n .padding(.horizontal)\n .disabled(isLoading)\n }\n\n var textAreButton: some View {\n Button {\n Task {\n isLoading = true\n defer {\n // ensure isLoading is set to false after the function executes.\n isLoading = false\n prompt = \"\"\n }\n /// Make the request\n let model: Model =\n if let customModel, !customModel.isEmpty {\n .custom(customModel)\n } else {\n selectedModel == .gpt3dot5 ? .gpt35Turbo : .gpt4\n }\n\n try await chatProvider.startStreamedChat(parameters: .init(\n messages: [.init(role: .user, content: .text(prompt))],\n model: model), prompt: prompt)\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n }\n\n @State private var chatProvider: ChatFluidConversationProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n @State private var selectedModel = GPTModel.gpt3dot5\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatStructureOutputTool/ChatStructureOutputToolDemoView.swift",
"content": "//\n// ChatStructureOutputToolDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 8/11/24.\n//\n\nimport Foundation\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct ChatStructureOutputToolDemoView: View {\n init(service: OpenAIService, customModel: String? = nil) {\n self.customModel = customModel\n chatProvider = .init(service: service, customModel: customModel)\n }\n\n let customModel: String?\n\n var body: some View {\n ScrollViewReader { proxy in\n VStack {\n List(chatProvider.chatDisplayMessages) { message in\n ChatMessageView(message: message)\n .listRowSeparator(.hidden)\n }\n .listStyle(.plain)\n .onChange(of: chatProvider.chatDisplayMessages.last?.content) {\n let lastMessage = chatProvider.chatDisplayMessages.last\n if let id = lastMessage?.id {\n proxy.scrollTo(id, anchor: .bottom)\n }\n }\n textArea\n }\n }\n }\n\n var textArea: some View {\n HStack(spacing: 0) {\n VStack(alignment: .leading, spacing: 0) {\n textField\n .padding(.vertical, Sizes.spacingExtraSmall)\n .padding(.horizontal, Sizes.spacingSmall)\n }\n .padding(.vertical, Sizes.spacingExtraSmall)\n .padding(.horizontal, Sizes.spacingExtraSmall)\n .background(\n RoundedRectangle(cornerRadius: 20)\n .stroke(.gray, lineWidth: 1))\n .padding(.horizontal, Sizes.spacingMedium)\n textAreSendButton\n }\n .padding(.horizontal)\n .disabled(isLoading)\n }\n\n var textField: some View {\n TextField(\n \"How Can I help you today?\",\n text: $prompt,\n axis: .vertical)\n }\n\n var textAreSendButton: some View {\n Button {\n Task {\n /// Loading UI\n isLoading = true\n defer { isLoading = false }\n // Clears text field.\n let userPrompt = prompt\n prompt = \"\"\n try await chatProvider.startChat(prompt: userPrompt)\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n .tint(ThemeColor.tintColor)\n .disabled(prompt.isEmpty)\n }\n\n @State private var chatProvider: ChatStructuredOutputToolProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatStructureOutputTool/ChatStructuredOutputToolProvider.swift",
"content": "//\n// ChatStructuredOutputToolProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 8/11/24.\n//\n\nimport Foundation\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - StructuredToolCall\n\nenum StructuredToolCall: String, CaseIterable {\n case structureUI = \"structured_ui\"\n\n var functionTool: ChatCompletionParameters.Tool {\n switch self {\n case .structureUI:\n .init(\n function: .init(\n name: rawValue,\n strict: true,\n description: \"Dynamically generated UI\",\n parameters: structureUISchema))\n }\n }\n\n var structureUISchema: JSONSchema {\n JSONSchema(\n type: .object,\n properties: [\n \"type\": JSONSchema(\n type: .string,\n description: \"The type of the UI component\",\n additionalProperties: false,\n enum: [\"div\", \"button\", \"header\", \"section\", \"field\", \"form\"]),\n \"label\": JSONSchema(\n type: .string,\n description: \"The label of the UI component, used for buttons or form fields\",\n additionalProperties: false),\n \"children\": JSONSchema(\n type: .array,\n description: \"Nested UI components\",\n items: JSONSchema(ref: \"#\"),\n additionalProperties: false),\n \"attributes\": JSONSchema(\n type: .array,\n description: \"Arbitrary attributes for the UI component, suitable for any element\",\n items: JSONSchema(\n type: .object,\n properties: [\n \"name\": JSONSchema(\n type: .string,\n description: \"The name of the attribute, for example onClick or className\",\n additionalProperties: false),\n \"value\": JSONSchema(\n type: .string,\n description: \"The value of the attribute\",\n additionalProperties: false),\n ],\n required: [\"name\", \"value\"],\n additionalProperties: false),\n additionalProperties: false),\n ],\n required: [\"type\", \"label\", \"children\", \"attributes\"],\n additionalProperties: false)\n }\n}\n\n// MARK: - ChatStructuredOutputToolProvider\n\n@Observable\nfinal class ChatStructuredOutputToolProvider {\n init(service: OpenAIService, customModel: String? = nil) {\n self.service = service\n self.customModel = customModel\n }\n\n // MARK: - Init\n\n let customModel: String?\n\n var chatDisplayMessages = [ChatMessageDisplayModel]()\n let systemMessage = ChatCompletionParameters.Message(role: .system, content: .text(\"You are a math tutor\"))\n\n func startChat(\n prompt: String)\n async throws\n {\n await startNewUserDisplayMessage(prompt)\n await startNewAssistantEmptyDisplayMessage()\n\n let userMessage = createUserMessage(prompt)\n chatMessageParameters.append(userMessage)\n\n let model: Model =\n if let customModel, !customModel.isEmpty {\n .custom(customModel)\n } else {\n .gpt4o20240806\n }\n\n let parameters = ChatCompletionParameters(\n messages: [systemMessage] + chatMessageParameters,\n model: model,\n tools: StructuredToolCall.allCases.map(\\.functionTool))\n\n do {\n let chat = try await service.startChat(parameters: parameters)\n guard let assistantMessage = chat.choices?.first?.message else { return }\n let content = assistantMessage.content ?? \"\"\n await updateLastAssistantMessage(.init(content: .content(.init(text: content)), origin: .received(.gpt)))\n if let toolCalls = assistantMessage.toolCalls {\n availableFunctions = [.structureUI: getStructureOutput(arguments:)]\n // Append the `assistantMessage` in to the `chatMessageParameters` to extend the conversation\n let parameterAssistantMessage = ChatCompletionParameters.Message(\n role: .assistant,\n content: .text(content), toolCalls: assistantMessage.toolCalls)\n\n chatMessageParameters.append(parameterAssistantMessage)\n\n /// # Step 4: send the info for each function call and function response to the model\n for toolCall in toolCalls {\n let name = toolCall.function.name\n let id = toolCall.id\n let functionToCall = availableFunctions[StructuredToolCall(rawValue: name!)!]!\n let arguments = toolCall.function.arguments\n let content = functionToCall(arguments)\n let toolMessage = ChatCompletionParameters.Message(\n role: .tool,\n content: .text(content),\n name: name,\n toolCallID: id)\n chatMessageParameters.append(toolMessage)\n }\n\n /// # get a new response from the model where it can see the function response\n await continueChat()\n }\n\n } catch let error as APIError {\n // If an error occurs, update the UI to display the error message.\n await updateLastAssistantMessage(.init(content: .error(\"\\(error.displayDescription)\"), origin: .received(.gpt)))\n }\n }\n\n // MARK: Tool functions\n\n func getStructureOutput(arguments: String) -> String {\n arguments\n }\n\n private let service: OpenAIService\n private var lastDisplayedMessageID: UUID?\n private var chatMessageParameters = [ChatCompletionParameters.Message]()\n private var availableFunctions = [StructuredToolCall: (String) -> String]()\n}\n\n// MARK: UI related\n\nextension ChatStructuredOutputToolProvider {\n func createUserMessage(\n _ prompt: String)\n -> ChatCompletionParameters.Message\n {\n .init(role: .user, content: .text(prompt))\n }\n\n func continueChat() async {\n let model: Model =\n if let customModel, !customModel.isEmpty {\n .custom(customModel)\n } else {\n .gpt4o\n }\n\n let paramsForChat = ChatCompletionParameters(\n messages: chatMessageParameters,\n model: model)\n do {\n let chat = try await service.startChat(parameters: paramsForChat)\n guard let assistantMessage = chat.choices?.first?.message else { return }\n await updateLastAssistantMessage(.init(content: .content(.init(text: assistantMessage.content)), origin: .received(.gpt)))\n } catch {\n // If an error occurs, update the UI to display the error message.\n await updateLastAssistantMessage(.init(content: .error(\"\\(error)\"), origin: .received(.gpt)))\n }\n }\n\n // MARK: - Private Methods\n\n @MainActor\n private func startNewUserDisplayMessage(_ prompt: String) {\n let startingMessage = ChatMessageDisplayModel(\n content: .content(.init(text: prompt)),\n origin: .sent)\n addMessage(startingMessage)\n }\n\n @MainActor\n private func startNewAssistantEmptyDisplayMessage() {\n let newMessage = ChatMessageDisplayModel(\n content: .content(.init(text: \"\")),\n origin: .received(.gpt))\n addMessage(newMessage)\n }\n\n @MainActor\n private func updateLastAssistantMessage(\n _ message: ChatMessageDisplayModel)\n {\n guard let id = lastDisplayedMessageID, let index = chatDisplayMessages.firstIndex(where: { $0.id == id }) else { return }\n\n var lastMessage = chatDisplayMessages[index]\n\n switch message.content {\n case .content(let newMedia):\n switch lastMessage.content {\n case .content(let lastMedia):\n var updatedMedia = lastMedia\n if\n let newText = newMedia.text,\n var lastMediaText = lastMedia.text\n {\n lastMediaText += newText\n updatedMedia.text = lastMediaText\n } else {\n updatedMedia.text = \"\"\n }\n if let urls = newMedia.urls {\n updatedMedia.urls = urls\n }\n lastMessage.content = .content(updatedMedia)\n\n case .error:\n break\n }\n\n case .error:\n lastMessage.content = message.content\n }\n\n chatDisplayMessages[index] = ChatMessageDisplayModel(\n id: id,\n content: lastMessage.content,\n origin: message.origin)\n }\n\n @MainActor\n private func addMessage(_ message: ChatMessageDisplayModel) {\n let newMessageId = message.id\n lastDisplayedMessageID = newMessageId\n withAnimation {\n chatDisplayMessages.append(message)\n }\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatStructuredOutputs/ChatStructuredOutputDemoView.swift",
"content": "//\n// ChatStructuredOutputDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 8/10/24.\n//\n\nimport Foundation\nimport SwiftOpenAI\nimport SwiftUI\n\n/// Schema demo\n///\n/// https://openai.com/index/introducing-structured-outputs-in-the-api/\n///\n/// \"response_format\": {\n/// \"type\": \"json_schema\",\n/// \"json_schema\": {\n/// \"name\": \"math_response\",\n/// \"strict\": true,\n/// \"schema\": {\n/// \"type\": \"object\",\n/// \"properties\": {\n/// \"steps\": {\n/// \"type\": \"array\",\n/// \"items\": {\n/// \"type\": \"object\",\n/// \"properties\": {\n/// \"explanation\": {\n/// \"type\": \"string\"\n/// },\n/// \"output\": {\n/// \"type\": \"string\"\n/// }\n/// },\n/// \"required\": [\"explanation\", \"output\"],\n/// \"additionalProperties\": false\n/// }\n/// },\n/// \"final_answer\": {\n/// \"type\": \"string\"\n/// }\n/// },\n/// \"required\": [\"steps\", \"final_answer\"],\n/// \"additionalProperties\": false\n/// }\n/// }\n/// }\n\n// Steps to define the above Schema:\n\n// 1: Define the Step schema object\n\nlet stepSchema = JSONSchema(\n type: .object,\n properties: [\n \"explanation\": JSONSchema(type: .string),\n \"output\": JSONSchema(\n type: .string),\n ],\n required: [\"explanation\", \"output\"],\n additionalProperties: false)\n\n// 2. Define the steps Array schema.\n\nlet stepsArraySchema = JSONSchema(type: .array, items: stepSchema)\n\n/// 3. Define the final Answer schema.\nlet finalAnswerSchema = JSONSchema(type: .string)\n\n/// 4. Define the response format JSON schema.\nlet responseFormatSchema = JSONSchemaResponseFormat(\n name: \"math_response\",\n strict: true,\n schema: JSONSchema(\n type: .object,\n properties: [\n \"steps\": stepsArraySchema,\n \"final_answer\": finalAnswerSchema,\n ],\n required: [\"steps\", \"final_answer\"],\n additionalProperties: false))\n\n// MARK: - ChatStructuredOutputDemoView\n\n// We can also handle optional values.\n//\n// let weatherSchema = JSONSchemaResponseFormat(\n// name: \"get_weather\",\n// description: \"Fetches the weather in the given location\",\n// strict: true,\n// schema: JSONSchema(\n// type: .object,\n// properties: [\n// \"location\": JSONSchema(\n// type: .string,\n// description: \"The location to get the weather for\"\n// ),\n// \"unit\": JSONSchema(\n// type: .optional(.string),\n// description: \"The unit to return the temperature in\",\n// enum: [\"F\", \"C\"]\n// ),\n// \"thinking\": .init(\n// type: .object,\n// description: \"your thinking\",\n// properties: [\"step\": .init(type: .string)],\n// required: [\"step\"])\n// ],\n// required: [\"location\", \"unit\", \"thinking\"]\n// )\n// )\n\nstruct ChatStructuredOutputDemoView: View {\n init(service: OpenAIService, customModel: String? = nil) {\n self.customModel = customModel\n _chatProvider = State(initialValue: ChatStructuredOutputProvider(service: service, customModel: customModel))\n }\n\n enum ChatConfig {\n case chatCompletion\n case chatCompeltionStream\n }\n\n let customModel: String?\n\n var body: some View {\n ScrollView {\n VStack {\n picker\n textArea\n Text(chatProvider.errorMessage)\n .foregroundColor(.red)\n switch selectedSegment {\n case .chatCompeltionStream:\n streamedChatResultView\n case .chatCompletion:\n chatCompletionResultView\n }\n }\n }\n .overlay(\n Group {\n if isLoading {\n ProgressView()\n } else {\n EmptyView()\n }\n })\n }\n\n var picker: some View {\n Picker(\"Options\", selection: $selectedSegment) {\n Text(\"Chat Completion\").tag(ChatConfig.chatCompletion)\n Text(\"Chat Completion stream\").tag(ChatConfig.chatCompeltionStream)\n }\n .pickerStyle(SegmentedPickerStyle())\n .padding()\n }\n\n var textArea: some View {\n HStack(spacing: 4) {\n TextField(\"Enter prompt\", text: $prompt, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n Button {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n\n let content = ChatCompletionParameters.Message.ContentType.text(prompt)\n prompt = \"\"\n let parameters = ChatCompletionParameters(\n messages: [\n .init(role: .system, content: .text(\"You are a helpful math tutor.\")),\n .init(\n role: .user,\n content: content),\n ],\n model: .gpt4o20240806,\n responseFormat: .jsonSchema(responseFormatSchema))\n switch selectedSegment {\n case .chatCompletion:\n try await chatProvider.startChat(parameters: parameters)\n case .chatCompeltionStream:\n try await chatProvider.startStreamedChat(parameters: parameters)\n }\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n }\n .padding()\n }\n\n /// stream = `false`\n var chatCompletionResultView: some View {\n ForEach(Array(chatProvider.messages.enumerated()), id: \\.offset) { _, val in\n VStack(spacing: 0) {\n Text(\"\\(val)\")\n }\n }\n }\n\n /// stream = `true`\n var streamedChatResultView: some View {\n VStack {\n Button(\"Cancel stream\") {\n chatProvider.cancelStream()\n }\n Text(chatProvider.message)\n }\n }\n\n @State private var chatProvider: ChatStructuredOutputProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n @State private var selectedSegment = ChatConfig.chatCompeltionStream\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatStructuredOutputs/ChatStructuredOutputProvider.swift",
"content": "//\n// ChatStructuredOutputProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 8/10/24.\n//\n\nimport Foundation\nimport SwiftOpenAI\n\n// MARK: - ChatStructuredOutputProvider\n\n@Observable\nfinal class ChatStructuredOutputProvider {\n init(service: OpenAIService, customModel: String? = nil) {\n self.service = service\n self.customModel = customModel\n }\n\n // MARK: - Initializer\n\n let customModel: String?\n\n var message = \"\"\n var messages = [String]()\n var errorMessage = \"\"\n\n // MARK: - Public Methods\n\n func startChat(\n parameters: ChatCompletionParameters)\n async throws\n {\n do {\n let choices = try await service.startChat(parameters: parameters).choices ?? []\n messages = choices.compactMap(\\.message?.content).map { $0.asJsonFormatted() }\n assert(messages.count == 1)\n errorMessage = choices.first?.message?.refusal ?? \"\"\n } catch APIError.responseUnsuccessful(let description, let statusCode) {\n self.errorMessage = \"Network error with status code: \\(statusCode) and description: \\(description)\"\n } catch {\n errorMessage = error.localizedDescription\n }\n }\n\n func startStreamedChat(\n parameters: ChatCompletionParameters)\n async throws\n {\n streamTask = Task {\n do {\n let stream = try await service.startStreamedChat(parameters: parameters)\n for try await result in stream {\n let firstChoiceDelta = result.choices?.first?.delta\n let content = firstChoiceDelta?.refusal ?? firstChoiceDelta?.content ?? \"\"\n self.message += content\n if result.choices?.first?.finishReason != nil {\n self.message = self.message.asJsonFormatted()\n }\n }\n } catch APIError.responseUnsuccessful(let description, let statusCode) {\n self.errorMessage = \"Network error with status code: \\(statusCode) and description: \\(description)\"\n } catch {\n self.errorMessage = error.localizedDescription\n }\n }\n }\n\n func cancelStream() {\n streamTask?.cancel()\n }\n\n private let service: OpenAIService\n private var streamTask: Task?\n}\n\n/// Helper that allows to display the JSON Schema.\nextension String {\n func asJsonFormatted() -> String {\n guard let data = data(using: .utf8) else { return self }\n do {\n // Parse JSON string to Any object\n if let jsonObject = try JSONSerialization.jsonObject(with: data, options: []) as? [String: Any] {\n // Convert back to data with pretty-printing\n let prettyPrintedData = try JSONSerialization.data(withJSONObject: jsonObject, options: [.prettyPrinted, .sortedKeys])\n\n // Convert formatted data back to string\n return String(data: prettyPrintedData, encoding: .utf8) ?? self\n }\n } catch {\n print(\"Error formatting JSON: \\(error)\")\n }\n return self\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/EmbeddingsDemo/EmbeddingsDemoView.swift",
"content": "//\n// EmbeddingsDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/23/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct EmbeddingsDemoView: View {\n init(service: OpenAIService) {\n _embeddingsProvider = State(initialValue: EmbeddingsProvider(service: service))\n }\n\n var textArea: some View {\n HStack(spacing: 4) {\n TextField(\"Enter prompt\", text: $prompt, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n Button {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n do {\n try await embeddingsProvider.createEmbeddings(parameters: .init(\n input: prompt,\n model: .textEmbedding3Large,\n encodingFormat: nil,\n dimensions: nil))\n } catch {\n errorMessage = \"\\(error)\"\n }\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n }\n .padding()\n }\n\n var list: some View {\n List {\n ForEach(Array(embeddingsProvider.embeddings.enumerated()), id: \\.offset) { _, embeddingObject in\n Section(header: Text(\"Section \\(embeddingObject.index) \\(embeddingObject.object)\")) {\n ForEach(embeddingObject.embedding, id: \\.self) { embedding in\n Text(\"Embedding Value \\(embedding)\")\n }\n }\n }\n }\n }\n\n var body: some View {\n VStack {\n textArea\n if !errorMessage.isEmpty {\n Text(\"Error \\(errorMessage)\")\n .bold()\n }\n list\n }\n .overlay(\n Group {\n if isLoading {\n ProgressView()\n } else {\n EmptyView()\n }\n })\n }\n\n @State private var embeddingsProvider: EmbeddingsProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n @State private var errorMessage = \"\"\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/EmbeddingsDemo/Embeddingsprovider.swift",
"content": "//\n// Embeddingsprovider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/23/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n@Observable\nclass EmbeddingsProvider {\n init(service: OpenAIService) {\n self.service = service\n }\n\n var embeddings = [EmbeddingObject]()\n\n func createEmbeddings(\n parameters: EmbeddingParameter)\n async throws\n {\n embeddings = try await service.createEmbeddings(parameters: parameters).data\n }\n\n private let service: OpenAIService\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Files/AttachmentView.swift",
"content": "//\n// AttachmentView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 5/29/24.\n//\n\nimport SwiftUI\n\nstruct AttachmentView: View {\n let fileName: String\n @Binding var actionTrigger: Bool\n\n let isLoading: Bool\n\n var body: some View {\n HStack(spacing: Sizes.spacingExtraSmall) {\n HStack {\n if isLoading == true {\n ProgressView()\n .frame(width: 10, height: 10)\n .padding(.horizontal, Sizes.spacingExtraSmall)\n } else {\n Image(systemName: \"doc\")\n .resizable()\n .aspectRatio(contentMode: .fit)\n .frame(width: 10)\n .foregroundColor(.secondary)\n }\n Text(fileName)\n .font(.caption2)\n }\n Button {\n actionTrigger = true\n\n } label: {\n Image(systemName: \"xmark.circle.fill\")\n }\n .disabled(isLoading)\n }\n .padding(.leading, Sizes.spacingMedium)\n .background(\n RoundedRectangle(cornerRadius: 8)\n .stroke(.gray.opacity(0.5), lineWidth: 0.5))\n }\n}\n\n#Preview {\n AttachmentView(fileName: \"Mydocument.pdf\", actionTrigger: .constant(true), isLoading: true)\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Files/FileAttachmentView.swift",
"content": "//\n// FileAttachmentView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 5/29/24.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - FileAttachmentView\n\nstruct FileAttachmentView: View {\n init(\n service: OpenAIService,\n action: FilePickerAction,\n fileUploadedCompletion: @escaping (_ file: FileObject) -> Void,\n fileDeletedCompletion: @escaping (_ parameters: FilePickerAction, _ id: String) -> Void)\n {\n fileProvider = FilesPickerProvider(service: service)\n self.action = action\n self.fileUploadedCompletion = fileUploadedCompletion\n self.fileDeletedCompletion = fileDeletedCompletion\n }\n\n var body: some View {\n Group {\n switch action {\n case .request(let parameters):\n newUploadedFileView(parameters: parameters)\n case .retrieveAndDisplay(let id):\n previousUploadedFileView(id: id)\n }\n }\n .onChange(of: deleted) { oldValue, newValue in\n if oldValue != newValue, newValue {\n Task {\n if let fileObject {\n fileDeleteStatus = try await fileProvider.deleteFileWith(id: fileObject.id)\n }\n }\n }\n }\n .onChange(of: fileDeleteStatus) { oldValue, newValue in\n if oldValue != newValue, let newValue, newValue.deleted {\n fileDeletedCompletion(action, newValue.id)\n }\n }\n }\n\n func newUploadedFileView(\n parameters: FileParameters)\n -> some View\n {\n AttachmentView(\n fileName: (fileObject?.filename ?? parameters.fileName) ?? \"\",\n actionTrigger: $deleted,\n isLoading: fileObject == nil || deleted)\n .disabled(fileObject == nil)\n .opacity(fileObject == nil ? 0.3 : 1)\n .onFirstAppear {\n Task {\n fileObject = try await fileProvider.uploadFile(parameters: parameters)\n }\n }\n .onChange(of: fileObject) { oldValue, newValue in\n if oldValue != newValue, let newValue {\n fileUploadedCompletion(newValue)\n }\n }\n }\n\n func previousUploadedFileView(\n id: String)\n -> some View\n {\n AttachmentView(fileName: fileObject?.filename ?? \"Document\", actionTrigger: $deleted, isLoading: fileObject == nil || deleted)\n .onFirstAppear {\n Task {\n fileObject = try await fileProvider.retrieveFileWith(id: id)\n }\n }\n }\n\n @State private var fileObject: FileObject?\n @State private var fileDeleteStatus: DeletionStatus?\n @State private var deleted = false\n\n private let fileProvider: FilesPickerProvider\n private let fileUploadedCompletion: (_ file: FileObject) -> Void\n private let fileDeletedCompletion: (_ action: FilePickerAction, _ id: String) -> Void\n private let action: FilePickerAction\n}\n\n// MARK: - OnFirstAppear\n\nprivate struct OnFirstAppear: ViewModifier {\n let perform: () -> Void\n\n @State private var firstTime = true\n\n func body(content: Content) -> some View {\n content.onAppear {\n if firstTime {\n firstTime = false\n perform()\n }\n }\n }\n}\n\nextension View {\n func onFirstAppear(perform: @escaping () -> Void) -> some View {\n modifier(OnFirstAppear(perform: perform))\n }\n}\n\n// MARK: - DeletionStatus + @retroactive Equatable\n\nextension DeletionStatus: @retroactive Equatable {\n public static func ==(lhs: DeletionStatus, rhs: DeletionStatus) -> Bool {\n lhs.id == rhs.id\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Files/FilesPicker.swift",
"content": "//\n// FilesPicker.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 5/29/24.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - FileObject + @retroactive Equatable\n\nextension FileObject: @retroactive Equatable {\n public static func ==(lhs: FileObject, rhs: FileObject) -> Bool {\n lhs.id == rhs.id\n }\n}\n\n// MARK: - FileParameters + @retroactive Equatable, @retroactive Identifiable\n\nextension FileParameters: @retroactive Equatable, @retroactive Identifiable {\n public var id: String {\n fileName ?? \"\"\n }\n\n public static func ==(lhs: FileParameters, rhs: FileParameters) -> Bool {\n lhs.file == rhs.file &&\n lhs.fileName == rhs.fileName &&\n lhs.purpose == rhs.purpose\n }\n}\n\n// MARK: - FilePickerAction\n\nenum FilePickerAction: Identifiable, Equatable {\n case request(FileParameters)\n case retrieveAndDisplay(id: String)\n\n var id: String {\n switch self {\n case .request(let fileParameters): fileParameters.id\n case .retrieveAndDisplay(let id): id\n }\n }\n}\n\n// MARK: - FilesPicker\n\nstruct FilesPicker: View {\n init(\n service: OpenAIService,\n sectionTitle: String? = nil,\n actionTitle: String,\n fileIDS: Binding<[String]>,\n actions: Binding<[FilePickerAction]>)\n {\n self.service = service\n self.sectionTitle = sectionTitle\n self.actionTitle = actionTitle\n _fileIDS = fileIDS\n _actions = actions\n }\n\n var body: some View {\n VStack(alignment: .leading) {\n Group {\n if let sectionTitle {\n VStack {\n Text(sectionTitle)\n Button {\n presentImporter = true\n } label: {\n Text(actionTitle)\n }\n }\n\n } else {\n Button {\n presentImporter = true\n } label: {\n Text(actionTitle)\n }\n }\n }\n .fileImporter(\n isPresented: $presentImporter,\n allowedContentTypes: [.pdf, .text, .mp3, .mpeg],\n allowsMultipleSelection: true)\n { result in\n switch result {\n case .success(let files):\n for file in files {\n // gain access to the directory\n let gotAccess = file.startAccessingSecurityScopedResource()\n guard gotAccess else { continue }\n if\n let data = try? Data(contentsOf: file.absoluteURL)\n {\n let parameter = FileParameters(fileName: file.lastPathComponent, file: data, purpose: \"assistants\")\n actions.append(.request(parameter))\n }\n file.stopAccessingSecurityScopedResource()\n }\n\n case .failure(let error):\n print(error)\n }\n }\n ForEach(actions, id: \\.id) { action in\n FileAttachmentView(\n service: service,\n action: action)\n { fileResponse in\n fileIDS.append(fileResponse.id)\n } fileDeletedCompletion: { actionToDelete, deletedFileID in\n /// Remove file ids from network request.\n fileIDS.removeAll(where: { id in\n id == deletedFileID\n })\n /// Update UI\n actions.removeAll { action in\n actionToDelete.id == action.id\n }\n }\n }\n }\n .frame(maxWidth: .infinity, alignment: .leading)\n }\n\n @State private var presentImporter = false\n @Binding private var actions: [FilePickerAction]\n @Binding private var fileIDS: [String]\n\n private let service: OpenAIService\n private let sectionTitle: String?\n private let actionTitle: String\n}\n\n#Preview {\n FilesPicker(\n service: OpenAIServiceFactory.service(apiKey: \"\"),\n sectionTitle: \"Knowledge\",\n actionTitle: \"Uplodad File\",\n fileIDS: .constant([\"s\"]),\n actions: .constant(\n [\n .retrieveAndDisplay(id: \"id1\"),\n .retrieveAndDisplay(id: \"id2\"),\n .retrieveAndDisplay(id: \"id3\"),\n .retrieveAndDisplay(id: \"id4\"),\n .retrieveAndDisplay(id: \"id5\"),\n .retrieveAndDisplay(id: \"id6\"),\n ]))\n .padding()\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Files/FilesPickerProvider.swift",
"content": "//\n// FilesPickerProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 5/29/24.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nfinal class FilesPickerProvider {\n init(service: OpenAIService) {\n self.service = service\n }\n\n var files = [FileObject]()\n var uploadedFile: FileObject?\n var deletedStatus: DeletionStatus?\n var retrievedFile: FileObject?\n var fileContent = [[String: Any]]()\n\n func listFiles() async throws {\n files = try await service.listFiles().data\n }\n\n func uploadFile(\n parameters: FileParameters)\n async throws -> FileObject?\n {\n try await service.uploadFile(parameters: parameters)\n }\n\n func deleteFileWith(\n id: String)\n async throws -> DeletionStatus?\n {\n try await service.deleteFileWith(id: id)\n }\n\n func retrieveFileWith(\n id: String)\n async throws -> FileObject?\n {\n try await service.retrieveFileWith(id: id)\n }\n\n func retrieveContentForFileWith(\n id: String)\n async throws\n {\n fileContent = try await service.retrieveContentForFileWith(id: id)\n }\n\n private let service: OpenAIService\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/FilesDemo/FilesDemoView.swift",
"content": "//\n// FilesDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/23/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - FilesDemoView\n\nstruct FilesDemoView: View {\n init(service: OpenAIService) {\n _filesProvider = State(initialValue: FilesProvider(service: service))\n }\n\n enum Config {\n case list\n case moreOptions\n }\n\n var body: some View {\n VStack {\n picker\n if !errorMessage.isEmpty {\n Text(\"Error \\(errorMessage)\")\n .bold()\n }\n switch selectedSegment {\n case .list:\n listView\n case .moreOptions:\n moreOptionsView\n }\n }\n .overlay(\n Group {\n if isLoading {\n ProgressView()\n } else {\n EmptyView()\n }\n })\n }\n\n var picker: some View {\n Picker(\"Options\", selection: $selectedSegment) {\n Text(\"Shows List\").tag(Config.list)\n Text(\"Show More options\").tag(Config.moreOptions)\n }\n .pickerStyle(SegmentedPickerStyle())\n .padding()\n }\n\n var moreOptionsView: some View {\n ScrollView {\n VStack {\n uploadFileButton\n Text(\"This button will load a file that has been added to this app bundle.\")\n if let uploadedFile = filesProvider.uploadedFile {\n FileObjectView(file: uploadedFile)\n }\n }\n }\n }\n\n var listView: some View {\n VStack(spacing: 0) {\n listFilesButton\n list\n }\n }\n\n var listFilesButton: some View {\n Button(\"List Files\") {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n do {\n try await filesProvider.listFiles()\n } catch {\n errorMessage = \"\\(error)\"\n }\n }\n }\n .buttonStyle(.borderedProminent)\n }\n\n var uploadFileButton: some View {\n Button(\"Upload File\") {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n do {\n let fileData = try contentLoader.loadBundledContent(fromFileNamed: \"WorldCupData\", ext: \"jsonl\")\n try await filesProvider.uploadFile(parameters: .init(fileName: \"WorldCupData\", file: fileData, purpose: \"fine-tune\"))\n } catch {\n errorMessage = \"\\(error)\"\n }\n }\n }\n .buttonStyle(.borderedProminent)\n }\n\n var list: some View {\n List {\n ForEach(Array(filesProvider.files.enumerated()), id: \\.offset) { _, file in\n FileObjectView(file: file)\n }\n }\n }\n\n @State private var filesProvider: FilesProvider\n @State private var isLoading = false\n @State private var errorMessage = \"\"\n @State private var selectedSegment = Config.list\n\n private let contentLoader = ContentLoader()\n}\n\n// MARK: - FileObjectView\n\nstruct FileObjectView: View {\n init(file: FileObject) {\n self.file = file\n }\n\n var body: some View {\n VStack(alignment: .leading, spacing: 4) {\n Text(\"File name = \\(file.filename)\")\n .font(.title2)\n VStack(alignment: .leading, spacing: 2) {\n Text(\"ID = \\(file.id)\")\n Text(\"Created = \\(file.createdAt)\")\n Text(\"Object = \\(file.object)\")\n Text(\"Purpose = \\(file.purpose)\")\n Text(\"Status = \\(file.status ?? \"NO STATUS\")\")\n Text(\"Status Details = \\(file.statusDetails ?? \"NO DETAILS\")\")\n }\n .font(.callout)\n }\n .foregroundColor(.primary)\n .padding()\n .background(\n RoundedRectangle(cornerSize: .init(width: 20, height: 20))\n .foregroundColor(.mint))\n }\n\n private let file: FileObject\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/FilesDemo/FilesProvider.swift",
"content": "//\n// FilesProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/23/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n@Observable\nclass FilesProvider {\n init(service: OpenAIService) {\n self.service = service\n }\n\n var files = [FileObject]()\n var uploadedFile: FileObject?\n var deletedStatus: DeletionStatus?\n var retrievedFile: FileObject?\n var fileContent = [[String: Any]]()\n\n func listFiles() async throws {\n files = try await service.listFiles().data\n }\n\n func uploadFile(\n parameters: FileParameters)\n async throws\n {\n uploadedFile = try await service.uploadFile(parameters: parameters)\n }\n\n func deleteFileWith(\n id: String)\n async throws\n {\n deletedStatus = try await service.deleteFileWith(id: id)\n }\n\n func retrieveFileWith(\n id: String)\n async throws\n {\n retrievedFile = try await service.retrieveFileWith(id: id)\n }\n\n func retrieveContentForFileWith(\n id: String)\n async throws\n {\n fileContent = try await service.retrieveContentForFileWith(id: id)\n }\n\n private let service: OpenAIService\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/FineTuningDemo/FineTuningJobDemoView.swift",
"content": "//\n// FineTuningJobDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/23/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - FineTuningJobDemoView\n\nstruct FineTuningJobDemoView: View {\n init(service: OpenAIService) {\n _fineTuningJobProvider = State(initialValue: FineTuningJobProvider(service: service))\n }\n\n var body: some View {\n VStack {\n Button(\"List Fine tuning jobs\") {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n try await fineTuningJobProvider.listFineTuningJobs()\n }\n }\n .buttonStyle(.borderedProminent)\n List {\n ForEach(Array(fineTuningJobProvider.fineTunedJobs.enumerated()), id: \\.offset) { _, job in\n FineTuningObjectView(job: job)\n }\n }\n }\n .overlay(\n Group {\n if isLoading {\n ProgressView()\n } else {\n EmptyView()\n }\n })\n }\n\n @State private var fineTuningJobProvider: FineTuningJobProvider\n @State private var isLoading = false\n}\n\n// MARK: - FineTuningObjectView\n\nstruct FineTuningObjectView: View {\n init(job: FineTuningJobObject) {\n self.job = job\n }\n\n var body: some View {\n VStack(alignment: .leading, spacing: 4) {\n Text(\"Fine Tuned Model - \\(job.fineTunedModel ?? \"NO MODEL\")\")\n .font(.title2)\n VStack(alignment: .leading, spacing: 2) {\n Text(\"Model = \\(job.model)\")\n Text(\"Object = \\(job.object)\")\n Text(\"ID = \\(job.id)\")\n Text(\"Created = \\(job.createdAt)\")\n Text(\"Organization ID = \\(job.organizationId)\")\n Text(\"Training file = \\(job.trainingFile)\")\n Text(\"Status = \\(job.status)\")\n .bold()\n }\n .font(.callout)\n }\n .foregroundColor(.primary)\n .padding()\n .background(\n RoundedRectangle(cornerSize: .init(width: 20, height: 20))\n .foregroundColor(.mint))\n }\n\n private let job: FineTuningJobObject\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/FineTuningDemo/FineTuningJobProvider.swift",
"content": "//\n// FineTuningJobProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/23/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n@Observable\nclass FineTuningJobProvider {\n init(service: OpenAIService) {\n self.service = service\n }\n\n var createdFineTuningJob: FineTuningJobObject?\n var canceledFineTuningJob: FineTuningJobObject?\n var retrievedFineTuningJob: FineTuningJobObject?\n var fineTunedJobs = [FineTuningJobObject]()\n var finteTuningEventObjects = [FineTuningJobEventObject]()\n\n func createFineTuningJob(\n parameters: FineTuningJobParameters)\n async throws\n {\n createdFineTuningJob = try await service.createFineTuningJob(parameters: parameters)\n }\n\n func listFineTuningJobs()\n async throws\n {\n fineTunedJobs = try await service.listFineTuningJobs(after: nil, limit: nil).data\n }\n\n func retrieveFineTuningJob(\n id: String)\n async throws\n {\n retrievedFineTuningJob = try await service.retrieveFineTuningJob(id: id)\n }\n\n func cancelFineTuningJob(\n id: String)\n async throws\n {\n canceledFineTuningJob = try await service.cancelFineTuningJobWith(id: id)\n }\n\n func listFineTuningEventsForJobWith(\n id: String)\n async throws\n {\n finteTuningEventObjects = try await service.listFineTuningEventsForJobWith(id: id, after: nil, limit: nil).data\n }\n\n private let service: OpenAIService\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ImagesDemo/ImagesDemoView.swift",
"content": "//\n// ImagesDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/24/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct ImagesDemoView: View {\n init(service: OpenAIService) {\n _imagesProvider = State(initialValue: ImagesProvider(service: service))\n }\n\n var body: some View {\n ScrollView {\n textArea\n if !errorMessage.isEmpty {\n Text(\"Error \\(errorMessage)\")\n .bold()\n }\n ForEach(Array(imagesProvider.images.enumerated()), id: \\.offset) { _, url in\n AsyncImage(url: url, scale: 1) { image in\n image\n .resizable()\n .aspectRatio(contentMode: .fill)\n .clipped()\n } placeholder: {\n EmptyView()\n }\n }\n }\n .overlay(\n Group {\n if isLoading {\n ProgressView()\n } else {\n EmptyView()\n }\n })\n }\n\n var textArea: some View {\n HStack(spacing: 4) {\n TextField(\"Enter prompt\", text: $prompt, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n Button {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n do {\n try await imagesProvider.createImages(parameters: .init(prompt: prompt, model: .dalle3(.largeSquare)))\n } catch {\n errorMessage = \"\\(error)\"\n }\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n }\n .padding()\n }\n\n @State private var imagesProvider: ImagesProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n @State private var errorMessage = \"\"\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ImagesDemo/ImagesProvider.swift",
"content": "//\n// ImagesProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/23/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n@Observable\nclass ImagesProvider {\n init(service: OpenAIService) {\n self.service = service\n }\n\n var images = [URL]()\n\n func createImages(\n parameters: ImageCreateParameters)\n async throws\n {\n let urls = try await service.legacyCreateImages(\n parameters: parameters).data.map(\\.url)\n images = urls.compactMap(\\.self)\n }\n\n func editImages(\n parameters: ImageEditParameters)\n async throws\n {\n let urls = try await service.legacyEditImage(\n parameters: parameters).data.map(\\.url)\n images = urls.compactMap(\\.self)\n }\n\n func createImageVariations(\n parameters: ImageVariationParameters)\n async throws\n {\n let urls = try await service.legacyCreateImageVariations(parameters: parameters).data.map(\\.url)\n images = urls.compactMap(\\.self)\n }\n\n private let service: OpenAIService\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/LocalChatDemo/LocalChatDemoView.swift",
"content": "//\n// LocalChatDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 6/24/24.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n/// For more visit https://github.com/ollama/ollama/blob/main/docs/openai.md\n\n/// Important:\n/// Before using a model, pull it locally ollama pull:\n\n/// `ollama pull llama3`\n/// Default model names\n/// For tooling that relies on default OpenAI model names such as gpt-3.5-turbo, use ollama cp to copy an existing model name to a temporary name:\n\n/// `ollama cp llama3 gpt-3.5-turbo`\n/// Afterwards, this new model name can be specified the model field:\n\n/// ```curl http://localhost:11434/v1/chat/completions \\\n/// -H \"Content-Type: application/json\" \\\n/// -d '{\n/// \"model\": \"gpt-3.5-turbo\",\n/// \"messages\": [\n/// {\n/// \"role\": \"user\",\n/// \"content\": \"Hello!\"\n/// }\n/// ]\n/// }'```\n\nstruct LocalChatDemoView: View {\n init(service: OpenAIService, customModel: String? = nil) {\n self.customModel = customModel\n _chatProvider = State(initialValue: ChatProvider(service: service))\n }\n\n enum ChatConfig {\n case chatCompletion\n case chatCompeltionStream\n }\n\n let customModel: String?\n\n var body: some View {\n ScrollView {\n VStack {\n picker\n textArea\n Text(chatProvider.errorMessage)\n .foregroundColor(.red)\n switch selectedSegment {\n case .chatCompeltionStream:\n streamedChatResultView\n case .chatCompletion:\n chatCompletionResultView\n }\n }\n }\n .overlay(\n Group {\n if isLoading {\n ProgressView()\n } else {\n EmptyView()\n }\n })\n }\n\n var picker: some View {\n Picker(\"Options\", selection: $selectedSegment) {\n Text(\"Chat Completion\").tag(ChatConfig.chatCompletion)\n Text(\"Chat Completion stream\").tag(ChatConfig.chatCompeltionStream)\n }\n .pickerStyle(SegmentedPickerStyle())\n .padding()\n }\n\n var textArea: some View {\n HStack(spacing: 4) {\n TextField(\"Enter prompt\", text: $prompt, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n Button {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n\n let content = ChatCompletionParameters.Message.ContentType.text(prompt)\n prompt = \"\"\n let model: Model =\n if let customModel, !customModel.isEmpty {\n .custom(customModel)\n } else {\n // Make sure you run `ollama pull llama3` in your terminal to download this model.\n .custom(\"llama3\")\n }\n\n let parameters = ChatCompletionParameters(\n messages: [.init(\n role: .user,\n content: content)],\n model: model)\n switch selectedSegment {\n case .chatCompletion:\n try await chatProvider.startChat(parameters: parameters)\n case .chatCompeltionStream:\n try await chatProvider.startStreamedChat(parameters: parameters)\n }\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n }\n .padding()\n }\n\n /// stream = `false`\n var chatCompletionResultView: some View {\n ForEach(Array(chatProvider.messages.enumerated()), id: \\.offset) { _, val in\n VStack(spacing: 0) {\n Text(\"\\(val)\")\n }\n }\n }\n\n /// stream = `true`\n var streamedChatResultView: some View {\n VStack {\n Button(\"Cancel stream\") {\n chatProvider.cancelStream()\n }\n Text(chatProvider.message)\n }\n }\n\n @State private var chatProvider: ChatProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n @State private var selectedSegment = ChatConfig.chatCompeltionStream\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/LocalHostEntryView.swift",
"content": "//\n// LocalHostEntryView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 6/24/24.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct LocalHostEntryView: View {\n var body: some View {\n NavigationStack {\n VStack {\n Spacer()\n TextField(\"Enter URL\", text: $url)\n .padding()\n .textFieldStyle(.roundedBorder)\n NavigationLink(destination: OptionsListView(\n openAIService: OpenAIServiceFactory.service(baseURL: url),\n options: [.localChat]))\n {\n Text(\"Continue\")\n .padding()\n .padding(.horizontal, 48)\n .foregroundColor(.white)\n .background(\n Capsule()\n .foregroundColor(url.isEmpty ? .gray.opacity(0.2) : Color(red: 64 / 255, green: 195 / 255, blue: 125 / 255)))\n }\n .disabled(url.isEmpty)\n Spacer()\n }\n .padding()\n .navigationTitle(\"Enter URL\")\n }\n }\n\n @State private var url = \"\"\n}\n\n#Preview {\n ApiKeyIntroView()\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ModelsDemo/ModelsDemoView.swift",
"content": "//\n// ModelsDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/24/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct ModelsDemoView: View {\n init(service: OpenAIService) {\n _modelsProvider = State(initialValue: ModelsProvider(service: service))\n }\n\n var body: some View {\n VStack {\n showModelsButton\n list\n }\n }\n\n var list: some View {\n List {\n ForEach(Array(modelsProvider.models.enumerated()), id: \\.offset) { _, model in\n Text(\"\\(model.id)\")\n }\n }\n }\n\n var showModelsButton: some View {\n Button(\"List models\") {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n do {\n try await modelsProvider.listModels()\n } catch {\n errorMessage = \"\\(error)\"\n }\n }\n }\n .buttonStyle(.bordered)\n }\n\n @State private var modelsProvider: ModelsProvider\n @State private var isLoading = false\n @State private var errorMessage = \"\"\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ModelsDemo/ModelsProvider.swift",
"content": "//\n// ModelsProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/24/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n@Observable\nclass ModelsProvider {\n init(service: OpenAIService) {\n self.service = service\n }\n\n var models = [ModelObject]()\n var retrievedModel: ModelObject?\n var deletionStatus: DeletionStatus?\n\n func listModels() async throws {\n models = try await service.listModels().data\n }\n\n func retrieveModelWith(\n id: String)\n async throws\n {\n retrievedModel = try await service.retrieveModelWith(id: id)\n }\n\n func deleteFineTuneModelWith(\n id: String)\n async throws\n {\n deletionStatus = try await service.deleteFineTuneModelWith(id: id)\n }\n\n private let service: OpenAIService\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ModerationsDemo/ModerationDemoView.swift",
"content": "//\n// ModerationDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/24/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct ModerationDemoView: View {\n init(service: OpenAIService) {\n _moderationProvider = State(initialValue: ModerationProvider(service: service))\n }\n\n var body: some View {\n VStack {\n textArea\n if moderationProvider.isFlagged {\n Text(\"That is not a nice thing to say.\")\n }\n if !errorMessage.isEmpty {\n Text(\"Error \\(errorMessage)\")\n .bold()\n }\n }\n .overlay(\n Group {\n if isLoading {\n ProgressView()\n } else {\n EmptyView()\n }\n })\n }\n\n var textArea: some View {\n HStack(spacing: 4) {\n TextField(\"Enter prompt\", text: $prompt, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n Button {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n do {\n try await moderationProvider.createModerationFromText(parameters: .init(input: prompt))\n } catch {\n errorMessage = \"\\(error)\"\n }\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n }\n .padding()\n }\n\n @State private var moderationProvider: ModerationProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n @State private var errorMessage = \"\"\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ModerationsDemo/ModerationProvider.swift",
"content": "//\n// ModerationProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/24/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n@Observable\nclass ModerationProvider {\n init(service: OpenAIService) {\n self.service = service\n }\n\n var isFlagged = false\n\n func createModerationFromText(\n parameters: ModerationParameter)\n async throws\n {\n isFlagged = try await service.createModerationFromText(parameters: parameters).isFlagged\n }\n\n func createModerationFromTexts(\n parameters: ModerationParameter<[String]>)\n async throws\n {\n isFlagged = try await service.createModerationFromTexts(parameters: parameters).isFlagged\n }\n\n private let service: OpenAIService\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/OptionsListView.swift",
"content": "//\n// OptionsListView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/19/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct OptionsListView: View {\n /// https://platform.openai.com/docs/api-reference\n enum APIOption: String, CaseIterable, Identifiable {\n case audio = \"Audio\"\n case chat = \"Chat\"\n case chatPredictedOutput = \"Chat Predicted Output\"\n case localChat = \"Local Chat\" // Ollama\n case vision = \"Vision\"\n case embeddings = \"Embeddings\"\n case fineTuning = \"Fine Tuning\"\n case files = \"Files\"\n case images = \"Images\"\n case models = \"Models\"\n case moderations = \"Moderations\"\n case chatHistoryConversation = \"Chat History Conversation\"\n case chatFunctionCall = \"Chat Functions call\"\n case chatFunctionsCallStream = \"Chat Functions call (Stream)\"\n case chatStructuredOutput = \"Chat Structured Output\"\n case chatStructuredOutputTool = \"Chat Structured Output Tools\"\n case configureAssistant = \"Configure Assistant\"\n case realTimeAPI = \"Real time API\"\n case responseStream = \"Response Stream Demo\"\n\n var id: String { rawValue }\n }\n\n var openAIService: OpenAIService\n\n var options: [APIOption]\n\n var body: some View {\n VStack {\n // Custom model input field\n VStack(alignment: .leading, spacing: 8) {\n Text(\"Custom Model (Optional)\")\n .font(.caption)\n .foregroundColor(.secondary)\n TextField(\"e.g., grok-beta, claude-3-opus, etc.\", text: $customModel)\n .textFieldStyle(.roundedBorder)\n .autocapitalization(.none)\n .disableAutocorrection(true)\n }\n .padding()\n List(options, id: \\.self, selection: $selection) { option in\n Text(option.rawValue)\n }\n }\n .sheet(item: $selection) { selection in\n VStack {\n Text(selection.rawValue)\n .font(.largeTitle)\n .padding()\n switch selection {\n case .audio:\n AudioDemoView(service: openAIService)\n case .chat:\n ChatDemoView(service: openAIService, customModel: customModel)\n case .chatPredictedOutput:\n ChatPredictedOutputDemoView(service: openAIService, customModel: customModel)\n case .vision:\n ChatVisionDemoView(service: openAIService, customModel: customModel)\n case .embeddings:\n EmbeddingsDemoView(service: openAIService)\n case .fineTuning:\n FineTuningJobDemoView(service: openAIService)\n case .files:\n FilesDemoView(service: openAIService)\n case .images:\n ImagesDemoView(service: openAIService)\n case .localChat:\n LocalChatDemoView(service: openAIService, customModel: customModel)\n case .models:\n ModelsDemoView(service: openAIService)\n case .moderations:\n ModerationDemoView(service: openAIService)\n case .chatHistoryConversation:\n ChatStreamFluidConversationDemoView(service: openAIService, customModel: customModel)\n case .chatFunctionCall:\n ChatFunctionCallDemoView(service: openAIService)\n case .chatFunctionsCallStream:\n ChatFunctionsCalllStreamDemoView(service: openAIService, customModel: customModel)\n case .chatStructuredOutput:\n ChatStructuredOutputDemoView(service: openAIService, customModel: customModel)\n case .chatStructuredOutputTool:\n ChatStructureOutputToolDemoView(service: openAIService, customModel: customModel)\n case .configureAssistant:\n AssistantConfigurationDemoView(service: openAIService)\n case .realTimeAPI:\n Text(\"WIP\")\n case .responseStream:\n ResponseStreamDemoView(service: openAIService)\n }\n }\n }\n }\n\n @State private var selection: APIOption? = nil\n @State private var customModel = \"\"\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/PredictedOutputsDemo/ChatPredictedOutputDemoView.swift",
"content": "//\n// ChatPredictedOutputDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 1/3/25.\n//\n\nimport Foundation\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - ChatPredictedOutputDemoView\n\n/// https://platform.openai.com/docs/guides/predicted-outputs\nstruct ChatPredictedOutputDemoView: View {\n init(service: OpenAIService, customModel: String? = nil) {\n self.customModel = customModel\n chatProvider = ChatProvider(service: service)\n }\n\n let customModel: String?\n\n var body: some View {\n ScrollView {\n VStack {\n textArea\n Text(chatProvider.errorMessage)\n .foregroundColor(.red)\n chatCompletionResultView\n }\n }\n .overlay(\n Group {\n if isLoading {\n ProgressView()\n } else {\n EmptyView()\n }\n })\n }\n\n var textArea: some View {\n HStack(spacing: 4) {\n TextField(\"Enter prompt\", text: $prompt, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n Button {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n\n let content = ChatCompletionParameters.Message.ContentType.text(prompt)\n prompt = \"\"\n let model: Model =\n if let customModel, !customModel.isEmpty {\n .custom(customModel)\n } else {\n .gpt4o\n }\n\n let parameters = ChatCompletionParameters(\n messages: [\n .init(role: .system, content: .text(systemMessage)),\n .init(role: .user, content: content),\n .init(role: .user, content: .text(predictedCode)),\n ], // Sending the predicted code as another user message.\n model: model,\n prediction: .init(content: .text(predictedCode)))\n try await chatProvider.startChat(parameters: parameters)\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n }\n .padding()\n }\n\n /// stream = `false`\n var chatCompletionResultView: some View {\n ForEach(Array(chatProvider.messages.enumerated()), id: \\.offset) { _, val in\n VStack(spacing: 0) {\n Text(\"\\(val)\")\n }\n }\n }\n\n @State private var chatProvider: ChatProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n}\n\nlet systemMessage = \"\"\"\n You are a code editor assistant. I only output code without any explanations, commentary, or additional text. I follow these rules:\n\n 1. Respond with code only, never any text or explanations\n 2. Use appropriate syntax highlighting/formatting \n 3. If the code needs to be modified/improved, output the complete updated code\n 4. Do not include caveats, introductions, or commentary\n 5. Do not ask questions or solicit feedback\n 6. Do not explain what changes were made\n 7. Assume the user knows what they want and will review the code themselves\n \"\"\"\n\nlet predictedCode = \"\"\"\n struct ChatPredictedOutputDemoView: View {\n\n @State private var chatProvider: ChatProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n\n init(service: OpenAIService) {\n chatProvider = ChatProvider(service: service)\n }\n\n var body: some View {\n ScrollView {\n VStack {\n textArea\n Text(chatProvider.errorMessage)\n .foregroundColor(.red)\n streamedChatResultView\n }\n }\n .overlay(\n Group {\n if isLoading {\n ProgressView()\n } else {\n EmptyView()\n }\n }\n )\n }\n\n var textArea: some View {\n HStack(spacing: 4) {\n TextField(\"Enter prompt\", text: $prompt, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .padding()\n Button {\n Task {\n isLoading = true\n defer { isLoading = false } // ensure isLoading is set to false when the\n\n let content: ChatCompletionParameters.Message.ContentType = .text(prompt)\n prompt = \"\"\n let parameters = ChatCompletionParameters(\n messages: [.init(\n role: .user,\n content: content)],\n model: .gpt4o)\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n }\n .padding()\n }\n\n /// stream = `true`\n var streamedChatResultView: some View {\n VStack {\n Button(\"Cancel stream\") {\n chatProvider.cancelStream()\n }\n Text(chatProvider.message)\n }\n }\n }\n \"\"\"\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Preview Content/Preview Assets.xcassets/Contents.json",
"content": "{\n \"info\" : {\n \"author\" : \"xcode\",\n \"version\" : 1\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Resources/WorldCupData.jsonl",
"content": "{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful assistant specializing in World Cup history.\"}, {\"role\": \"user\", \"content\": \"Tell me about the World Cup winner in Spain 1982.\"}, {\"role\": \"assistant\", \"content\": \"The winner of the 1982 FIFA World Cup held in Spain was Italy. They defeated West Germany 3-1 in the final match.\"}]}\n{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful assistant specializing in World Cup history.\"}, {\"role\": \"user\", \"content\": \"What about Mexico 1986?\"}, {\"role\": \"assistant\", \"content\": \"The 1986 FIFA World Cup in Mexico was won by Argentina. They beat West Germany 3-2 in the final.\"}]}\n{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful assistant specializing in World Cup history.\"}, {\"role\": \"user\", \"content\": \"Who won in Italy 1990?\"}, {\"role\": \"assistant\", \"content\": \"West Germany won the 1990 World Cup in Italy. They defeated Argentina 1-0 in the final.\"}]}\n{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful assistant specializing in World Cup history.\"}, {\"role\": \"user\", \"content\": \"What about USA 1994?\"}, {\"role\": \"assistant\", \"content\": \"Brazil won the 1994 World Cup held in the USA. They defeated Italy in a penalty shootout after a 0-0 draw in the final match.\"}]}\n{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful assistant specializing in World Cup history.\"}, {\"role\": \"user\", \"content\": \"Tell me about France 1998.\"}, {\"role\": \"assistant\", \"content\": \"France won the 1998 World Cup held in their home country. They defeated Brazil 3-0 in the final.\"}]}\n{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful assistant specializing in World Cup history.\"}, {\"role\": \"user\", \"content\": \"What happened in Korea-Japan 2002?\"}, {\"role\": \"assistant\", \"content\": \"Brazil won the 2002 World Cup held in South Korea and Japan. They defeated Germany 2-0 in the final match.\"}]}\n{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful assistant specializing in World Cup history.\"}, {\"role\": \"user\", \"content\": \"Who won in Germany 2006?\"}, {\"role\": \"assistant\", \"content\": \"Italy won the 2006 World Cup held in Germany. They defeated France in a penalty shootout after a 1-1 draw in the final.\"}]}\n{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful assistant specializing in World Cup history.\"}, {\"role\": \"user\", \"content\": \"Tell me about South Africa 2010.\"}, {\"role\": \"assistant\", \"content\": \"Spain won the 2010 World Cup held in South Africa. They defeated the Netherlands 1-0 in the final.\"}]}\n{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful assistant specializing in World Cup history.\"}, {\"role\": \"user\", \"content\": \"Who won in Brazil 2014?\"}, {\"role\": \"assistant\", \"content\": \"Germany won the 2014 World Cup held in Brazil. They defeated Argentina 1-0 in the final.\"}]}\n{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful assistant specializing in World Cup history.\"}, {\"role\": \"user\", \"content\": \"What about Russia 2018?\"}, {\"role\": \"assistant\", \"content\": \"France won the 2018 World Cup held in Russia. They defeated Croatia 4-2 in the final match.\"}]}\n{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful assistant specializing in World Cup history.\"}, {\"role\": \"user\", \"content\": \"Tell me about Qatar 2022.\"}, {\"role\": \"assistant\", \"content\": \"I don't know\"}]}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ResponseAPIDemo/ResponseStreamDemoView.swift",
"content": "//\n// ResponseStreamDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 6/7/25.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n// MARK: - ResponseStreamDemoView\n\nstruct ResponseStreamDemoView: View {\n init(service: OpenAIService) {\n _provider = State(initialValue: ResponseStreamProvider(service: service))\n }\n\n @Environment(\\.colorScheme) var colorScheme\n\n var body: some View {\n VStack(spacing: 0) {\n // Header\n headerView\n\n // Messages\n ScrollViewReader { proxy in\n ScrollView {\n LazyVStack(spacing: 12) {\n ForEach(provider.messages) { message in\n MessageBubbleView(message: message)\n .id(message.id)\n }\n\n if provider.isStreaming {\n HStack {\n LoadingIndicatorView()\n .frame(width: 30, height: 30)\n Spacer()\n }\n .padding(.horizontal)\n }\n }\n .padding()\n }\n .onChange(of: provider.messages.count) { _, _ in\n withAnimation {\n proxy.scrollTo(provider.messages.last?.id, anchor: .bottom)\n }\n }\n }\n\n // Error view\n if let error = provider.error {\n Text(error)\n .foregroundColor(.red)\n .font(.caption)\n .padding(.horizontal)\n .padding(.vertical, 8)\n .background(Color.red.opacity(0.1))\n }\n\n // Input area\n inputArea\n }\n .navigationTitle(\"Response Stream Demo\")\n .navigationBarTitleDisplayMode(.inline)\n .toolbar {\n ToolbarItem(placement: .navigationBarTrailing) {\n Button(\"Clear\") {\n provider.clearConversation()\n }\n .disabled(provider.isStreaming)\n }\n }\n }\n\n @State private var provider: ResponseStreamProvider\n @State private var inputText = \"\"\n @FocusState private var isInputFocused: Bool\n\n // MARK: - Subviews\n\n private var headerView: some View {\n VStack(alignment: .leading, spacing: 8) {\n Text(\"Streaming Responses with Conversation State\")\n .font(.headline)\n\n Text(\"This demo uses the Responses API with streaming to maintain conversation context across multiple turns.\")\n .font(.caption)\n .foregroundColor(.secondary)\n\n if provider.messages.isEmpty {\n Label(\"Start a conversation below\", systemImage: \"bubble.left.and.bubble.right\")\n .font(.caption)\n .foregroundColor(.blue)\n .padding(.top, 4)\n }\n }\n .frame(maxWidth: .infinity, alignment: .leading)\n .padding()\n .background(Color(UIColor.secondarySystemBackground))\n }\n\n private var inputArea: some View {\n HStack(spacing: 12) {\n TextField(\"Type a message...\", text: $inputText, axis: .vertical)\n .textFieldStyle(.roundedBorder)\n .lineLimit(1 ... 5)\n .focused($isInputFocused)\n .disabled(provider.isStreaming)\n .onSubmit {\n sendMessage()\n }\n\n Button(action: sendMessage) {\n Image(systemName: provider.isStreaming ? \"stop.circle.fill\" : \"arrow.up.circle.fill\")\n .font(.title2)\n .foregroundColor(provider.isStreaming ? .red : (inputText.isEmpty ? .gray : .blue))\n }\n .disabled(!provider.isStreaming && inputText.isEmpty)\n }\n .padding()\n .background(Color(UIColor.systemBackground))\n .overlay(\n Rectangle()\n .frame(height: 1)\n .foregroundColor(Color(UIColor.separator)),\n alignment: .top)\n }\n\n private func sendMessage() {\n guard !inputText.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty else { return }\n\n if provider.isStreaming {\n provider.stopStreaming()\n } else {\n let message = inputText\n inputText = \"\"\n provider.sendMessage(message)\n }\n }\n}\n\n// MARK: - MessageBubbleView\n\nstruct MessageBubbleView: View {\n let message: ResponseStreamProvider.ResponseMessage\n\n @Environment(\\.colorScheme) var colorScheme\n\n var body: some View {\n HStack {\n if message.role == .assistant {\n messageContent\n .background(backgroundGradient)\n .cornerRadius(16)\n .overlay(\n RoundedRectangle(cornerRadius: 16)\n .stroke(borderColor, lineWidth: 1))\n Spacer(minLength: 60)\n } else {\n Spacer(minLength: 60)\n messageContent\n .background(Color.blue)\n .cornerRadius(16)\n .foregroundColor(.white)\n }\n }\n }\n\n private var messageContent: some View {\n VStack(alignment: .leading, spacing: 4) {\n if message.role == .assistant, message.isStreaming {\n HStack(spacing: 4) {\n Image(systemName: \"dot.radiowaves.left.and.right\")\n .font(.caption2)\n .foregroundColor(.blue)\n Text(\"Streaming...\")\n .font(.caption2)\n .foregroundColor(.secondary)\n }\n }\n\n Text(message.content.isEmpty && message.isStreaming ? \" \" : message.content)\n .padding(.horizontal, 12)\n .padding(.vertical, 8)\n\n if message.role == .assistant, !message.isStreaming, message.responseId != nil {\n Text(\"Response ID: \\(String(message.responseId?.prefix(8) ?? \"\"))\")\n .font(.caption2)\n .foregroundColor(.secondary)\n .padding(.horizontal, 12)\n .padding(.bottom, 4)\n }\n }\n }\n\n private var backgroundGradient: some View {\n LinearGradient(\n gradient: Gradient(colors: [\n Color(UIColor.secondarySystemBackground),\n Color(UIColor.tertiarySystemBackground),\n ]),\n startPoint: .topLeading,\n endPoint: .bottomTrailing)\n }\n\n private var borderColor: Color {\n colorScheme == .dark ? Color.white.opacity(0.1) : Color.black.opacity(0.1)\n }\n}\n\n// MARK: - LoadingIndicatorView\n\nstruct LoadingIndicatorView: View {\n var body: some View {\n ZStack {\n ForEach(0 ..< 3) { index in\n Circle()\n .fill(Color.blue)\n .frame(width: 8, height: 8)\n .offset(x: CGFloat(index - 1) * 12)\n .opacity(0.8)\n .scaleEffect(animationScale(for: index))\n }\n }\n .onAppear {\n withAnimation(\n .easeInOut(duration: 0.8)\n .repeatForever(autoreverses: true))\n {\n animationAmount = 1\n }\n }\n }\n\n @State private var animationAmount = 0.0\n\n private func animationScale(for index: Int) -> Double {\n let delay = Double(index) * 0.1\n let progress = (animationAmount + delay).truncatingRemainder(dividingBy: 1.0)\n return 0.5 + (0.5 * sin(progress * .pi))\n }\n}\n\n// MARK: - Preview\n\n#Preview {\n NavigationView {\n ResponseStreamDemoView(service: OpenAIServiceFactory.service(apiKey: \"test\"))\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ResponseAPIDemo/ResponseStreamProvider.swift",
"content": "//\n// ResponseStreamProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 6/7/25.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n@MainActor\n@Observable\nclass ResponseStreamProvider {\n // MARK: - Initialization\n\n init(service: OpenAIService) {\n self.service = service\n }\n\n // MARK: - Message Model\n\n struct ResponseMessage: Identifiable {\n let id = UUID()\n let role: MessageRole\n var content: String\n let timestamp: Date\n var isStreaming = false\n let responseId: String?\n\n enum MessageRole {\n case user\n case assistant\n }\n }\n\n var messages = [ResponseMessage]()\n var isStreaming = false\n var currentStreamingMessage: ResponseMessage?\n var error: String?\n\n // MARK: - Public Methods\n\n func sendMessage(_ text: String) {\n // Cancel any existing stream\n streamTask?.cancel()\n\n // Add user message\n let userMessage = ResponseMessage(\n role: .user,\n content: text,\n timestamp: Date(),\n responseId: nil)\n messages.append(userMessage)\n\n // Start streaming response\n streamTask = Task {\n await streamResponse(for: text)\n }\n }\n\n func stopStreaming() {\n streamTask?.cancel()\n streamTask = nil\n\n // Finalize current streaming message\n if var message = currentStreamingMessage {\n message.isStreaming = false\n if let index = messages.firstIndex(where: { $0.id == message.id }) {\n messages[index] = message\n }\n }\n\n currentStreamingMessage = nil\n isStreaming = false\n }\n\n func clearConversation() {\n stopStreaming()\n messages.removeAll()\n previousResponseId = nil\n error = nil\n }\n\n private let service: OpenAIService\n private var previousResponseId: String?\n private var streamTask: Task?\n\n // MARK: - Private Methods\n\n private func streamResponse(for userInput: String) async {\n isStreaming = true\n error = nil\n\n // Create streaming message placeholder\n let streamingMessage = ResponseMessage(\n role: .assistant,\n content: \"\",\n timestamp: Date(),\n isStreaming: true,\n responseId: nil)\n messages.append(streamingMessage)\n currentStreamingMessage = streamingMessage\n\n do {\n // Build input array with conversation history\n var inputArray = [InputItem]()\n\n // Add conversation history\n for message in messages.dropLast(2) { // Exclude current user message and streaming placeholder\n let content = message.content\n switch message.role {\n case .user:\n inputArray.append(.message(InputMessage(role: \"user\", content: .text(content))))\n case .assistant:\n // Assistant messages in conversation history should be sent as simple text\n inputArray.append(.message(InputMessage(\n role: \"assistant\",\n content: .text(content))))\n }\n }\n\n // Add current user message\n inputArray.append(.message(InputMessage(role: \"user\", content: .text(userInput))))\n\n let parameters = ModelResponseParameter(\n input: .array(inputArray),\n model: .gpt5,\n instructions: \"You are a helpful assistant. Use the conversation history to provide contextual responses.\",\n maxOutputTokens: 1000,\n previousResponseId: previousResponseId,\n tools: [.imageGeneration(.init())])\n\n let stream = try await service.responseCreateStream(parameters)\n var accumulatedText = \"\"\n\n for try await event in stream {\n guard !Task.isCancelled else { break }\n\n switch event {\n case .responseCreated:\n // Response created event - we'll get the ID in responseCompleted\n break\n\n case .outputTextDelta(let delta):\n accumulatedText += delta.delta\n updateStreamingMessage(with: accumulatedText)\n\n case .responseCompleted(let completed):\n // Update previous response ID for conversation continuity\n previousResponseId = completed.response.id\n\n // Finalize the message\n finalizeStreamingMessage(\n with: accumulatedText,\n responseId: completed.response.id)\n\n case .responseFailed(let failed):\n throw APIError.requestFailed(\n description: failed.response.error?.message ?? \"Stream failed\")\n\n case .error(let errorEvent):\n throw APIError.requestFailed(\n description: errorEvent.message)\n\n default:\n // Handle other events as needed\n break\n }\n }\n\n } catch {\n self.error = error.localizedDescription\n\n // Remove streaming message on error\n if let streamingId = currentStreamingMessage?.id {\n messages.removeAll { $0.id == streamingId }\n }\n }\n\n currentStreamingMessage = nil\n isStreaming = false\n }\n\n private func updateStreamingMessage(with content: String) {\n guard\n let messageId = currentStreamingMessage?.id,\n let index = messages.firstIndex(where: { $0.id == messageId })\n else {\n return\n }\n\n messages[index].content = content\n }\n\n private func finalizeStreamingMessage(with content: String, responseId: String) {\n guard\n let messageId = currentStreamingMessage?.id,\n let index = messages.firstIndex(where: { $0.id == messageId })\n else {\n return\n }\n\n messages[index].content = content\n messages[index].isStreaming = false\n messages[index] = ResponseMessage(\n role: .assistant,\n content: content,\n timestamp: messages[index].timestamp,\n isStreaming: false,\n responseId: responseId)\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/ServiceSelectionView.swift",
"content": "//\n// ServiceSelectionView.swift\n// SwiftOpenAIExample\n//\n// Created by Lou Zell on 3/27/24.\n//\n\nimport SwiftUI\n\nstruct ServiceSelectionView: View {\n var body: some View {\n NavigationStack {\n List {\n Section(\"Select Service\") {\n NavigationLink(destination: ApiKeyIntroView()) {\n VStack(alignment: .leading) {\n Text(\"Default OpenAI Service\")\n .padding(.bottom, 10)\n Group {\n Text(\"Use this service to test SwiftOpenAI functionality by providing your own OpenAI key.\")\n }\n .font(.caption)\n .fontWeight(.light)\n }\n }\n\n NavigationLink(destination: AIProxyIntroView()) {\n VStack(alignment: .leading) {\n Text(\"AIProxy Service\")\n .padding(.bottom, 10)\n Group {\n Text(\n \"Use this service to test SwiftOpenAI functionality with requests proxied through AIProxy for key protection.\")\n }\n .font(.caption)\n .fontWeight(.light)\n }\n }\n\n NavigationLink(destination: LocalHostEntryView()) {\n VStack(alignment: .leading) {\n Text(\"Ollama\")\n .padding(.bottom, 10)\n Group {\n Text(\"Use this service to test SwiftOpenAI functionality by providing your own local host.\")\n }\n .font(.caption)\n .fontWeight(.light)\n }\n }\n }\n }\n }\n }\n}\n\n#Preview {\n ServiceSelectionView()\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/SharedModels/ChatDisplayMessage.swift",
"content": "//\n// ChatDisplayMessage.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/4/23.\n//\n\nimport Foundation\nimport SwiftOpenAI\n\nstruct ChatDisplayMessage: Identifiable {\n init(\n id: UUID = UUID(),\n content: DisplayContent,\n type: DisplayMessageType,\n delta: ChatDisplayMessage.Delta?)\n {\n self.id = id\n self.content = content\n self.type = type\n self.delta = delta\n }\n\n struct Delta {\n var role: String\n var content: String\n var functionCallName: String?\n var functionCallArguments: String?\n }\n\n enum DisplayContent: Equatable {\n case text(String)\n case images([URL])\n case content([ChatCompletionParameters.Message.ContentType.MessageContent])\n case error(String)\n\n static func ==(lhs: DisplayContent, rhs: DisplayContent) -> Bool {\n switch (lhs, rhs) {\n case (.images(let a), .images(let b)):\n a == b\n case (.content(let a), .content(let b)):\n a == b\n case (.error(let a), .error(let b)):\n a == b\n default:\n false\n }\n }\n }\n\n enum DisplayMessageType {\n case received, sent\n }\n\n let id: UUID\n let content: DisplayContent\n let type: DisplayMessageType\n let delta: Delta?\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/SharedUI/ChatDisplayMessageView.swift",
"content": "//\n// ChatDisplayMessageView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/4/23.\n//\n\nimport SwiftUI\n\nstruct ChatDisplayMessageView: View {\n let message: ChatDisplayMessage\n\n var body: some View {\n VStack(alignment: .leading, spacing: 8) {\n headerFor(message: message)\n Group {\n switch message.content {\n case .content(let content):\n let text = content.compactMap { contentItem -> String? in\n if case .text(let text) = contentItem {\n return text\n } else {\n return nil\n }\n }.first ?? \"\"\n\n let urls = content.compactMap { contentItem -> URL? in\n if case .imageUrl(let imageDetail) = contentItem {\n return imageDetail.url\n } else {\n return nil\n }\n }\n VStack(alignment: .leading, spacing: 8) {\n chatImagesViewFrom(urls: urls)\n chatMessageViewWith(text)\n }\n\n case .error(let error):\n Text(error)\n .padding()\n .font(.callout)\n .background(\n RoundedRectangle(cornerRadius: 20)\n .foregroundColor(.red.opacity(0.7)))\n\n case .text(let text):\n chatMessageViewWith(text)\n\n case .images(let urls):\n chatImagesViewFrom(urls: urls)\n }\n }\n .padding(.leading, 23)\n }\n }\n\n @ViewBuilder\n func chatMessageViewWith(\n _ text: String)\n -> some View\n {\n if text.isEmpty {\n ChatMessageLoadingView(animationDuration: 0.5)\n .frame(width: 10, height: 10)\n } else {\n Text(text)\n .font(.body)\n }\n }\n\n func headerFor(\n message: ChatDisplayMessage)\n -> some View\n {\n HStack {\n Image(systemName: message.type == .sent ? \"person.circle\" : \"wand.and.stars\")\n .resizable()\n .frame(width: 15, height: 15)\n Text(message.type == .sent ? \"USER\" : \"CHATGPT\")\n .font(.caption2)\n }\n .foregroundColor(.gray.opacity(0.9))\n }\n\n func chatImagesViewFrom(\n urls: [URL])\n -> some View\n {\n ScrollView(.horizontal, showsIndicators: false) {\n HStack(spacing: 8) {\n ForEach(urls, id: \\.self) { url in\n URLImageView(url: url)\n }\n }\n }\n }\n\n @State private var urls = [URL]()\n}\n\n#Preview {\n VStack(alignment: .leading) {\n ChatDisplayMessageView(message: .init(content: .text(\"How are you?\"), type: .sent, delta: nil))\n ChatDisplayMessageView(message: .init(content: .text(\"I am ok\"), type: .received, delta: nil))\n ChatDisplayMessageView(message: .init(content: .images([]), type: .received, delta: nil))\n }\n .padding()\n .frame(maxWidth: .infinity, alignment: .leading)\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/SharedUI/ChatMessageLoadingView.swift",
"content": "//\n// ChatMessageLoadingView.swift\n//\n//\n// Created by James Rochabrun on 3/28/24.\n//\n\nimport Foundation\nimport SwiftUI\n\nstruct ChatMessageLoadingView: View {\n var animationDuration: Double\n @State private var isScaledUp = false\n\n var body: some View {\n Circle()\n .scaleEffect(isScaledUp ? 1.5 : 1) // 1.5 is 150% size, 1 is 100% size\n .onAppear {\n withAnimation(Animation.easeInOut(duration: animationDuration).repeatForever(autoreverses: true)) {\n isScaledUp.toggle()\n }\n }\n }\n}\n\n#Preview {\n ChatMessageLoadingView(animationDuration: 0.2)\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/SharedUI/LoadingView.swift",
"content": "//\n// LoadingView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/4/23.\n//\n\nimport SwiftUI\n\nstruct LoadingView: View {\n let timer = Timer.publish(every: 0.5, on: .main, in: .common).autoconnect()\n\n var body: some View {\n HStack {\n Text(\"\\(getDots())\")\n .font(.title)\n .onReceive(timer) { _ in\n withAnimation {\n dotsCount = (dotsCount + 1) % 4\n }\n }\n }\n .frame(minHeight: 40)\n }\n\n func getDots() -> String {\n String(repeating: \".\", count: dotsCount)\n }\n\n @State private var dotsCount = 0\n\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/SharedUI/Theme/Sizes.swift",
"content": "//\n// Sizes.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/13/23.\n//\n\nimport Foundation\n\n// MARK: - Sizes\n\nenum Sizes { }\n\nextension Sizes {\n static let spacingExtraSmall: CGFloat = 4.0\n static let spacingSmall: CGFloat = 6\n static let spacingMedium: CGFloat = 8\n static let spacingLarge: CGFloat = 12\n static let spacingExtraLarge: CGFloat = 16\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/SharedUI/Theme/ThemeColor.swift",
"content": "//\n// ThemeColor.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/13/23.\n//\n\nimport SwiftUI\n\n// MARK: - ThemeColor\n\nenum ThemeColor { }\n\nextension ThemeColor {\n static let tintColor = Color.purple\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/SharedUI/URLImageView.swift",
"content": "//\n// URLImageView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/4/23.\n//\n\nimport SwiftUI\n\n// MARK: - URLImageView\n\nstruct URLImageView: View {\n let url: URL\n\n var body: some View {\n AsyncImage(\n url: url,\n transaction: Transaction(animation: .easeInOut))\n { phase in\n switch phase {\n case .empty:\n ProgressView()\n\n case .success(let image):\n image\n .resizable()\n .frame(width: 100, height: 100)\n .transition(.opacity)\n\n case .failure:\n Image(systemName: \"wifi.slash\")\n\n @unknown default:\n EmptyView()\n }\n }\n .frame(width: 100, height: 100)\n .background(Color.gray)\n .clipShape(RoundedRectangle(cornerRadius: 10))\n }\n}\n\nlet urlImageViewMockURL =\n URL(\n string: \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\")!\n\n#Preview {\n ScrollView {\n VStack(spacing: 40) {\n URLImageView(url: urlImageViewMockURL)\n URLImageView(url: urlImageViewMockURL)\n .clipShape(Circle())\n .overlay(Circle().stroke(Color.white, lineWidth: 4))\n .shadow(radius: 10)\n URLImageView(url: urlImageViewMockURL)\n .clipShape(Circle())\n .overlay(Circle().stroke(Color.white, lineWidth: 4))\n }\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/SwiftOpenAIExample.entitlements",
"content": "\n\n\n\n com.apple.security.app-sandbox\n \n com.apple.security.files.user-selected.read-only\n \n\n\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/SwiftOpenAIExampleApp.swift",
"content": "//\n// SwiftOpenAIExampleApp.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/19/23.\n//\n\nimport SwiftUI\n\n@main\nstruct SwiftOpenAIExampleApp: App {\n var body: some Scene {\n WindowGroup {\n ServiceSelectionView()\n }\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Utilities/ContentLoader.swift",
"content": "//\n// ContentLoader.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 10/19/23.\n//\n\nimport Foundation\n\nstruct ContentLoader {\n enum Error: Swift.Error {\n case fileNotFound(name: String)\n case fileDecodingFailed(name: String, Swift.Error)\n }\n\n func urlFromAsset(fromFileNamed name: String, ext: String) -> URL? {\n guard\n let url = Bundle.main.url(\n forResource: name,\n withExtension: ext)\n else {\n return nil\n }\n return url\n }\n\n func loadBundledContent(fromFileNamed name: String, ext: String) throws -> Data {\n guard let url = urlFromAsset(fromFileNamed: name, ext: ext) else {\n throw Error.fileNotFound(name: name)\n }\n\n do {\n return try Data(contentsOf: url)\n } catch {\n throw Error.fileDecodingFailed(name: name, error)\n }\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Vision/ChatVisionDemoView.swift",
"content": "//\n// ChatVisionDemoView.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/8/23.\n//\n\nimport PhotosUI\nimport SwiftOpenAI\nimport SwiftUI\n\nstruct ChatVisionDemoView: View {\n init(service: OpenAIService, customModel: String? = nil) {\n self.customModel = customModel\n _chatProvider = State(initialValue: ChatVisionProvider(service: service, customModel: customModel))\n }\n\n let customModel: String?\n\n var body: some View {\n ScrollViewReader { proxy in\n VStack {\n List(chatProvider.chatMessages) { message in\n ChatDisplayMessageView(message: message)\n .listRowSeparator(.hidden)\n }\n .listStyle(.plain)\n .onChange(of: chatProvider.chatMessages.last?.content) {\n let lastMessage = chatProvider.chatMessages.last\n if let id = lastMessage?.id {\n proxy.scrollTo(id, anchor: .bottom)\n }\n }\n textArea\n }\n }\n }\n\n var textArea: some View {\n HStack(spacing: 0) {\n photoPicker\n VStack(alignment: .leading, spacing: 0) {\n if !selectedImages.isEmpty {\n selectedImagesView\n Divider()\n .foregroundColor(.gray)\n }\n textField\n .padding(6)\n }\n .padding(.vertical, 2)\n .padding(.horizontal, 2)\n .animation(.bouncy, value: selectedImages.isEmpty)\n .background(\n RoundedRectangle(cornerRadius: 16)\n .stroke(.gray, lineWidth: 1))\n .padding(.horizontal, 8)\n textAreSendButton\n }\n .padding(.horizontal)\n .disabled(isLoading)\n }\n\n var textField: some View {\n TextField(\n \"How Can I help you today?\",\n text: $prompt,\n axis: .vertical)\n }\n\n var textAreSendButton: some View {\n Button {\n Task {\n isLoading = true\n defer {\n // ensure isLoading is set to false after the function executes.\n isLoading = false\n }\n /// Make the request\n let content: [ChatCompletionParameters.Message.ContentType.MessageContent] = [\n .text(prompt),\n ] + selectedImageURLS.map { .imageUrl(.init(url: $0)) }\n resetInput()\n let model: Model =\n if let customModel, !customModel.isEmpty {\n .custom(customModel)\n } else {\n .gpt4o\n }\n\n try await chatProvider.startStreamedChat(parameters: .init(\n messages: [.init(role: .user, content: .contentArray(content))],\n model: model, maxTokens: 300), content: content)\n }\n } label: {\n Image(systemName: \"paperplane\")\n }\n .buttonStyle(.bordered)\n .disabled(prompt.isEmpty)\n }\n\n var photoPicker: some View {\n PhotosPicker(selection: $selectedItems, matching: .images) {\n Image(systemName: \"photo\")\n }\n .onChange(of: selectedItems) {\n Task {\n selectedImages.removeAll()\n for item in selectedItems {\n if let data = try? await item.loadTransferable(type: Data.self) {\n let base64String = data.base64EncodedString()\n let url = URL(string: \"data:image/jpeg;base64,\\(base64String)\")!\n selectedImageURLS.append(url)\n if let uiImage = UIImage(data: data) {\n let image = Image(uiImage: uiImage)\n selectedImages.append(image)\n }\n }\n }\n }\n }\n }\n\n var selectedImagesView: some View {\n HStack(spacing: 0) {\n ForEach(0 ..< selectedImages.count, id: \\.self) { i in\n selectedImages[i]\n .resizable()\n .frame(width: 60, height: 60)\n .clipShape(RoundedRectangle(cornerRadius: 12))\n .padding(4)\n }\n }\n }\n\n @State private var chatProvider: ChatVisionProvider\n @State private var isLoading = false\n @State private var prompt = \"\"\n @State private var selectedItems = [PhotosPickerItem]()\n @State private var selectedImages = [Image]()\n @State private var selectedImageURLS = [URL]()\n\n /// Called when the user taps on the send button. Clears the selected images and prompt.\n private func resetInput() {\n prompt = \"\"\n selectedImages = []\n selectedItems = []\n selectedImageURLS = []\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample/Vision/ChatVisionProvider.swift",
"content": "//\n// ChatVisionProvider.swift\n// SwiftOpenAIExample\n//\n// Created by James Rochabrun on 11/9/23.\n//\n\nimport SwiftOpenAI\nimport SwiftUI\n\n@Observable\nclass ChatVisionProvider {\n init(service: OpenAIService, customModel: String? = nil) {\n self.service = service\n self.customModel = customModel\n }\n\n // MARK: - Initializer\n\n let customModel: String?\n\n // MARK: - Public Properties\n\n /// A collection of messages for display in the UI, representing the conversation.\n var chatMessages = [ChatDisplayMessage]()\n\n // MARK: - Public Methods\n\n func startStreamedChat(\n parameters: ChatCompletionParameters,\n content: [ChatCompletionParameters.Message.ContentType.MessageContent])\n async throws\n {\n // Displays the user message in the UI\n await startNewUserDisplayMessage(content)\n // Start a new assistant message that is initially empty.\n await startNewAssistantEmptyDisplayMessage()\n\n do {\n // Begin the chat stream with the updated parameters.\n let stream = try await service.startStreamedChat(parameters: parameters)\n for try await result in stream {\n // Extract the first choice from the stream results, if none exist, exit the loop.\n guard let choice = result.choices?.first else { return }\n\n // Store initial `role` and `functionCall` data from the first `choice.delta` for UI display.\n // This information is essential for maintaining context in the conversation and for updating\n // the chat UI with proper role attributions for each message.\n var newDelta = ChatDisplayMessage.Delta(role: \"\", content: \"\")\n if let firstDelta = firstChatMessageResponseDelta[result.id ?? \"\"] {\n // If we have already stored the first delta for this result ID, reuse its role.\n newDelta.role = firstDelta.role!\n } else {\n // Otherwise, store the first delta received for future reference.\n firstChatMessageResponseDelta[result.id ?? \"\"] = choice.delta\n }\n // Assign the content received in the current message to the newDelta.\n newDelta.content = temporalReceivedMessageContent\n // Update the UI with the latest assistant message and the corresponding delta.\n await updateLastAssistantMessage(content: choice.delta?.content ?? \"\", delta: newDelta)\n }\n } catch {\n // If an error occurs, update the UI to display the error message.\n updateLastDisplayedMessage(.init(content: .error(\"\\(error)\"), type: .received, delta: nil))\n }\n }\n\n // MARK: - Private Properties\n\n private let service: OpenAIService\n\n /// Accumulates the streamed message content for real-time display updates in the UI.\n private var temporalReceivedMessageContent = \"\"\n /// Tracks the identifier of the last message displayed, enabling updates in the from the streaming API response.\n private var lastDisplayedMessageID: UUID?\n /// Stores the initial chat message's delta, which uniquely includes metadata like `role`.\n private var firstChatMessageResponseDelta = [String: ChatCompletionChunkObject.ChatChoice.Delta]()\n\n // MARK: - Private Methods\n\n @MainActor\n private func startNewUserDisplayMessage(_ content: [ChatCompletionParameters.Message.ContentType.MessageContent]) {\n // Updates the UI with\n let startingMessage = ChatDisplayMessage(\n content: .content(content),\n type: .sent, delta: nil)\n addMessage(startingMessage)\n }\n\n @MainActor\n private func startNewAssistantEmptyDisplayMessage() {\n firstChatMessageResponseDelta = [:]\n temporalReceivedMessageContent = \"\"\n let newMessage = ChatDisplayMessage(content: .text(temporalReceivedMessageContent), type: .received, delta: nil)\n let newMessageId = newMessage.id\n lastDisplayedMessageID = newMessageId\n addMessage(newMessage)\n }\n\n @MainActor\n private func updateLastAssistantMessage(\n content: String,\n delta: ChatDisplayMessage.Delta)\n {\n temporalReceivedMessageContent += content\n guard let id = lastDisplayedMessageID, let index = chatMessages.firstIndex(where: { $0.id == id }) else { return }\n chatMessages[index] = ChatDisplayMessage(\n id: id,\n content: .text(temporalReceivedMessageContent),\n type: .received,\n delta: delta)\n }\n\n @MainActor\n private func addMessage(_ message: ChatDisplayMessage) {\n withAnimation {\n chatMessages.append(message)\n }\n }\n\n private func updateLastDisplayedMessage(_ message: ChatDisplayMessage) {\n chatMessages[chatMessages.count - 1] = message\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample.xcodeproj/project.pbxproj",
"content": "// !$*UTF8*$!\n{\n\tarchiveVersion = 1;\n\tclasses = {\n\t};\n\tobjectVersion = 60;\n\tobjects = {\n\n/* Begin PBXBuildFile section */\n\t\t0DEE5DC12BB40643004894AD /* SwiftOpenAI in Frameworks */ = {isa = PBXBuildFile; productRef = 0DEE5DC02BB40643004894AD /* SwiftOpenAI */; };\n\t\t0DF957842BB53BEF00DD2013 /* ServiceSelectionView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 0DF957832BB53BEF00DD2013 /* ServiceSelectionView.swift */; };\n\t\t0DF957862BB543F100DD2013 /* AIProxyIntroView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 0DF957852BB543F100DD2013 /* AIProxyIntroView.swift */; };\n\t\t7B029E372C6893FD0025681A /* ChatStructuredOutputProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B029E362C6893FD0025681A /* ChatStructuredOutputProvider.swift */; };\n\t\t7B029E392C68940D0025681A /* ChatStructuredOutputDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B029E382C68940D0025681A /* ChatStructuredOutputDemoView.swift */; };\n\t\t7B029E3C2C69BE990025681A /* ChatStructuredOutputToolProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B029E3B2C69BE990025681A /* ChatStructuredOutputToolProvider.swift */; };\n\t\t7B029E3E2C69BEA70025681A /* ChatStructureOutputToolDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B029E3D2C69BEA70025681A /* ChatStructureOutputToolDemoView.swift */; };\n\t\t7B1268052B08246400400694 /* AssistantConfigurationDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B1268042B08246400400694 /* AssistantConfigurationDemoView.swift */; };\n\t\t7B1268072B08247C00400694 /* AssistantConfigurationProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B1268062B08247C00400694 /* AssistantConfigurationProvider.swift */; };\n\t\t7B2B6D562DF434670059B4BB /* ResponseStreamDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B2B6D552DF434670059B4BB /* ResponseStreamDemoView.swift */; };\n\t\t7B2B6D582DF4347E0059B4BB /* ResponseStreamProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B2B6D572DF4347E0059B4BB /* ResponseStreamProvider.swift */; };\n\t\t7B3DDCC52BAAA722004B5C96 /* AssistantsListDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B3DDCC42BAAA722004B5C96 /* AssistantsListDemoView.swift */; };\n\t\t7B3DDCC72BAAAD34004B5C96 /* AssistantThreadConfigurationProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B3DDCC62BAAAD34004B5C96 /* AssistantThreadConfigurationProvider.swift */; };\n\t\t7B3DDCC92BAAAF96004B5C96 /* AssistantStreamDemoScreen.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B3DDCC82BAAAF96004B5C96 /* AssistantStreamDemoScreen.swift */; };\n\t\t7B413DFE2BB6846D009684CD /* ChatMessageLoadingView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B413DFD2BB6846D009684CD /* ChatMessageLoadingView.swift */; };\n\t\t7B436B962AE24A04003CE281 /* OptionsListView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436B952AE24A04003CE281 /* OptionsListView.swift */; };\n\t\t7B436B992AE25052003CE281 /* ContentLoader.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436B982AE25052003CE281 /* ContentLoader.swift */; };\n\t\t7B436B9B2AE25094003CE281 /* narcos.m4a in Resources */ = {isa = PBXBuildFile; fileRef = 7B436B9A2AE25093003CE281 /* narcos.m4a */; };\n\t\t7B436B9E2AE256BC003CE281 /* german.m4a in Resources */ = {isa = PBXBuildFile; fileRef = 7B436B9D2AE256BC003CE281 /* german.m4a */; };\n\t\t7B436BA12AE25958003CE281 /* ChatProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BA02AE25958003CE281 /* ChatProvider.swift */; };\n\t\t7B436BA32AE25962003CE281 /* ChatDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BA22AE25962003CE281 /* ChatDemoView.swift */; };\n\t\t7B436BA62AE77F37003CE281 /* Embeddingsprovider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BA52AE77F37003CE281 /* Embeddingsprovider.swift */; };\n\t\t7B436BA82AE77F41003CE281 /* EmbeddingsDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BA72AE77F41003CE281 /* EmbeddingsDemoView.swift */; };\n\t\t7B436BAB2AE788F1003CE281 /* FineTuningJobProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BAA2AE788F1003CE281 /* FineTuningJobProvider.swift */; };\n\t\t7B436BAD2AE788FB003CE281 /* FineTuningJobDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BAC2AE788FB003CE281 /* FineTuningJobDemoView.swift */; };\n\t\t7B436BB02AE79369003CE281 /* FilesDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BAF2AE79369003CE281 /* FilesDemoView.swift */; };\n\t\t7B436BB22AE79370003CE281 /* FilesProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BB12AE79370003CE281 /* FilesProvider.swift */; };\n\t\t7B436BB42AE79481003CE281 /* WorldCupData.jsonl in Resources */ = {isa = PBXBuildFile; fileRef = 7B436BB32AE79481003CE281 /* WorldCupData.jsonl */; };\n\t\t7B436BB72AE7A2EA003CE281 /* ImagesProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BB62AE7A2EA003CE281 /* ImagesProvider.swift */; };\n\t\t7B436BB92AE7A2F2003CE281 /* ImagesDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BB82AE7A2F2003CE281 /* ImagesDemoView.swift */; };\n\t\t7B436BBC2AE7ABD3003CE281 /* ModelsProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BBB2AE7ABD3003CE281 /* ModelsProvider.swift */; };\n\t\t7B436BBE2AE7ABDA003CE281 /* ModelsDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BBD2AE7ABDA003CE281 /* ModelsDemoView.swift */; };\n\t\t7B436BC12AE7B01F003CE281 /* ModerationProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BC02AE7B01F003CE281 /* ModerationProvider.swift */; };\n\t\t7B436BC32AE7B027003CE281 /* ModerationDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B436BC22AE7B027003CE281 /* ModerationDemoView.swift */; };\n\t\t7B50DD282C2A9A390070A64D /* LocalHostEntryView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B50DD272C2A9A390070A64D /* LocalHostEntryView.swift */; };\n\t\t7B50DD2B2C2A9D2F0070A64D /* LocalChatDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B50DD2A2C2A9D2F0070A64D /* LocalChatDemoView.swift */; };\n\t\t7B7239A02AF625F200646679 /* ChatFluidConversationProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B72399F2AF625F200646679 /* ChatFluidConversationProvider.swift */; };\n\t\t7B7239A22AF6260D00646679 /* ChatDisplayMessage.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B7239A12AF6260D00646679 /* ChatDisplayMessage.swift */; };\n\t\t7B7239A42AF6289900646679 /* ChatStreamFluidConversationDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B7239A32AF6289900646679 /* ChatStreamFluidConversationDemoView.swift */; };\n\t\t7B7239A62AF628F800646679 /* ChatDisplayMessageView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B7239A52AF628F800646679 /* ChatDisplayMessageView.swift */; };\n\t\t7B7239A82AF6292100646679 /* LoadingView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B7239A72AF6292100646679 /* LoadingView.swift */; };\n\t\t7B7239AB2AF6294C00646679 /* URLImageView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B7239AA2AF6294C00646679 /* URLImageView.swift */; };\n\t\t7B7239AE2AF9FF0000646679 /* ChatFunctionsCallStreamProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B7239AD2AF9FF0000646679 /* ChatFunctionsCallStreamProvider.swift */; };\n\t\t7B7239B12AF9FF3C00646679 /* ChatFunctionsCalllStreamDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B7239B02AF9FF3C00646679 /* ChatFunctionsCalllStreamDemoView.swift */; };\n\t\t7B99C2E72C0718DE00E701B3 /* FilesPicker.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B99C2E62C0718DE00E701B3 /* FilesPicker.swift */; };\n\t\t7B99C2E92C0718FF00E701B3 /* FileAttachmentView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B99C2E82C0718FF00E701B3 /* FileAttachmentView.swift */; };\n\t\t7B99C2EB2C07191200E701B3 /* AttachmentView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B99C2EA2C07191200E701B3 /* AttachmentView.swift */; };\n\t\t7B99C2ED2C071B1600E701B3 /* FilesPickerProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7B99C2EC2C071B1600E701B3 /* FilesPickerProvider.swift */; };\n\t\t7BA788CD2AE23A48008825D5 /* SwiftOpenAIExampleApp.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BA788CC2AE23A48008825D5 /* SwiftOpenAIExampleApp.swift */; };\n\t\t7BA788CF2AE23A48008825D5 /* ApiKeyIntroView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BA788CE2AE23A48008825D5 /* ApiKeyIntroView.swift */; };\n\t\t7BA788D12AE23A49008825D5 /* Assets.xcassets in Resources */ = {isa = PBXBuildFile; fileRef = 7BA788D02AE23A49008825D5 /* Assets.xcassets */; };\n\t\t7BA788D52AE23A49008825D5 /* Preview Assets.xcassets in Resources */ = {isa = PBXBuildFile; fileRef = 7BA788D42AE23A49008825D5 /* Preview Assets.xcassets */; };\n\t\t7BA788E92AE23A49008825D5 /* SwiftOpenAIExampleUITests.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BA788E82AE23A49008825D5 /* SwiftOpenAIExampleUITests.swift */; };\n\t\t7BA788EB2AE23A49008825D5 /* SwiftOpenAIExampleUITestsLaunchTests.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BA788EA2AE23A49008825D5 /* SwiftOpenAIExampleUITestsLaunchTests.swift */; };\n\t\t7BA788FC2AE23B42008825D5 /* AudioDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BA788FB2AE23B42008825D5 /* AudioDemoView.swift */; };\n\t\t7BA788FE2AE23B95008825D5 /* AudioProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BA788FD2AE23B95008825D5 /* AudioProvider.swift */; };\n\t\t7BBE7E912AFCA52A0096A693 /* ChatVisionDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BBE7E902AFCA52A0096A693 /* ChatVisionDemoView.swift */; };\n\t\t7BBE7E942AFCC9640096A693 /* ChatVisionProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BBE7E932AFCC9640096A693 /* ChatVisionProvider.swift */; };\n\t\t7BBE7EA52B02E8A70096A693 /* Sizes.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BBE7EA42B02E8A70096A693 /* Sizes.swift */; };\n\t\t7BBE7EA72B02E8AC0096A693 /* ThemeColor.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BBE7EA62B02E8AC0096A693 /* ThemeColor.swift */; };\n\t\t7BBE7EA92B02E8E50096A693 /* ChatMessageView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BBE7EA82B02E8E50096A693 /* ChatMessageView.swift */; };\n\t\t7BBE7EAB2B02E8FC0096A693 /* ChatMessageDisplayModel.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BBE7EAA2B02E8FC0096A693 /* ChatMessageDisplayModel.swift */; };\n\t\t7BBE7EDE2B03718E0096A693 /* ChatFunctionCallProvider.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BBE7EDD2B03718E0096A693 /* ChatFunctionCallProvider.swift */; };\n\t\t7BBE7EE02B0372550096A693 /* ChatFunctionCallDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BBE7EDF2B0372550096A693 /* ChatFunctionCallDemoView.swift */; };\n\t\t7BE802592D2878170080E06A /* ChatPredictedOutputDemoView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BE802582D2878170080E06A /* ChatPredictedOutputDemoView.swift */; };\n\t\t7BE9A5AF2B0B33E600CE8103 /* SwiftOpenAIExampleTests.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7BA788DE2AE23A49008825D5 /* SwiftOpenAIExampleTests.swift */; };\n/* End PBXBuildFile section */\n\n/* Begin PBXContainerItemProxy section */\n\t\t7BA788DB2AE23A49008825D5 /* PBXContainerItemProxy */ = {\n\t\t\tisa = PBXContainerItemProxy;\n\t\t\tcontainerPortal = 7BA788C12AE23A48008825D5 /* Project object */;\n\t\t\tproxyType = 1;\n\t\t\tremoteGlobalIDString = 7BA788C82AE23A48008825D5;\n\t\t\tremoteInfo = SwiftOpenAIExample;\n\t\t};\n\t\t7BA788E52AE23A49008825D5 /* PBXContainerItemProxy */ = {\n\t\t\tisa = PBXContainerItemProxy;\n\t\t\tcontainerPortal = 7BA788C12AE23A48008825D5 /* Project object */;\n\t\t\tproxyType = 1;\n\t\t\tremoteGlobalIDString = 7BA788C82AE23A48008825D5;\n\t\t\tremoteInfo = SwiftOpenAIExample;\n\t\t};\n/* End PBXContainerItemProxy section */\n\n/* Begin PBXFileReference section */\n\t\t0DF957832BB53BEF00DD2013 /* ServiceSelectionView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ServiceSelectionView.swift; sourceTree = \"\"; };\n\t\t0DF957852BB543F100DD2013 /* AIProxyIntroView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = AIProxyIntroView.swift; sourceTree = \"\"; };\n\t\t7B029E362C6893FD0025681A /* ChatStructuredOutputProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatStructuredOutputProvider.swift; sourceTree = \"\"; };\n\t\t7B029E382C68940D0025681A /* ChatStructuredOutputDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatStructuredOutputDemoView.swift; sourceTree = \"\"; };\n\t\t7B029E3B2C69BE990025681A /* ChatStructuredOutputToolProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatStructuredOutputToolProvider.swift; sourceTree = \"\"; };\n\t\t7B029E3D2C69BEA70025681A /* ChatStructureOutputToolDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatStructureOutputToolDemoView.swift; sourceTree = \"\"; };\n\t\t7B1268042B08246400400694 /* AssistantConfigurationDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = AssistantConfigurationDemoView.swift; sourceTree = \"\"; };\n\t\t7B1268062B08247C00400694 /* AssistantConfigurationProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = AssistantConfigurationProvider.swift; sourceTree = \"\"; };\n\t\t7B2B6D552DF434670059B4BB /* ResponseStreamDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ResponseStreamDemoView.swift; sourceTree = \"\"; };\n\t\t7B2B6D572DF4347E0059B4BB /* ResponseStreamProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ResponseStreamProvider.swift; sourceTree = \"\"; };\n\t\t7B3DDCC42BAAA722004B5C96 /* AssistantsListDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = AssistantsListDemoView.swift; sourceTree = \"\"; };\n\t\t7B3DDCC62BAAAD34004B5C96 /* AssistantThreadConfigurationProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = AssistantThreadConfigurationProvider.swift; sourceTree = \"\"; };\n\t\t7B3DDCC82BAAAF96004B5C96 /* AssistantStreamDemoScreen.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = AssistantStreamDemoScreen.swift; sourceTree = \"\"; };\n\t\t7B413DFD2BB6846D009684CD /* ChatMessageLoadingView.swift */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.swift; path = ChatMessageLoadingView.swift; sourceTree = \"\"; };\n\t\t7B436B952AE24A04003CE281 /* OptionsListView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = OptionsListView.swift; sourceTree = \"\"; };\n\t\t7B436B982AE25052003CE281 /* ContentLoader.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ContentLoader.swift; sourceTree = \"\"; };\n\t\t7B436B9A2AE25093003CE281 /* narcos.m4a */ = {isa = PBXFileReference; lastKnownFileType = file; path = narcos.m4a; sourceTree = \"\"; };\n\t\t7B436B9D2AE256BC003CE281 /* german.m4a */ = {isa = PBXFileReference; lastKnownFileType = file; path = german.m4a; sourceTree = \"\"; };\n\t\t7B436BA02AE25958003CE281 /* ChatProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatProvider.swift; sourceTree = \"\"; };\n\t\t7B436BA22AE25962003CE281 /* ChatDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatDemoView.swift; sourceTree = \"\"; };\n\t\t7B436BA52AE77F37003CE281 /* Embeddingsprovider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = Embeddingsprovider.swift; sourceTree = \"\"; };\n\t\t7B436BA72AE77F41003CE281 /* EmbeddingsDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = EmbeddingsDemoView.swift; sourceTree = \"\"; };\n\t\t7B436BAA2AE788F1003CE281 /* FineTuningJobProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = FineTuningJobProvider.swift; sourceTree = \"\"; };\n\t\t7B436BAC2AE788FB003CE281 /* FineTuningJobDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = FineTuningJobDemoView.swift; sourceTree = \"\"; };\n\t\t7B436BAF2AE79369003CE281 /* FilesDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = FilesDemoView.swift; sourceTree = \"\"; };\n\t\t7B436BB12AE79370003CE281 /* FilesProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = FilesProvider.swift; sourceTree = \"\"; };\n\t\t7B436BB32AE79481003CE281 /* WorldCupData.jsonl */ = {isa = PBXFileReference; lastKnownFileType = text; path = WorldCupData.jsonl; sourceTree = \"\"; };\n\t\t7B436BB62AE7A2EA003CE281 /* ImagesProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ImagesProvider.swift; sourceTree = \"\"; };\n\t\t7B436BB82AE7A2F2003CE281 /* ImagesDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ImagesDemoView.swift; sourceTree = \"\"; };\n\t\t7B436BBB2AE7ABD3003CE281 /* ModelsProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ModelsProvider.swift; sourceTree = \"\"; };\n\t\t7B436BBD2AE7ABDA003CE281 /* ModelsDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ModelsDemoView.swift; sourceTree = \"\"; };\n\t\t7B436BC02AE7B01F003CE281 /* ModerationProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ModerationProvider.swift; sourceTree = \"\"; };\n\t\t7B436BC22AE7B027003CE281 /* ModerationDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ModerationDemoView.swift; sourceTree = \"\"; };\n\t\t7B50DD272C2A9A390070A64D /* LocalHostEntryView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = LocalHostEntryView.swift; sourceTree = \"\"; };\n\t\t7B50DD2A2C2A9D2F0070A64D /* LocalChatDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = LocalChatDemoView.swift; sourceTree = \"\"; };\n\t\t7B72399F2AF625F200646679 /* ChatFluidConversationProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatFluidConversationProvider.swift; sourceTree = \"\"; };\n\t\t7B7239A12AF6260D00646679 /* ChatDisplayMessage.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatDisplayMessage.swift; sourceTree = \"\"; };\n\t\t7B7239A32AF6289900646679 /* ChatStreamFluidConversationDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatStreamFluidConversationDemoView.swift; sourceTree = \"\"; };\n\t\t7B7239A52AF628F800646679 /* ChatDisplayMessageView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatDisplayMessageView.swift; sourceTree = \"\"; };\n\t\t7B7239A72AF6292100646679 /* LoadingView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = LoadingView.swift; sourceTree = \"\"; };\n\t\t7B7239AA2AF6294C00646679 /* URLImageView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = URLImageView.swift; sourceTree = \"\"; };\n\t\t7B7239AD2AF9FF0000646679 /* ChatFunctionsCallStreamProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatFunctionsCallStreamProvider.swift; sourceTree = \"\"; };\n\t\t7B7239B02AF9FF3C00646679 /* ChatFunctionsCalllStreamDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatFunctionsCalllStreamDemoView.swift; sourceTree = \"\"; };\n\t\t7B99C2E62C0718DE00E701B3 /* FilesPicker.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = FilesPicker.swift; sourceTree = \"\"; };\n\t\t7B99C2E82C0718FF00E701B3 /* FileAttachmentView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = FileAttachmentView.swift; sourceTree = \"\"; };\n\t\t7B99C2EA2C07191200E701B3 /* AttachmentView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = AttachmentView.swift; sourceTree = \"\"; };\n\t\t7B99C2EC2C071B1600E701B3 /* FilesPickerProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = FilesPickerProvider.swift; sourceTree = \"\"; };\n\t\t7BA788C92AE23A48008825D5 /* SwiftOpenAIExample.app */ = {isa = PBXFileReference; explicitFileType = wrapper.application; includeInIndex = 0; path = SwiftOpenAIExample.app; sourceTree = BUILT_PRODUCTS_DIR; };\n\t\t7BA788CC2AE23A48008825D5 /* SwiftOpenAIExampleApp.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = SwiftOpenAIExampleApp.swift; sourceTree = \"\"; };\n\t\t7BA788CE2AE23A48008825D5 /* ApiKeyIntroView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ApiKeyIntroView.swift; sourceTree = \"\"; };\n\t\t7BA788D02AE23A49008825D5 /* Assets.xcassets */ = {isa = PBXFileReference; lastKnownFileType = folder.assetcatalog; path = Assets.xcassets; sourceTree = \"\"; };\n\t\t7BA788D22AE23A49008825D5 /* SwiftOpenAIExample.entitlements */ = {isa = PBXFileReference; lastKnownFileType = text.plist.entitlements; path = SwiftOpenAIExample.entitlements; sourceTree = \"\"; };\n\t\t7BA788D42AE23A49008825D5 /* Preview Assets.xcassets */ = {isa = PBXFileReference; lastKnownFileType = folder.assetcatalog; path = \"Preview Assets.xcassets\"; sourceTree = \"\"; };\n\t\t7BA788DA2AE23A49008825D5 /* SwiftOpenAIExampleTests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = SwiftOpenAIExampleTests.xctest; sourceTree = BUILT_PRODUCTS_DIR; };\n\t\t7BA788DE2AE23A49008825D5 /* SwiftOpenAIExampleTests.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = SwiftOpenAIExampleTests.swift; sourceTree = \"\"; };\n\t\t7BA788E42AE23A49008825D5 /* SwiftOpenAIExampleUITests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = SwiftOpenAIExampleUITests.xctest; sourceTree = BUILT_PRODUCTS_DIR; };\n\t\t7BA788E82AE23A49008825D5 /* SwiftOpenAIExampleUITests.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = SwiftOpenAIExampleUITests.swift; sourceTree = \"\"; };\n\t\t7BA788EA2AE23A49008825D5 /* SwiftOpenAIExampleUITestsLaunchTests.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = SwiftOpenAIExampleUITestsLaunchTests.swift; sourceTree = \"\"; };\n\t\t7BA788FB2AE23B42008825D5 /* AudioDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = AudioDemoView.swift; sourceTree = \"\"; };\n\t\t7BA788FD2AE23B95008825D5 /* AudioProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = AudioProvider.swift; sourceTree = \"\"; };\n\t\t7BBE7E902AFCA52A0096A693 /* ChatVisionDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatVisionDemoView.swift; sourceTree = \"\"; };\n\t\t7BBE7E932AFCC9640096A693 /* ChatVisionProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatVisionProvider.swift; sourceTree = \"\"; };\n\t\t7BBE7EA42B02E8A70096A693 /* Sizes.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = Sizes.swift; sourceTree = \"\"; };\n\t\t7BBE7EA62B02E8AC0096A693 /* ThemeColor.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ThemeColor.swift; sourceTree = \"\"; };\n\t\t7BBE7EA82B02E8E50096A693 /* ChatMessageView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatMessageView.swift; sourceTree = \"\"; };\n\t\t7BBE7EAA2B02E8FC0096A693 /* ChatMessageDisplayModel.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatMessageDisplayModel.swift; sourceTree = \"\"; };\n\t\t7BBE7EDD2B03718E0096A693 /* ChatFunctionCallProvider.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatFunctionCallProvider.swift; sourceTree = \"\"; };\n\t\t7BBE7EDF2B0372550096A693 /* ChatFunctionCallDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatFunctionCallDemoView.swift; sourceTree = \"\"; };\n\t\t7BE802582D2878170080E06A /* ChatPredictedOutputDemoView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ChatPredictedOutputDemoView.swift; sourceTree = \"\"; };\n/* End PBXFileReference section */\n\n/* Begin PBXFrameworksBuildPhase section */\n\t\t7BA788C62AE23A48008825D5 /* Frameworks */ = {\n\t\t\tisa = PBXFrameworksBuildPhase;\n\t\t\tbuildActionMask = 2147483647;\n\t\t\tfiles = (\n\t\t\t\t0DEE5DC12BB40643004894AD /* SwiftOpenAI in Frameworks */,\n\t\t\t);\n\t\t\trunOnlyForDeploymentPostprocessing = 0;\n\t\t};\n\t\t7BA788D72AE23A49008825D5 /* Frameworks */ = {\n\t\t\tisa = PBXFrameworksBuildPhase;\n\t\t\tbuildActionMask = 2147483647;\n\t\t\tfiles = (\n\t\t\t);\n\t\t\trunOnlyForDeploymentPostprocessing = 0;\n\t\t};\n\t\t7BA788E12AE23A49008825D5 /* Frameworks */ = {\n\t\t\tisa = PBXFrameworksBuildPhase;\n\t\t\tbuildActionMask = 2147483647;\n\t\t\tfiles = (\n\t\t\t);\n\t\t\trunOnlyForDeploymentPostprocessing = 0;\n\t\t};\n/* End PBXFrameworksBuildPhase section */\n\n/* Begin PBXGroup section */\n\t\t7B029E352C6893BF0025681A /* ChatStructuredOutputs */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B029E362C6893FD0025681A /* ChatStructuredOutputProvider.swift */,\n\t\t\t\t7B029E382C68940D0025681A /* ChatStructuredOutputDemoView.swift */,\n\t\t\t);\n\t\t\tpath = ChatStructuredOutputs;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B029E3A2C69BE750025681A /* ChatStructureOutputTool */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B029E3B2C69BE990025681A /* ChatStructuredOutputToolProvider.swift */,\n\t\t\t\t7B029E3D2C69BEA70025681A /* ChatStructureOutputToolDemoView.swift */,\n\t\t\t);\n\t\t\tpath = ChatStructureOutputTool;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B1268032B08241200400694 /* Assistants */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B1268042B08246400400694 /* AssistantConfigurationDemoView.swift */,\n\t\t\t\t7B1268062B08247C00400694 /* AssistantConfigurationProvider.swift */,\n\t\t\t\t7B3DDCC42BAAA722004B5C96 /* AssistantsListDemoView.swift */,\n\t\t\t\t7B3DDCC62BAAAD34004B5C96 /* AssistantThreadConfigurationProvider.swift */,\n\t\t\t\t7B3DDCC82BAAAF96004B5C96 /* AssistantStreamDemoScreen.swift */,\n\t\t\t);\n\t\t\tpath = Assistants;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B2B6D542DF434550059B4BB /* ResponseAPIDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B2B6D552DF434670059B4BB /* ResponseStreamDemoView.swift */,\n\t\t\t\t7B2B6D572DF4347E0059B4BB /* ResponseStreamProvider.swift */,\n\t\t\t);\n\t\t\tpath = ResponseAPIDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B436B972AE25045003CE281 /* Utilities */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B436B982AE25052003CE281 /* ContentLoader.swift */,\n\t\t\t);\n\t\t\tpath = Utilities;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B436B9C2AE2515C003CE281 /* Resources */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B436B9D2AE256BC003CE281 /* german.m4a */,\n\t\t\t\t7B436B9A2AE25093003CE281 /* narcos.m4a */,\n\t\t\t\t7B436BB32AE79481003CE281 /* WorldCupData.jsonl */,\n\t\t\t);\n\t\t\tpath = Resources;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B436B9F2AE2593D003CE281 /* ChatDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B436BA02AE25958003CE281 /* ChatProvider.swift */,\n\t\t\t\t7B436BA22AE25962003CE281 /* ChatDemoView.swift */,\n\t\t\t);\n\t\t\tpath = ChatDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B436BA42AE77EF9003CE281 /* EmbeddingsDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B436BA52AE77F37003CE281 /* Embeddingsprovider.swift */,\n\t\t\t\t7B436BA72AE77F41003CE281 /* EmbeddingsDemoView.swift */,\n\t\t\t);\n\t\t\tpath = EmbeddingsDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B436BA92AE788CA003CE281 /* FineTuningDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B436BAA2AE788F1003CE281 /* FineTuningJobProvider.swift */,\n\t\t\t\t7B436BAC2AE788FB003CE281 /* FineTuningJobDemoView.swift */,\n\t\t\t);\n\t\t\tpath = FineTuningDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B436BAE2AE7935C003CE281 /* FilesDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B436BAF2AE79369003CE281 /* FilesDemoView.swift */,\n\t\t\t\t7B436BB12AE79370003CE281 /* FilesProvider.swift */,\n\t\t\t);\n\t\t\tpath = FilesDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B436BB52AE7A2DA003CE281 /* ImagesDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B436BB62AE7A2EA003CE281 /* ImagesProvider.swift */,\n\t\t\t\t7B436BB82AE7A2F2003CE281 /* ImagesDemoView.swift */,\n\t\t\t);\n\t\t\tpath = ImagesDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B436BBA2AE7ABC4003CE281 /* ModelsDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B436BBB2AE7ABD3003CE281 /* ModelsProvider.swift */,\n\t\t\t\t7B436BBD2AE7ABDA003CE281 /* ModelsDemoView.swift */,\n\t\t\t);\n\t\t\tpath = ModelsDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B436BBF2AE7B003003CE281 /* ModerationsDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B436BC02AE7B01F003CE281 /* ModerationProvider.swift */,\n\t\t\t\t7B436BC22AE7B027003CE281 /* ModerationDemoView.swift */,\n\t\t\t);\n\t\t\tpath = ModerationsDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B50DD292C2A9D1D0070A64D /* LocalChatDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B50DD2A2C2A9D2F0070A64D /* LocalChatDemoView.swift */,\n\t\t\t);\n\t\t\tpath = LocalChatDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B72399E2AF625B700646679 /* ChatStreamFluidConversationDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B72399F2AF625F200646679 /* ChatFluidConversationProvider.swift */,\n\t\t\t\t7B7239A32AF6289900646679 /* ChatStreamFluidConversationDemoView.swift */,\n\t\t\t);\n\t\t\tpath = ChatStreamFluidConversationDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B7239A92AF6294200646679 /* SharedUI */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BBE7EA32B02E89B0096A693 /* Theme */,\n\t\t\t\t7B7239A72AF6292100646679 /* LoadingView.swift */,\n\t\t\t\t7B7239AA2AF6294C00646679 /* URLImageView.swift */,\n\t\t\t\t7B7239A52AF628F800646679 /* ChatDisplayMessageView.swift */,\n\t\t\t\t7B413DFD2BB6846D009684CD /* ChatMessageLoadingView.swift */,\n\t\t\t);\n\t\t\tpath = SharedUI;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B7239AC2AF9FEC300646679 /* ChatFunctionsCall */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BBE7EDC2B0371670096A693 /* Completion */,\n\t\t\t\t7BBE7EDB2B0370E60096A693 /* Stream */,\n\t\t\t\t7BBE7EAA2B02E8FC0096A693 /* ChatMessageDisplayModel.swift */,\n\t\t\t\t7BBE7EA82B02E8E50096A693 /* ChatMessageView.swift */,\n\t\t\t);\n\t\t\tpath = ChatFunctionsCall;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B7239AF2AF9FF1D00646679 /* SharedModels */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B7239A12AF6260D00646679 /* ChatDisplayMessage.swift */,\n\t\t\t);\n\t\t\tpath = SharedModels;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7B99C2E52C0718CD00E701B3 /* Files */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B99C2E62C0718DE00E701B3 /* FilesPicker.swift */,\n\t\t\t\t7B99C2E82C0718FF00E701B3 /* FileAttachmentView.swift */,\n\t\t\t\t7B99C2EA2C07191200E701B3 /* AttachmentView.swift */,\n\t\t\t\t7B99C2EC2C071B1600E701B3 /* FilesPickerProvider.swift */,\n\t\t\t);\n\t\t\tpath = Files;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BA788C02AE23A48008825D5 = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BA788CB2AE23A48008825D5 /* SwiftOpenAIExample */,\n\t\t\t\t7BA788DD2AE23A49008825D5 /* SwiftOpenAIExampleTests */,\n\t\t\t\t7BA788E72AE23A49008825D5 /* SwiftOpenAIExampleUITests */,\n\t\t\t\t7BA788CA2AE23A48008825D5 /* Products */,\n\t\t\t);\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BA788CA2AE23A48008825D5 /* Products */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BA788C92AE23A48008825D5 /* SwiftOpenAIExample.app */,\n\t\t\t\t7BA788DA2AE23A49008825D5 /* SwiftOpenAIExampleTests.xctest */,\n\t\t\t\t7BA788E42AE23A49008825D5 /* SwiftOpenAIExampleUITests.xctest */,\n\t\t\t);\n\t\t\tname = Products;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BA788CB2AE23A48008825D5 /* SwiftOpenAIExample */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B2B6D542DF434550059B4BB /* ResponseAPIDemo */,\n\t\t\t\t7BA788CC2AE23A48008825D5 /* SwiftOpenAIExampleApp.swift */,\n\t\t\t\t7BE802572D2877D30080E06A /* PredictedOutputsDemo */,\n\t\t\t\t7B50DD292C2A9D1D0070A64D /* LocalChatDemo */,\n\t\t\t\t7B99C2E52C0718CD00E701B3 /* Files */,\n\t\t\t\t7B7239AF2AF9FF1D00646679 /* SharedModels */,\n\t\t\t\t7B7239A92AF6294200646679 /* SharedUI */,\n\t\t\t\t7B1268032B08241200400694 /* Assistants */,\n\t\t\t\t7BA788FA2AE23B27008825D5 /* AudioDemo */,\n\t\t\t\t7B436B9F2AE2593D003CE281 /* ChatDemo */,\n\t\t\t\t7B7239AC2AF9FEC300646679 /* ChatFunctionsCall */,\n\t\t\t\t7B029E352C6893BF0025681A /* ChatStructuredOutputs */,\n\t\t\t\t7B029E3A2C69BE750025681A /* ChatStructureOutputTool */,\n\t\t\t\t7B72399E2AF625B700646679 /* ChatStreamFluidConversationDemo */,\n\t\t\t\t7B436BA42AE77EF9003CE281 /* EmbeddingsDemo */,\n\t\t\t\t7B436BA92AE788CA003CE281 /* FineTuningDemo */,\n\t\t\t\t7B436BAE2AE7935C003CE281 /* FilesDemo */,\n\t\t\t\t7B436BB52AE7A2DA003CE281 /* ImagesDemo */,\n\t\t\t\t7B436BBA2AE7ABC4003CE281 /* ModelsDemo */,\n\t\t\t\t7B436BBF2AE7B003003CE281 /* ModerationsDemo */,\n\t\t\t\t7B436B9C2AE2515C003CE281 /* Resources */,\n\t\t\t\t7B436B972AE25045003CE281 /* Utilities */,\n\t\t\t\t7BBE7E922AFCC9300096A693 /* Vision */,\n\t\t\t\t7BA788CE2AE23A48008825D5 /* ApiKeyIntroView.swift */,\n\t\t\t\t7B50DD272C2A9A390070A64D /* LocalHostEntryView.swift */,\n\t\t\t\t0DF957852BB543F100DD2013 /* AIProxyIntroView.swift */,\n\t\t\t\t7B436B952AE24A04003CE281 /* OptionsListView.swift */,\n\t\t\t\t0DF957832BB53BEF00DD2013 /* ServiceSelectionView.swift */,\n\t\t\t\t7BA788D02AE23A49008825D5 /* Assets.xcassets */,\n\t\t\t\t7BA788D22AE23A49008825D5 /* SwiftOpenAIExample.entitlements */,\n\t\t\t\t7BA788D32AE23A49008825D5 /* Preview Content */,\n\t\t\t);\n\t\t\tpath = SwiftOpenAIExample;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BA788D32AE23A49008825D5 /* Preview Content */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BA788D42AE23A49008825D5 /* Preview Assets.xcassets */,\n\t\t\t);\n\t\t\tpath = \"Preview Content\";\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BA788DD2AE23A49008825D5 /* SwiftOpenAIExampleTests */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BA788DE2AE23A49008825D5 /* SwiftOpenAIExampleTests.swift */,\n\t\t\t);\n\t\t\tpath = SwiftOpenAIExampleTests;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BA788E72AE23A49008825D5 /* SwiftOpenAIExampleUITests */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BA788E82AE23A49008825D5 /* SwiftOpenAIExampleUITests.swift */,\n\t\t\t\t7BA788EA2AE23A49008825D5 /* SwiftOpenAIExampleUITestsLaunchTests.swift */,\n\t\t\t);\n\t\t\tpath = SwiftOpenAIExampleUITests;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BA788FA2AE23B27008825D5 /* AudioDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BA788FB2AE23B42008825D5 /* AudioDemoView.swift */,\n\t\t\t\t7BA788FD2AE23B95008825D5 /* AudioProvider.swift */,\n\t\t\t);\n\t\t\tpath = AudioDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BBE7E922AFCC9300096A693 /* Vision */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BBE7E902AFCA52A0096A693 /* ChatVisionDemoView.swift */,\n\t\t\t\t7BBE7E932AFCC9640096A693 /* ChatVisionProvider.swift */,\n\t\t\t);\n\t\t\tpath = Vision;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BBE7EA32B02E89B0096A693 /* Theme */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BBE7EA42B02E8A70096A693 /* Sizes.swift */,\n\t\t\t\t7BBE7EA62B02E8AC0096A693 /* ThemeColor.swift */,\n\t\t\t);\n\t\t\tpath = Theme;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BBE7EDB2B0370E60096A693 /* Stream */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7B7239AD2AF9FF0000646679 /* ChatFunctionsCallStreamProvider.swift */,\n\t\t\t\t7B7239B02AF9FF3C00646679 /* ChatFunctionsCalllStreamDemoView.swift */,\n\t\t\t);\n\t\t\tpath = Stream;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BBE7EDC2B0371670096A693 /* Completion */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BBE7EDD2B03718E0096A693 /* ChatFunctionCallProvider.swift */,\n\t\t\t\t7BBE7EDF2B0372550096A693 /* ChatFunctionCallDemoView.swift */,\n\t\t\t);\n\t\t\tpath = Completion;\n\t\t\tsourceTree = \"\";\n\t\t};\n\t\t7BE802572D2877D30080E06A /* PredictedOutputsDemo */ = {\n\t\t\tisa = PBXGroup;\n\t\t\tchildren = (\n\t\t\t\t7BE802582D2878170080E06A /* ChatPredictedOutputDemoView.swift */,\n\t\t\t);\n\t\t\tpath = PredictedOutputsDemo;\n\t\t\tsourceTree = \"\";\n\t\t};\n/* End PBXGroup section */\n\n/* Begin PBXNativeTarget section */\n\t\t7BA788C82AE23A48008825D5 /* SwiftOpenAIExample */ = {\n\t\t\tisa = PBXNativeTarget;\n\t\t\tbuildConfigurationList = 7BA788EE2AE23A49008825D5 /* Build configuration list for PBXNativeTarget \"SwiftOpenAIExample\" */;\n\t\t\tbuildPhases = (\n\t\t\t\t7BA788C52AE23A48008825D5 /* Sources */,\n\t\t\t\t7BA788C62AE23A48008825D5 /* Frameworks */,\n\t\t\t\t7BA788C72AE23A48008825D5 /* Resources */,\n\t\t\t);\n\t\t\tbuildRules = (\n\t\t\t);\n\t\t\tdependencies = (\n\t\t\t);\n\t\t\tname = SwiftOpenAIExample;\n\t\t\tpackageProductDependencies = (\n\t\t\t\t0DEE5DC02BB40643004894AD /* SwiftOpenAI */,\n\t\t\t);\n\t\t\tproductName = SwiftOpenAIExample;\n\t\t\tproductReference = 7BA788C92AE23A48008825D5 /* SwiftOpenAIExample.app */;\n\t\t\tproductType = \"com.apple.product-type.application\";\n\t\t};\n\t\t7BA788D92AE23A49008825D5 /* SwiftOpenAIExampleTests */ = {\n\t\t\tisa = PBXNativeTarget;\n\t\t\tbuildConfigurationList = 7BA788F12AE23A49008825D5 /* Build configuration list for PBXNativeTarget \"SwiftOpenAIExampleTests\" */;\n\t\t\tbuildPhases = (\n\t\t\t\t7BA788D62AE23A49008825D5 /* Sources */,\n\t\t\t\t7BA788D72AE23A49008825D5 /* Frameworks */,\n\t\t\t\t7BA788D82AE23A49008825D5 /* Resources */,\n\t\t\t);\n\t\t\tbuildRules = (\n\t\t\t);\n\t\t\tdependencies = (\n\t\t\t\t7BA788DC2AE23A49008825D5 /* PBXTargetDependency */,\n\t\t\t);\n\t\t\tname = SwiftOpenAIExampleTests;\n\t\t\tproductName = SwiftOpenAIExampleTests;\n\t\t\tproductReference = 7BA788DA2AE23A49008825D5 /* SwiftOpenAIExampleTests.xctest */;\n\t\t\tproductType = \"com.apple.product-type.bundle.unit-test\";\n\t\t};\n\t\t7BA788E32AE23A49008825D5 /* SwiftOpenAIExampleUITests */ = {\n\t\t\tisa = PBXNativeTarget;\n\t\t\tbuildConfigurationList = 7BA788F42AE23A49008825D5 /* Build configuration list for PBXNativeTarget \"SwiftOpenAIExampleUITests\" */;\n\t\t\tbuildPhases = (\n\t\t\t\t7BA788E02AE23A49008825D5 /* Sources */,\n\t\t\t\t7BA788E12AE23A49008825D5 /* Frameworks */,\n\t\t\t\t7BA788E22AE23A49008825D5 /* Resources */,\n\t\t\t);\n\t\t\tbuildRules = (\n\t\t\t);\n\t\t\tdependencies = (\n\t\t\t\t7BA788E62AE23A49008825D5 /* PBXTargetDependency */,\n\t\t\t);\n\t\t\tname = SwiftOpenAIExampleUITests;\n\t\t\tproductName = SwiftOpenAIExampleUITests;\n\t\t\tproductReference = 7BA788E42AE23A49008825D5 /* SwiftOpenAIExampleUITests.xctest */;\n\t\t\tproductType = \"com.apple.product-type.bundle.ui-testing\";\n\t\t};\n/* End PBXNativeTarget section */\n\n/* Begin PBXProject section */\n\t\t7BA788C12AE23A48008825D5 /* Project object */ = {\n\t\t\tisa = PBXProject;\n\t\t\tattributes = {\n\t\t\t\tBuildIndependentTargetsInParallel = 1;\n\t\t\t\tLastSwiftUpdateCheck = 1500;\n\t\t\t\tLastUpgradeCheck = 1500;\n\t\t\t\tTargetAttributes = {\n\t\t\t\t\t7BA788C82AE23A48008825D5 = {\n\t\t\t\t\t\tCreatedOnToolsVersion = 15.0;\n\t\t\t\t\t};\n\t\t\t\t\t7BA788D92AE23A49008825D5 = {\n\t\t\t\t\t\tCreatedOnToolsVersion = 15.0;\n\t\t\t\t\t\tTestTargetID = 7BA788C82AE23A48008825D5;\n\t\t\t\t\t};\n\t\t\t\t\t7BA788E32AE23A49008825D5 = {\n\t\t\t\t\t\tCreatedOnToolsVersion = 15.0;\n\t\t\t\t\t\tTestTargetID = 7BA788C82AE23A48008825D5;\n\t\t\t\t\t};\n\t\t\t\t};\n\t\t\t};\n\t\t\tbuildConfigurationList = 7BA788C42AE23A48008825D5 /* Build configuration list for PBXProject \"SwiftOpenAIExample\" */;\n\t\t\tcompatibilityVersion = \"Xcode 14.0\";\n\t\t\tdevelopmentRegion = en;\n\t\t\thasScannedForEncodings = 0;\n\t\t\tknownRegions = (\n\t\t\t\ten,\n\t\t\t\tBase,\n\t\t\t);\n\t\t\tmainGroup = 7BA788C02AE23A48008825D5;\n\t\t\tpackageReferences = (\n\t\t\t\t0DEE5DBF2BB40643004894AD /* XCLocalSwiftPackageReference \"../..\" */,\n\t\t\t);\n\t\t\tproductRefGroup = 7BA788CA2AE23A48008825D5 /* Products */;\n\t\t\tprojectDirPath = \"\";\n\t\t\tprojectRoot = \"\";\n\t\t\ttargets = (\n\t\t\t\t7BA788C82AE23A48008825D5 /* SwiftOpenAIExample */,\n\t\t\t\t7BA788D92AE23A49008825D5 /* SwiftOpenAIExampleTests */,\n\t\t\t\t7BA788E32AE23A49008825D5 /* SwiftOpenAIExampleUITests */,\n\t\t\t);\n\t\t};\n/* End PBXProject section */\n\n/* Begin PBXResourcesBuildPhase section */\n\t\t7BA788C72AE23A48008825D5 /* Resources */ = {\n\t\t\tisa = PBXResourcesBuildPhase;\n\t\t\tbuildActionMask = 2147483647;\n\t\t\tfiles = (\n\t\t\t\t7B436B9E2AE256BC003CE281 /* german.m4a in Resources */,\n\t\t\t\t7BA788D52AE23A49008825D5 /* Preview Assets.xcassets in Resources */,\n\t\t\t\t7B436BB42AE79481003CE281 /* WorldCupData.jsonl in Resources */,\n\t\t\t\t7B436B9B2AE25094003CE281 /* narcos.m4a in Resources */,\n\t\t\t\t7BA788D12AE23A49008825D5 /* Assets.xcassets in Resources */,\n\t\t\t);\n\t\t\trunOnlyForDeploymentPostprocessing = 0;\n\t\t};\n\t\t7BA788D82AE23A49008825D5 /* Resources */ = {\n\t\t\tisa = PBXResourcesBuildPhase;\n\t\t\tbuildActionMask = 2147483647;\n\t\t\tfiles = (\n\t\t\t);\n\t\t\trunOnlyForDeploymentPostprocessing = 0;\n\t\t};\n\t\t7BA788E22AE23A49008825D5 /* Resources */ = {\n\t\t\tisa = PBXResourcesBuildPhase;\n\t\t\tbuildActionMask = 2147483647;\n\t\t\tfiles = (\n\t\t\t);\n\t\t\trunOnlyForDeploymentPostprocessing = 0;\n\t\t};\n/* End PBXResourcesBuildPhase section */\n\n/* Begin PBXSourcesBuildPhase section */\n\t\t7BA788C52AE23A48008825D5 /* Sources */ = {\n\t\t\tisa = PBXSourcesBuildPhase;\n\t\t\tbuildActionMask = 2147483647;\n\t\t\tfiles = (\n\t\t\t\t7BBE7EA92B02E8E50096A693 /* ChatMessageView.swift in Sources */,\n\t\t\t\t7BE802592D2878170080E06A /* ChatPredictedOutputDemoView.swift in Sources */,\n\t\t\t\t7B7239AE2AF9FF0000646679 /* ChatFunctionsCallStreamProvider.swift in Sources */,\n\t\t\t\t7B436BA12AE25958003CE281 /* ChatProvider.swift in Sources */,\n\t\t\t\t7B436BC32AE7B027003CE281 /* ModerationDemoView.swift in Sources */,\n\t\t\t\t7B7239AB2AF6294C00646679 /* URLImageView.swift in Sources */,\n\t\t\t\t7B7239B12AF9FF3C00646679 /* ChatFunctionsCalllStreamDemoView.swift in Sources */,\n\t\t\t\t7B50DD282C2A9A390070A64D /* LocalHostEntryView.swift in Sources */,\n\t\t\t\t7BBE7EAB2B02E8FC0096A693 /* ChatMessageDisplayModel.swift in Sources */,\n\t\t\t\t7B99C2E92C0718FF00E701B3 /* FileAttachmentView.swift in Sources */,\n\t\t\t\t7BBE7EA52B02E8A70096A693 /* Sizes.swift in Sources */,\n\t\t\t\t7B7239A22AF6260D00646679 /* ChatDisplayMessage.swift in Sources */,\n\t\t\t\t0DF957862BB543F100DD2013 /* AIProxyIntroView.swift in Sources */,\n\t\t\t\t7B1268052B08246400400694 /* AssistantConfigurationDemoView.swift in Sources */,\n\t\t\t\t7B436BB72AE7A2EA003CE281 /* ImagesProvider.swift in Sources */,\n\t\t\t\t7B436B962AE24A04003CE281 /* OptionsListView.swift in Sources */,\n\t\t\t\t7BBE7EDE2B03718E0096A693 /* ChatFunctionCallProvider.swift in Sources */,\n\t\t\t\t7B7239A62AF628F800646679 /* ChatDisplayMessageView.swift in Sources */,\n\t\t\t\t7B99C2ED2C071B1600E701B3 /* FilesPickerProvider.swift in Sources */,\n\t\t\t\t7B7239A02AF625F200646679 /* ChatFluidConversationProvider.swift in Sources */,\n\t\t\t\t7BA788CF2AE23A48008825D5 /* ApiKeyIntroView.swift in Sources */,\n\t\t\t\t7BA788CD2AE23A48008825D5 /* SwiftOpenAIExampleApp.swift in Sources */,\n\t\t\t\t7B3DDCC52BAAA722004B5C96 /* AssistantsListDemoView.swift in Sources */,\n\t\t\t\t7B3DDCC72BAAAD34004B5C96 /* AssistantThreadConfigurationProvider.swift in Sources */,\n\t\t\t\t7B3DDCC92BAAAF96004B5C96 /* AssistantStreamDemoScreen.swift in Sources */,\n\t\t\t\t7B029E3E2C69BEA70025681A /* ChatStructureOutputToolDemoView.swift in Sources */,\n\t\t\t\t7B413DFE2BB6846D009684CD /* ChatMessageLoadingView.swift in Sources */,\n\t\t\t\t7B436BB92AE7A2F2003CE281 /* ImagesDemoView.swift in Sources */,\n\t\t\t\t7B436BB22AE79370003CE281 /* FilesProvider.swift in Sources */,\n\t\t\t\t7BBE7E942AFCC9640096A693 /* ChatVisionProvider.swift in Sources */,\n\t\t\t\t0DF957842BB53BEF00DD2013 /* ServiceSelectionView.swift in Sources */,\n\t\t\t\t7B436BAD2AE788FB003CE281 /* FineTuningJobDemoView.swift in Sources */,\n\t\t\t\t7B436BB02AE79369003CE281 /* FilesDemoView.swift in Sources */,\n\t\t\t\t7BBE7E912AFCA52A0096A693 /* ChatVisionDemoView.swift in Sources */,\n\t\t\t\t7B99C2EB2C07191200E701B3 /* AttachmentView.swift in Sources */,\n\t\t\t\t7B50DD2B2C2A9D2F0070A64D /* LocalChatDemoView.swift in Sources */,\n\t\t\t\t7B029E3C2C69BE990025681A /* ChatStructuredOutputToolProvider.swift in Sources */,\n\t\t\t\t7B436BAB2AE788F1003CE281 /* FineTuningJobProvider.swift in Sources */,\n\t\t\t\t7B7239A42AF6289900646679 /* ChatStreamFluidConversationDemoView.swift in Sources */,\n\t\t\t\t7BA788FC2AE23B42008825D5 /* AudioDemoView.swift in Sources */,\n\t\t\t\t7B99C2E72C0718DE00E701B3 /* FilesPicker.swift in Sources */,\n\t\t\t\t7B1268072B08247C00400694 /* AssistantConfigurationProvider.swift in Sources */,\n\t\t\t\t7B029E392C68940D0025681A /* ChatStructuredOutputDemoView.swift in Sources */,\n\t\t\t\t7B436BBE2AE7ABDA003CE281 /* ModelsDemoView.swift in Sources */,\n\t\t\t\t7B029E372C6893FD0025681A /* ChatStructuredOutputProvider.swift in Sources */,\n\t\t\t\t7B436BA32AE25962003CE281 /* ChatDemoView.swift in Sources */,\n\t\t\t\t7B7239A82AF6292100646679 /* LoadingView.swift in Sources */,\n\t\t\t\t7B436B992AE25052003CE281 /* ContentLoader.swift in Sources */,\n\t\t\t\t7B436BC12AE7B01F003CE281 /* ModerationProvider.swift in Sources */,\n\t\t\t\t7B436BBC2AE7ABD3003CE281 /* ModelsProvider.swift in Sources */,\n\t\t\t\t7B2B6D562DF434670059B4BB /* ResponseStreamDemoView.swift in Sources */,\n\t\t\t\t7B2B6D582DF4347E0059B4BB /* ResponseStreamProvider.swift in Sources */,\n\t\t\t\t7B436BA62AE77F37003CE281 /* Embeddingsprovider.swift in Sources */,\n\t\t\t\t7BBE7EA72B02E8AC0096A693 /* ThemeColor.swift in Sources */,\n\t\t\t\t7BA788FE2AE23B95008825D5 /* AudioProvider.swift in Sources */,\n\t\t\t\t7B436BA82AE77F41003CE281 /* EmbeddingsDemoView.swift in Sources */,\n\t\t\t\t7BBE7EE02B0372550096A693 /* ChatFunctionCallDemoView.swift in Sources */,\n\t\t\t);\n\t\t\trunOnlyForDeploymentPostprocessing = 0;\n\t\t};\n\t\t7BA788D62AE23A49008825D5 /* Sources */ = {\n\t\t\tisa = PBXSourcesBuildPhase;\n\t\t\tbuildActionMask = 2147483647;\n\t\t\tfiles = (\n\t\t\t\t7BE9A5AF2B0B33E600CE8103 /* SwiftOpenAIExampleTests.swift in Sources */,\n\t\t\t);\n\t\t\trunOnlyForDeploymentPostprocessing = 0;\n\t\t};\n\t\t7BA788E02AE23A49008825D5 /* Sources */ = {\n\t\t\tisa = PBXSourcesBuildPhase;\n\t\t\tbuildActionMask = 2147483647;\n\t\t\tfiles = (\n\t\t\t\t7BA788E92AE23A49008825D5 /* SwiftOpenAIExampleUITests.swift in Sources */,\n\t\t\t\t7BA788EB2AE23A49008825D5 /* SwiftOpenAIExampleUITestsLaunchTests.swift in Sources */,\n\t\t\t);\n\t\t\trunOnlyForDeploymentPostprocessing = 0;\n\t\t};\n/* End PBXSourcesBuildPhase section */\n\n/* Begin PBXTargetDependency section */\n\t\t7BA788DC2AE23A49008825D5 /* PBXTargetDependency */ = {\n\t\t\tisa = PBXTargetDependency;\n\t\t\ttarget = 7BA788C82AE23A48008825D5 /* SwiftOpenAIExample */;\n\t\t\ttargetProxy = 7BA788DB2AE23A49008825D5 /* PBXContainerItemProxy */;\n\t\t};\n\t\t7BA788E62AE23A49008825D5 /* PBXTargetDependency */ = {\n\t\t\tisa = PBXTargetDependency;\n\t\t\ttarget = 7BA788C82AE23A48008825D5 /* SwiftOpenAIExample */;\n\t\t\ttargetProxy = 7BA788E52AE23A49008825D5 /* PBXContainerItemProxy */;\n\t\t};\n/* End PBXTargetDependency section */\n\n/* Begin XCBuildConfiguration section */\n\t\t7BA788EC2AE23A49008825D5 /* Debug */ = {\n\t\t\tisa = XCBuildConfiguration;\n\t\t\tbuildSettings = {\n\t\t\t\tALWAYS_SEARCH_USER_PATHS = NO;\n\t\t\t\tASSETCATALOG_COMPILER_GENERATE_SWIFT_ASSET_SYMBOL_EXTENSIONS = YES;\n\t\t\t\tCLANG_ANALYZER_NONNULL = YES;\n\t\t\t\tCLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;\n\t\t\t\tCLANG_CXX_LANGUAGE_STANDARD = \"gnu++20\";\n\t\t\t\tCLANG_ENABLE_MODULES = YES;\n\t\t\t\tCLANG_ENABLE_OBJC_ARC = YES;\n\t\t\t\tCLANG_ENABLE_OBJC_WEAK = YES;\n\t\t\t\tCLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;\n\t\t\t\tCLANG_WARN_BOOL_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_COMMA = YES;\n\t\t\t\tCLANG_WARN_CONSTANT_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;\n\t\t\t\tCLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;\n\t\t\t\tCLANG_WARN_DOCUMENTATION_COMMENTS = YES;\n\t\t\t\tCLANG_WARN_EMPTY_BODY = YES;\n\t\t\t\tCLANG_WARN_ENUM_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_INFINITE_RECURSION = YES;\n\t\t\t\tCLANG_WARN_INT_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;\n\t\t\t\tCLANG_WARN_OBJC_LITERAL_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;\n\t\t\t\tCLANG_WARN_QUOTED_INCLUDE_IN_FRAMEWORK_HEADER = YES;\n\t\t\t\tCLANG_WARN_RANGE_LOOP_ANALYSIS = YES;\n\t\t\t\tCLANG_WARN_STRICT_PROTOTYPES = YES;\n\t\t\t\tCLANG_WARN_SUSPICIOUS_MOVE = YES;\n\t\t\t\tCLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;\n\t\t\t\tCLANG_WARN_UNREACHABLE_CODE = YES;\n\t\t\t\tCLANG_WARN__DUPLICATE_METHOD_MATCH = YES;\n\t\t\t\tCOPY_PHASE_STRIP = NO;\n\t\t\t\tDEBUG_INFORMATION_FORMAT = dwarf;\n\t\t\t\tENABLE_STRICT_OBJC_MSGSEND = YES;\n\t\t\t\tENABLE_TESTABILITY = YES;\n\t\t\t\tENABLE_USER_SCRIPT_SANDBOXING = YES;\n\t\t\t\tGCC_C_LANGUAGE_STANDARD = gnu17;\n\t\t\t\tGCC_DYNAMIC_NO_PIC = NO;\n\t\t\t\tGCC_NO_COMMON_BLOCKS = YES;\n\t\t\t\tGCC_OPTIMIZATION_LEVEL = 0;\n\t\t\t\tGCC_PREPROCESSOR_DEFINITIONS = (\n\t\t\t\t\t\"DEBUG=1\",\n\t\t\t\t\t\"$(inherited)\",\n\t\t\t\t);\n\t\t\t\tGCC_WARN_64_TO_32_BIT_CONVERSION = YES;\n\t\t\t\tGCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;\n\t\t\t\tGCC_WARN_UNDECLARED_SELECTOR = YES;\n\t\t\t\tGCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;\n\t\t\t\tGCC_WARN_UNUSED_FUNCTION = YES;\n\t\t\t\tGCC_WARN_UNUSED_VARIABLE = YES;\n\t\t\t\tLOCALIZATION_PREFERS_STRING_CATALOGS = YES;\n\t\t\t\tMTL_ENABLE_DEBUG_INFO = INCLUDE_SOURCE;\n\t\t\t\tMTL_FAST_MATH = YES;\n\t\t\t\tONLY_ACTIVE_ARCH = YES;\n\t\t\t\tSWIFT_ACTIVE_COMPILATION_CONDITIONS = \"DEBUG $(inherited)\";\n\t\t\t\tSWIFT_OPTIMIZATION_LEVEL = \"-Onone\";\n\t\t\t};\n\t\t\tname = Debug;\n\t\t};\n\t\t7BA788ED2AE23A49008825D5 /* Release */ = {\n\t\t\tisa = XCBuildConfiguration;\n\t\t\tbuildSettings = {\n\t\t\t\tALWAYS_SEARCH_USER_PATHS = NO;\n\t\t\t\tASSETCATALOG_COMPILER_GENERATE_SWIFT_ASSET_SYMBOL_EXTENSIONS = YES;\n\t\t\t\tCLANG_ANALYZER_NONNULL = YES;\n\t\t\t\tCLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;\n\t\t\t\tCLANG_CXX_LANGUAGE_STANDARD = \"gnu++20\";\n\t\t\t\tCLANG_ENABLE_MODULES = YES;\n\t\t\t\tCLANG_ENABLE_OBJC_ARC = YES;\n\t\t\t\tCLANG_ENABLE_OBJC_WEAK = YES;\n\t\t\t\tCLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;\n\t\t\t\tCLANG_WARN_BOOL_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_COMMA = YES;\n\t\t\t\tCLANG_WARN_CONSTANT_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;\n\t\t\t\tCLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;\n\t\t\t\tCLANG_WARN_DOCUMENTATION_COMMENTS = YES;\n\t\t\t\tCLANG_WARN_EMPTY_BODY = YES;\n\t\t\t\tCLANG_WARN_ENUM_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_INFINITE_RECURSION = YES;\n\t\t\t\tCLANG_WARN_INT_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;\n\t\t\t\tCLANG_WARN_OBJC_LITERAL_CONVERSION = YES;\n\t\t\t\tCLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;\n\t\t\t\tCLANG_WARN_QUOTED_INCLUDE_IN_FRAMEWORK_HEADER = YES;\n\t\t\t\tCLANG_WARN_RANGE_LOOP_ANALYSIS = YES;\n\t\t\t\tCLANG_WARN_STRICT_PROTOTYPES = YES;\n\t\t\t\tCLANG_WARN_SUSPICIOUS_MOVE = YES;\n\t\t\t\tCLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;\n\t\t\t\tCLANG_WARN_UNREACHABLE_CODE = YES;\n\t\t\t\tCLANG_WARN__DUPLICATE_METHOD_MATCH = YES;\n\t\t\t\tCOPY_PHASE_STRIP = NO;\n\t\t\t\tDEBUG_INFORMATION_FORMAT = \"dwarf-with-dsym\";\n\t\t\t\tENABLE_NS_ASSERTIONS = NO;\n\t\t\t\tENABLE_STRICT_OBJC_MSGSEND = YES;\n\t\t\t\tENABLE_USER_SCRIPT_SANDBOXING = YES;\n\t\t\t\tGCC_C_LANGUAGE_STANDARD = gnu17;\n\t\t\t\tGCC_NO_COMMON_BLOCKS = YES;\n\t\t\t\tGCC_WARN_64_TO_32_BIT_CONVERSION = YES;\n\t\t\t\tGCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;\n\t\t\t\tGCC_WARN_UNDECLARED_SELECTOR = YES;\n\t\t\t\tGCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;\n\t\t\t\tGCC_WARN_UNUSED_FUNCTION = YES;\n\t\t\t\tGCC_WARN_UNUSED_VARIABLE = YES;\n\t\t\t\tLOCALIZATION_PREFERS_STRING_CATALOGS = YES;\n\t\t\t\tMTL_ENABLE_DEBUG_INFO = NO;\n\t\t\t\tMTL_FAST_MATH = YES;\n\t\t\t\tSWIFT_COMPILATION_MODE = wholemodule;\n\t\t\t};\n\t\t\tname = Release;\n\t\t};\n\t\t7BA788EF2AE23A49008825D5 /* Debug */ = {\n\t\t\tisa = XCBuildConfiguration;\n\t\t\tbuildSettings = {\n\t\t\t\tASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;\n\t\t\t\tASSETCATALOG_COMPILER_GLOBAL_ACCENT_COLOR_NAME = AccentColor;\n\t\t\t\tCODE_SIGN_ENTITLEMENTS = SwiftOpenAIExample/SwiftOpenAIExample.entitlements;\n\t\t\t\tCODE_SIGN_STYLE = Automatic;\n\t\t\t\tCURRENT_PROJECT_VERSION = 1;\n\t\t\t\tDEVELOPMENT_ASSET_PATHS = \"\\\"SwiftOpenAIExample/Preview Content\\\"\";\n\t\t\t\tDEVELOPMENT_TEAM = CQ45U4X9K3;\n\t\t\t\tENABLE_HARDENED_RUNTIME = YES;\n\t\t\t\tENABLE_PREVIEWS = YES;\n\t\t\t\tGENERATE_INFOPLIST_FILE = YES;\n\t\t\t\tINFOPLIST_KEY_NSMicrophoneUsageDescription = \"Microphone access is needed for voice chat\";\n\t\t\t\t\"INFOPLIST_KEY_UIApplicationSceneManifest_Generation[sdk=iphoneos*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UIApplicationSceneManifest_Generation[sdk=iphonesimulator*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UIApplicationSupportsIndirectInputEvents[sdk=iphoneos*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UIApplicationSupportsIndirectInputEvents[sdk=iphonesimulator*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UILaunchScreen_Generation[sdk=iphoneos*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UILaunchScreen_Generation[sdk=iphonesimulator*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UIStatusBarStyle[sdk=iphoneos*]\" = UIStatusBarStyleDefault;\n\t\t\t\t\"INFOPLIST_KEY_UIStatusBarStyle[sdk=iphonesimulator*]\" = UIStatusBarStyleDefault;\n\t\t\t\tINFOPLIST_KEY_UISupportedInterfaceOrientations_iPad = \"UIInterfaceOrientationPortrait UIInterfaceOrientationPortraitUpsideDown UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight\";\n\t\t\t\tINFOPLIST_KEY_UISupportedInterfaceOrientations_iPhone = \"UIInterfaceOrientationPortrait UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight\";\n\t\t\t\tIPHONEOS_DEPLOYMENT_TARGET = 17.0;\n\t\t\t\tLD_RUNPATH_SEARCH_PATHS = \"@executable_path/Frameworks\";\n\t\t\t\t\"LD_RUNPATH_SEARCH_PATHS[sdk=macosx*]\" = \"@executable_path/../Frameworks\";\n\t\t\t\tMACOSX_DEPLOYMENT_TARGET = 14.0;\n\t\t\t\tMARKETING_VERSION = 1.0;\n\t\t\t\tPRODUCT_BUNDLE_IDENTIFIER = jamesRochabrun.SwiftOpenAIExample;\n\t\t\t\tPRODUCT_NAME = \"$(TARGET_NAME)\";\n\t\t\t\tSDKROOT = auto;\n\t\t\t\tSUPPORTED_PLATFORMS = \"iphoneos iphonesimulator macosx\";\n\t\t\t\tSWIFT_EMIT_LOC_STRINGS = YES;\n\t\t\t\tSWIFT_VERSION = 5.0;\n\t\t\t\tTARGETED_DEVICE_FAMILY = \"1,2\";\n\t\t\t};\n\t\t\tname = Debug;\n\t\t};\n\t\t7BA788F02AE23A49008825D5 /* Release */ = {\n\t\t\tisa = XCBuildConfiguration;\n\t\t\tbuildSettings = {\n\t\t\t\tASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;\n\t\t\t\tASSETCATALOG_COMPILER_GLOBAL_ACCENT_COLOR_NAME = AccentColor;\n\t\t\t\tCODE_SIGN_ENTITLEMENTS = SwiftOpenAIExample/SwiftOpenAIExample.entitlements;\n\t\t\t\tCODE_SIGN_STYLE = Automatic;\n\t\t\t\tCURRENT_PROJECT_VERSION = 1;\n\t\t\t\tDEVELOPMENT_ASSET_PATHS = \"\\\"SwiftOpenAIExample/Preview Content\\\"\";\n\t\t\t\tDEVELOPMENT_TEAM = CQ45U4X9K3;\n\t\t\t\tENABLE_HARDENED_RUNTIME = YES;\n\t\t\t\tENABLE_PREVIEWS = YES;\n\t\t\t\tGENERATE_INFOPLIST_FILE = YES;\n\t\t\t\tINFOPLIST_KEY_NSMicrophoneUsageDescription = \"Microphone access is needed for voice chat\";\n\t\t\t\t\"INFOPLIST_KEY_UIApplicationSceneManifest_Generation[sdk=iphoneos*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UIApplicationSceneManifest_Generation[sdk=iphonesimulator*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UIApplicationSupportsIndirectInputEvents[sdk=iphoneos*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UIApplicationSupportsIndirectInputEvents[sdk=iphonesimulator*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UILaunchScreen_Generation[sdk=iphoneos*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UILaunchScreen_Generation[sdk=iphonesimulator*]\" = YES;\n\t\t\t\t\"INFOPLIST_KEY_UIStatusBarStyle[sdk=iphoneos*]\" = UIStatusBarStyleDefault;\n\t\t\t\t\"INFOPLIST_KEY_UIStatusBarStyle[sdk=iphonesimulator*]\" = UIStatusBarStyleDefault;\n\t\t\t\tINFOPLIST_KEY_UISupportedInterfaceOrientations_iPad = \"UIInterfaceOrientationPortrait UIInterfaceOrientationPortraitUpsideDown UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight\";\n\t\t\t\tINFOPLIST_KEY_UISupportedInterfaceOrientations_iPhone = \"UIInterfaceOrientationPortrait UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight\";\n\t\t\t\tIPHONEOS_DEPLOYMENT_TARGET = 17.0;\n\t\t\t\tLD_RUNPATH_SEARCH_PATHS = \"@executable_path/Frameworks\";\n\t\t\t\t\"LD_RUNPATH_SEARCH_PATHS[sdk=macosx*]\" = \"@executable_path/../Frameworks\";\n\t\t\t\tMACOSX_DEPLOYMENT_TARGET = 14.0;\n\t\t\t\tMARKETING_VERSION = 1.0;\n\t\t\t\tPRODUCT_BUNDLE_IDENTIFIER = jamesRochabrun.SwiftOpenAIExample;\n\t\t\t\tPRODUCT_NAME = \"$(TARGET_NAME)\";\n\t\t\t\tSDKROOT = auto;\n\t\t\t\tSUPPORTED_PLATFORMS = \"iphoneos iphonesimulator macosx\";\n\t\t\t\tSWIFT_EMIT_LOC_STRINGS = YES;\n\t\t\t\tSWIFT_VERSION = 5.0;\n\t\t\t\tTARGETED_DEVICE_FAMILY = \"1,2\";\n\t\t\t};\n\t\t\tname = Release;\n\t\t};\n\t\t7BA788F22AE23A49008825D5 /* Debug */ = {\n\t\t\tisa = XCBuildConfiguration;\n\t\t\tbuildSettings = {\n\t\t\t\tALWAYS_EMBED_SWIFT_STANDARD_LIBRARIES = YES;\n\t\t\t\tBUNDLE_LOADER = \"$(TEST_HOST)\";\n\t\t\t\tCODE_SIGN_STYLE = Automatic;\n\t\t\t\tCURRENT_PROJECT_VERSION = 1;\n\t\t\t\tDEVELOPMENT_TEAM = CQ45U4X9K3;\n\t\t\t\tGENERATE_INFOPLIST_FILE = YES;\n\t\t\t\tIPHONEOS_DEPLOYMENT_TARGET = 17.0;\n\t\t\t\tMACOSX_DEPLOYMENT_TARGET = 14.0;\n\t\t\t\tMARKETING_VERSION = 1.0;\n\t\t\t\tPRODUCT_BUNDLE_IDENTIFIER = jamesRochabrun.SwiftOpenAIExampleTests;\n\t\t\t\tPRODUCT_NAME = \"$(TARGET_NAME)\";\n\t\t\t\tSDKROOT = auto;\n\t\t\t\tSUPPORTED_PLATFORMS = \"iphoneos iphonesimulator macosx\";\n\t\t\t\tSWIFT_EMIT_LOC_STRINGS = NO;\n\t\t\t\tSWIFT_VERSION = 5.0;\n\t\t\t\tTARGETED_DEVICE_FAMILY = \"1,2\";\n\t\t\t\tTEST_HOST = \"$(BUILT_PRODUCTS_DIR)/SwiftOpenAIExample.app/$(BUNDLE_EXECUTABLE_FOLDER_PATH)/SwiftOpenAIExample\";\n\t\t\t};\n\t\t\tname = Debug;\n\t\t};\n\t\t7BA788F32AE23A49008825D5 /* Release */ = {\n\t\t\tisa = XCBuildConfiguration;\n\t\t\tbuildSettings = {\n\t\t\t\tALWAYS_EMBED_SWIFT_STANDARD_LIBRARIES = YES;\n\t\t\t\tBUNDLE_LOADER = \"$(TEST_HOST)\";\n\t\t\t\tCODE_SIGN_STYLE = Automatic;\n\t\t\t\tCURRENT_PROJECT_VERSION = 1;\n\t\t\t\tDEVELOPMENT_TEAM = CQ45U4X9K3;\n\t\t\t\tGENERATE_INFOPLIST_FILE = YES;\n\t\t\t\tIPHONEOS_DEPLOYMENT_TARGET = 17.0;\n\t\t\t\tMACOSX_DEPLOYMENT_TARGET = 14.0;\n\t\t\t\tMARKETING_VERSION = 1.0;\n\t\t\t\tPRODUCT_BUNDLE_IDENTIFIER = jamesRochabrun.SwiftOpenAIExampleTests;\n\t\t\t\tPRODUCT_NAME = \"$(TARGET_NAME)\";\n\t\t\t\tSDKROOT = auto;\n\t\t\t\tSUPPORTED_PLATFORMS = \"iphoneos iphonesimulator macosx\";\n\t\t\t\tSWIFT_EMIT_LOC_STRINGS = NO;\n\t\t\t\tSWIFT_VERSION = 5.0;\n\t\t\t\tTARGETED_DEVICE_FAMILY = \"1,2\";\n\t\t\t\tTEST_HOST = \"$(BUILT_PRODUCTS_DIR)/SwiftOpenAIExample.app/$(BUNDLE_EXECUTABLE_FOLDER_PATH)/SwiftOpenAIExample\";\n\t\t\t};\n\t\t\tname = Release;\n\t\t};\n\t\t7BA788F52AE23A49008825D5 /* Debug */ = {\n\t\t\tisa = XCBuildConfiguration;\n\t\t\tbuildSettings = {\n\t\t\t\tALWAYS_EMBED_SWIFT_STANDARD_LIBRARIES = YES;\n\t\t\t\tCODE_SIGN_STYLE = Automatic;\n\t\t\t\tCURRENT_PROJECT_VERSION = 1;\n\t\t\t\tDEVELOPMENT_TEAM = CQ45U4X9K3;\n\t\t\t\tGENERATE_INFOPLIST_FILE = YES;\n\t\t\t\tIPHONEOS_DEPLOYMENT_TARGET = 17.0;\n\t\t\t\tMACOSX_DEPLOYMENT_TARGET = 14.0;\n\t\t\t\tMARKETING_VERSION = 1.0;\n\t\t\t\tPRODUCT_BUNDLE_IDENTIFIER = jamesRochabrun.SwiftOpenAIExampleUITests;\n\t\t\t\tPRODUCT_NAME = \"$(TARGET_NAME)\";\n\t\t\t\tSDKROOT = auto;\n\t\t\t\tSUPPORTED_PLATFORMS = \"iphoneos iphonesimulator macosx\";\n\t\t\t\tSWIFT_EMIT_LOC_STRINGS = NO;\n\t\t\t\tSWIFT_VERSION = 5.0;\n\t\t\t\tTARGETED_DEVICE_FAMILY = \"1,2\";\n\t\t\t\tTEST_TARGET_NAME = SwiftOpenAIExample;\n\t\t\t};\n\t\t\tname = Debug;\n\t\t};\n\t\t7BA788F62AE23A49008825D5 /* Release */ = {\n\t\t\tisa = XCBuildConfiguration;\n\t\t\tbuildSettings = {\n\t\t\t\tALWAYS_EMBED_SWIFT_STANDARD_LIBRARIES = YES;\n\t\t\t\tCODE_SIGN_STYLE = Automatic;\n\t\t\t\tCURRENT_PROJECT_VERSION = 1;\n\t\t\t\tDEVELOPMENT_TEAM = CQ45U4X9K3;\n\t\t\t\tGENERATE_INFOPLIST_FILE = YES;\n\t\t\t\tIPHONEOS_DEPLOYMENT_TARGET = 17.0;\n\t\t\t\tMACOSX_DEPLOYMENT_TARGET = 14.0;\n\t\t\t\tMARKETING_VERSION = 1.0;\n\t\t\t\tPRODUCT_BUNDLE_IDENTIFIER = jamesRochabrun.SwiftOpenAIExampleUITests;\n\t\t\t\tPRODUCT_NAME = \"$(TARGET_NAME)\";\n\t\t\t\tSDKROOT = auto;\n\t\t\t\tSUPPORTED_PLATFORMS = \"iphoneos iphonesimulator macosx\";\n\t\t\t\tSWIFT_EMIT_LOC_STRINGS = NO;\n\t\t\t\tSWIFT_VERSION = 5.0;\n\t\t\t\tTARGETED_DEVICE_FAMILY = \"1,2\";\n\t\t\t\tTEST_TARGET_NAME = SwiftOpenAIExample;\n\t\t\t};\n\t\t\tname = Release;\n\t\t};\n/* End XCBuildConfiguration section */\n\n/* Begin XCConfigurationList section */\n\t\t7BA788C42AE23A48008825D5 /* Build configuration list for PBXProject \"SwiftOpenAIExample\" */ = {\n\t\t\tisa = XCConfigurationList;\n\t\t\tbuildConfigurations = (\n\t\t\t\t7BA788EC2AE23A49008825D5 /* Debug */,\n\t\t\t\t7BA788ED2AE23A49008825D5 /* Release */,\n\t\t\t);\n\t\t\tdefaultConfigurationIsVisible = 0;\n\t\t\tdefaultConfigurationName = Release;\n\t\t};\n\t\t7BA788EE2AE23A49008825D5 /* Build configuration list for PBXNativeTarget \"SwiftOpenAIExample\" */ = {\n\t\t\tisa = XCConfigurationList;\n\t\t\tbuildConfigurations = (\n\t\t\t\t7BA788EF2AE23A49008825D5 /* Debug */,\n\t\t\t\t7BA788F02AE23A49008825D5 /* Release */,\n\t\t\t);\n\t\t\tdefaultConfigurationIsVisible = 0;\n\t\t\tdefaultConfigurationName = Release;\n\t\t};\n\t\t7BA788F12AE23A49008825D5 /* Build configuration list for PBXNativeTarget \"SwiftOpenAIExampleTests\" */ = {\n\t\t\tisa = XCConfigurationList;\n\t\t\tbuildConfigurations = (\n\t\t\t\t7BA788F22AE23A49008825D5 /* Debug */,\n\t\t\t\t7BA788F32AE23A49008825D5 /* Release */,\n\t\t\t);\n\t\t\tdefaultConfigurationIsVisible = 0;\n\t\t\tdefaultConfigurationName = Release;\n\t\t};\n\t\t7BA788F42AE23A49008825D5 /* Build configuration list for PBXNativeTarget \"SwiftOpenAIExampleUITests\" */ = {\n\t\t\tisa = XCConfigurationList;\n\t\t\tbuildConfigurations = (\n\t\t\t\t7BA788F52AE23A49008825D5 /* Debug */,\n\t\t\t\t7BA788F62AE23A49008825D5 /* Release */,\n\t\t\t);\n\t\t\tdefaultConfigurationIsVisible = 0;\n\t\t\tdefaultConfigurationName = Release;\n\t\t};\n/* End XCConfigurationList section */\n\n/* Begin XCLocalSwiftPackageReference section */\n\t\t0DEE5DBF2BB40643004894AD /* XCLocalSwiftPackageReference \"../..\" */ = {\n\t\t\tisa = XCLocalSwiftPackageReference;\n\t\t\trelativePath = ../..;\n\t\t};\n/* End XCLocalSwiftPackageReference section */\n\n/* Begin XCSwiftPackageProductDependency section */\n\t\t0DEE5DC02BB40643004894AD /* SwiftOpenAI */ = {\n\t\t\tisa = XCSwiftPackageProductDependency;\n\t\t\tproductName = SwiftOpenAI;\n\t\t};\n/* End XCSwiftPackageProductDependency section */\n\t};\n\trootObject = 7BA788C12AE23A48008825D5 /* Project object */;\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample.xcodeproj/project.xcworkspace/contents.xcworkspacedata",
"content": "\n\n \n \n\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExample.xcodeproj/xcshareddata/xcschemes/SwiftOpenAIExample.xcscheme",
"content": "\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExampleTests/SwiftOpenAIExampleTests.swift",
"content": "//\n// SwiftOpenAIExampleTests.swift\n// SwiftOpenAIExampleTests\n//\n// Created by James Rochabrun on 10/19/23.\n//\n\nimport XCTest\n\nfinal class SwiftOpenAIExampleTests: XCTestCase {\n override func setUpWithError() throws {\n // Put setup code here. This method is called before the invocation of each test method in the class.\n }\n\n override func tearDownWithError() throws {\n // Put teardown code here. This method is called after the invocation of each test method in the class.\n }\n\n func testExample() throws {\n // This is an example of a functional test case.\n // Use XCTAssert and related functions to verify your tests produce the correct results.\n // Any test you write for XCTest can be annotated as throws and async.\n // Mark your test throws to produce an unexpected failure when your test encounters an uncaught error.\n // Mark your test async to allow awaiting for asynchronous code to complete. Check the results with assertions afterwards.\n }\n\n func testPerformanceExample() throws {\n // This is an example of a performance test case.\n measure {\n // Put the code you want to measure the time of here.\n }\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExampleUITests/SwiftOpenAIExampleUITests.swift",
"content": "//\n// SwiftOpenAIExampleUITests.swift\n// SwiftOpenAIExampleUITests\n//\n// Created by James Rochabrun on 10/19/23.\n//\n\nimport XCTest\n\nfinal class SwiftOpenAIExampleUITests: XCTestCase {\n override func setUpWithError() throws {\n // Put setup code here. This method is called before the invocation of each test method in the class.\n\n // In UI tests it is usually best to stop immediately when a failure occurs.\n continueAfterFailure = false\n\n // In UI tests it’s important to set the initial state - such as interface orientation - required for your tests before they run. The setUp method is a good place to do this.\n }\n\n override func tearDownWithError() throws {\n // Put teardown code here. This method is called after the invocation of each test method in the class.\n }\n\n func testExample() throws {\n // UI tests must launch the application that they test.\n let app = XCUIApplication()\n app.launch()\n\n // Use XCTAssert and related functions to verify your tests produce the correct results.\n }\n\n func testLaunchPerformance() throws {\n if #available(macOS 10.15, iOS 13.0, tvOS 13.0, watchOS 7.0, *) {\n // This measures how long it takes to launch your application.\n measure(metrics: [XCTApplicationLaunchMetric()]) {\n XCUIApplication().launch()\n }\n }\n }\n}\n"
},
{
"path": "Examples/SwiftOpenAIExample/SwiftOpenAIExampleUITests/SwiftOpenAIExampleUITestsLaunchTests.swift",
"content": "//\n// SwiftOpenAIExampleUITestsLaunchTests.swift\n// SwiftOpenAIExampleUITests\n//\n// Created by James Rochabrun on 10/19/23.\n//\n\nimport XCTest\n\nfinal class SwiftOpenAIExampleUITestsLaunchTests: XCTestCase {\n override class var runsForEachTargetApplicationUIConfiguration: Bool {\n true\n }\n\n override func setUpWithError() throws {\n continueAfterFailure = false\n }\n\n func testLaunch() throws {\n let app = XCUIApplication()\n app.launch()\n\n // Insert steps here to perform after app launch but before taking a screenshot,\n // such as logging into a test account or navigating somewhere in the app\n\n let attachment = XCTAttachment(screenshot: app.screenshot())\n attachment.name = \"Launch Screen\"\n attachment.lifetime = .keepAlways\n add(attachment)\n }\n}\n"
},
{
"path": "LICENSE",
"content": "MIT License\n\nCopyright (c) 2023 James Rochabrun\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.\n"
},
{
"path": "Package.swift",
"content": "// swift-tools-version: 5.9\n// The swift-tools-version declares the minimum version of Swift required to build this package.\n\nimport PackageDescription\n\nlet package = Package(\n name: \"SwiftOpenAI\",\n platforms: [\n .iOS(.v15),\n .macOS(.v12),\n .watchOS(.v9),\n ],\n products: [\n // Products define the executables and libraries a package produces, making them visible to other packages.\n .library(\n name: \"SwiftOpenAI\",\n targets: [\"SwiftOpenAI\"]),\n ],\n dependencies: [\n .package(url: \"https://github.com/swift-server/async-http-client.git\", from: \"1.25.2\"),\n ],\n targets: [\n // Targets are the basic building blocks of a package, defining a module or a test suite.\n // Targets can depend on other targets in this package and products from dependencies.\n .target(\n name: \"SwiftOpenAI\",\n dependencies: [\n .product(name: \"AsyncHTTPClient\", package: \"async-http-client\", condition: .when(platforms: [.linux])),\n ]),\n .testTarget(\n name: \"SwiftOpenAITests\",\n dependencies: [\"SwiftOpenAI\"]),\n ])\n"
},
{
"path": "README.md",
"content": "# SwiftOpenAI\n![\"repoOpenAI\"](\"https://github.com/jamesrochabrun/SwiftOpenAI/assets/5378604/51bc5736-a32f-4a9f-922e-209d950e28f7\")
\n\n\n\n\n\n[](https://lbesson.mit-license.org/)\n[](https://github.com/apple/swift)\n[](https://developer.apple.com/documentation/swiftui)\n[](https://developer.apple.com/xcode/)\n[](https://github.com/apple/swift-package-manager)\n[](https://buymeacoffee.com/jamesrochabrun)\n\nAn open-source Swift package designed for effortless interaction with OpenAI's public API. \n\n🚀 Now also available as [CLI](https://github.com/jamesrochabrun/SwiftOpenAICLI) and also as [MCP](https://github.com/jamesrochabrun/SwiftOpenAIMCP)\n\n## Table of Contents\n- [Description](#description)\n- [Getting an API Key](#getting-an-api-key)\n- [Installation](#installation)\n- [Compatibility](#compatibility)\n- [Usage](#usage)\n- [Collaboration](#collaboration)\n\n## Description\n\n`SwiftOpenAI` is an open-source Swift package that streamlines interactions with **all** OpenAI's API endpoints, now with added support for Azure, AIProxy, Assistant stream APIs, and the new **Realtime API** for low-latency bidirectional voice conversations.\n\n### OpenAI ENDPOINTS\n\n- [Audio](#audio)\n - [Transcriptions](#audio-transcriptions)\n - [Translations](#audio-translations)\n - [Speech](#audio-Speech)\n - [Realtime](#audio-realtime)\n- [Chat](#chat)\n - [Function Calling](#function-calling)\n - [Structured Outputs](#structured-outputs)\n - [Vision](#vision)\n- [Response](#response)\n - [Streaming Responses](#streaming-responses)\n- [Embeddings](#embeddings)\n- [Fine-tuning](#fine-tuning)\n- [Batch](#batch)\n- [Files](#files)\n- [Images](#images)\n- [Models](#models)\n- [Moderations](#moderations)\n\n### **BETA**\n- [Assistants](#assistants)\n - [Assistants File Object](#assistants-file-object)\n- [Threads](#threads)\n- [Messages](#messages)\n - [Message File Object](#message-file-object)\n- [Runs](#runs)\n - [Run Step object](#run-step-object)\n - [Run Step details](#run-step-details)\n- [Assistants Streaming](#assistants-streaming)\n - [Message Delta Object](#message-delta-object)\n - [Run Step Delta Object](#run-step-delta-object)\n- [Vector Stores](#vector-stores)\n - [Vector store File](#vector-store-file)\n - [Vector store File Batch](#vector-store-file-batch)\n\n## Getting an API Key\n\n⚠️ **Important**\n\nTo interact with OpenAI services, you'll need an API key. Follow these steps to obtain one:\n\n1. Visit [OpenAI](https://www.openai.com/).\n2. Sign up for an [account](https://platform.openai.com/signup) or [log in](https://platform.openai.com/login) if you already have one.\n3. Navigate to the [API key page](https://platform.openai.com/account/api-keys) and follow the instructions to generate a new API key.\n\nFor more information, consult OpenAI's [official documentation](https://platform.openai.com/docs/).\n\n⚠️ Please take precautions to keep your API key secure per [OpenAI's guidance](https://platform.openai.com/docs/api-reference/authentication):\n\n> Remember that your API key is a secret! Do not share it with others or expose\n> it in any client-side code (browsers, apps). Production requests must be\n> routed through your backend server where your API key can be securely\n> loaded from an environment variable or key management service.\n\nSwiftOpenAI has built-in support for AIProxy, which is a backend for AI apps, to satisfy this requirement.\nTo configure AIProxy, see the instructions [here](#aiproxy).\n\n\n## Installation\n\n### Swift Package Manager\n\n1. Open your Swift project in Xcode.\n2. Go to `File` -> `Add Package Dependency`.\n3. In the search bar, enter [this URL](https://github.com/jamesrochabrun/SwiftOpenAI).\n4. Choose the version you'd like to install (see the note below).\n5. Click `Add Package`.\n\nNote: Xcode has a quirk where it defaults an SPM package's upper limit to 2.0.0. This package is beyond that\nlimit, so you should not accept the defaults that Xcode proposes. Instead, enter the lower bound of the\n[release version](https://github.com/jamesrochabrun/SwiftOpenAI/releases) that you'd like to support, and then\ntab out of the input box for Xcode to adjust the upper bound. Alternatively, you may select `branch` -> `main`\nto stay on the bleeding edge.\n\n## Compatibility\n\n### Platform Support\n\nSwiftOpenAI supports both Apple platforms and Linux.\n- **Apple platforms** include iOS 15+, macOS 13+, and watchOS 9+.\n- **Linux**: SwiftOpenAI on Linux uses AsyncHTTPClient to work around URLSession bugs in Apple's Foundation framework, and can be used with the [Vapor](https://vapor.codes/) server framework.\n\n### OpenAI-Compatible Providers\n\nSwiftOpenAI supports various providers that are OpenAI-compatible, including but not limited to:\n\n- [Azure OpenAI](#azure-openai)\n- [Anthropic](#anthropic)\n- [Gemini](#gemini)\n- [Ollama](#ollama)\n- [Groq](#groq)\n- [xAI](#xai)\n- [OpenRouter](#openRouter)\n- [DeepSeek](#deepseek)\n- [AIProxy](#aiproxy)\n\nCheck OpenAIServiceFactory for convenience initializers that you can use to provide custom URLs.\n\n## Usage\n\nTo use SwiftOpenAI in your project, first import the package:\n\n```swift\nimport SwiftOpenAI\n```\n\nThen, initialize the service using your OpenAI API key:\n\n```swift\nlet apiKey = \"your_openai_api_key_here\"\nlet service = OpenAIServiceFactory.service(apiKey: apiKey)\n```\n\nYou can optionally specify an organization name if needed.\n\n```swift\nlet apiKey = \"your_openai_api_key_here\"\nlet oganizationID = \"your_organixation_id\"\nlet service = OpenAIServiceFactory.service(apiKey: apiKey, organizationID: oganizationID)\n```\n\nhttps://developer.apple.com/documentation/foundation/nsurlsessionconfiguration/1408259-timeoutintervalforrequest\n\nFor reasoning models, ensure that you extend the timeoutIntervalForRequest in the URL session configuration to a higher value. The default is 60 seconds, which may be insufficient, as requests to reasoning models can take longer to process and respond.\n\nTo configure it:\n\n```swift\nlet apiKey = \"your_openai_api_key_here\"\nlet organizationID = \"your_organization_id\"\nlet session = URLSession.shared\nsession.configuration.timeoutIntervalForRequest = 360 // e.g., 360 seconds or more.\nlet httpClient = URLSessionHTTPClientAdapter(urlSession: session)\nlet service = OpenAIServiceFactory.service(apiKey: apiKey, organizationID: organizationID, httpClient: httpClient)\n```\n\nThat's all you need to begin accessing the full range of OpenAI endpoints.\n\n### How to get the status code of network errors\n\nYou may want to build UI around the type of error that the API returns.\nFor example, a `429` means that your requests are being rate limited.\nThe `APIError` type has a case `responseUnsuccessful` with two associated values: a `description` and `statusCode`.\nHere is a usage example using the chat completion API:\n\n```swift\nlet service = OpenAIServiceFactory.service(apiKey: apiKey)\nlet parameters = ChatCompletionParameters(messages: [.init(role: .user, content: .text(\"hello world\"))],\n model: .gpt4o)\ndo {\n let choices = try await service.startChat(parameters: parameters).choices\n // Work with choices\n} catch APIError.responseUnsuccessful(let description, let statusCode) {\n print(\"Network error with status code: \\(statusCode) and description: \\(description)\")\n} catch {\n print(error.localizedDescription)\n}\n```\n\n\n### Audio\n\n### Audio Transcriptions\nParameters\n```swift\npublic struct AudioTranscriptionParameters: Encodable {\n \n /// The name of the file asset is not documented in OpenAI's official documentation; however, it is essential for constructing the multipart request.\n let fileName: String\n /// The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.\n let file: Data\n /// ID of the model to use. Only whisper-1 is currently available.\n let model: String\n /// The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will improve accuracy and latency.\n let language: String?\n /// An optional text to guide the model's style or continue a previous audio segment. The [prompt](https://platform.openai.com/docs/guides/speech-to-text/prompting) should match the audio language.\n let prompt: String?\n /// The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt. Defaults to json\n let responseFormat: String?\n /// The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. Defaults to 0\n let temperature: Double?\n \n public enum Model {\n case whisperOne \n case custom(model: String)\n }\n \n public init(\n fileName: String,\n file: Data,\n model: Model = .whisperOne,\n prompt: String? = nil,\n responseFormat: String? = nil,\n temperature: Double? = nil,\n language: String? = nil)\n {\n self.fileName = fileName\n self.file = file\n self.model = model.rawValue\n self.prompt = prompt\n self.responseFormat = responseFormat\n self.temperature = temperature\n self.language = language\n }\n}\n```\n\nResponse\n```swift\npublic struct AudioObject: Decodable {\n \n /// The transcribed text if the request uses the `transcriptions` API, or the translated text if the request uses the `translations` endpoint.\n public let text: String\n}\n```\n\nUsage\n```swift\nlet fileName = \"narcos.m4a\"\nlet data = Data(contentsOfURL:_) // Data retrieved from the file named \"narcos.m4a\".\nlet parameters = AudioTranscriptionParameters(fileName: fileName, file: data) // **Important**: in the file name always provide the file extension.\nlet audioObject = try await service.createTranscription(parameters: parameters)\n```\n### Audio Translations\nParameters\n```swift\npublic struct AudioTranslationParameters: Encodable {\n \n /// The name of the file asset is not documented in OpenAI's official documentation; however, it is essential for constructing the multipart request.\n let fileName: String\n /// The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.\n let file: Data\n /// ID of the model to use. Only whisper-1 is currently available.\n let model: String\n /// An optional text to guide the model's style or continue a previous audio segment. The [prompt](https://platform.openai.com/docs/guides/speech-to-text/prompting) should match the audio language.\n let prompt: String?\n /// The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt. Defaults to json\n let responseFormat: String?\n /// The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. Defaults to 0\n let temperature: Double?\n \n public enum Model {\n case whisperOne \n case custom(model: String)\n }\n \n public init(\n fileName: String,\n file: Data,\n model: Model = .whisperOne,\n prompt: String? = nil,\n responseFormat: String? = nil,\n temperature: Double? = nil)\n {\n self.fileName = fileName\n self.file = file\n self.model = model.rawValue\n self.prompt = prompt\n self.responseFormat = responseFormat\n self.temperature = temperature\n }\n}\n```\n\nResponse\n```swift\npublic struct AudioObject: Decodable {\n \n /// The transcribed text if the request uses the `transcriptions` API, or the translated text if the request uses the `translations` endpoint.\n public let text: String\n}\n```\n\nUsage\n```swift\nlet fileName = \"german.m4a\"\nlet data = Data(contentsOfURL:_) // Data retrieved from the file named \"german.m4a\".\nlet parameters = AudioTranslationParameters(fileName: fileName, file: data) // **Important**: in the file name always provide the file extension.\nlet audioObject = try await service.createTranslation(parameters: parameters)\n```\n\n### Audio Speech\nParameters\n```swift\n/// [Generates audio from the input text.](https://platform.openai.com/docs/api-reference/audio/createSpeech)\npublic struct AudioSpeechParameters: Encodable {\n\n /// One of the available [TTS models](https://platform.openai.com/docs/models/tts): tts-1 or tts-1-hd\n let model: String\n /// The text to generate audio for. The maximum length is 4096 characters.\n let input: String\n /// The voice to use when generating the audio. Supported voices are alloy, echo, fable, onyx, nova, and shimmer. Previews of the voices are available in the [Text to speech guide.](https://platform.openai.com/docs/guides/text-to-speech/voice-options)\n let voice: String\n /// Defaults to mp3, The format to audio in. Supported formats are mp3, opus, aac, and flac.\n let responseFormat: String?\n /// Defaults to 1, The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.\n let speed: Double?\n\n public enum TTSModel: String {\n case tts1 = \"tts-1\"\n case tts1HD = \"tts-1-hd\"\n }\n\n public enum Voice: String {\n case alloy\n case echo\n case fable\n case onyx\n case nova\n case shimmer\n }\n\n public enum ResponseFormat: String {\n case mp3\n case opus\n case aac\n case flac\n }\n \n public init(\n model: TTSModel,\n input: String,\n voice: Voice,\n responseFormat: ResponseFormat? = nil,\n speed: Double? = nil)\n {\n self.model = model.rawValue\n self.input = input\n self.voice = voice.rawValue\n self.responseFormat = responseFormat?.rawValue\n self.speed = speed\n }\n}\n```\n\nResponse\n```swift\n/// The [audio speech](https://platform.openai.com/docs/api-reference/audio/createSpeech) response.\npublic struct AudioSpeechObject: Decodable {\n\n /// The audio file content data.\n public let output: Data\n}\n```\n\nUsage\n```swift\nlet prompt = \"Hello, how are you today?\"\nlet parameters = AudioSpeechParameters(model: .tts1, input: prompt, voice: .shimmer)\nlet audioObjectData = try await service.createSpeech(parameters: parameters).output\nplayAudio(from: audioObjectData)\n\n// Play data\n private func playAudio(from data: Data) {\n do {\n // Initialize the audio player with the data\n audioPlayer = try AVAudioPlayer(data: data)\n audioPlayer?.prepareToPlay()\n audioPlayer?.play()\n } catch {\n // Handle errors\n print(\"Error playing audio: \\(error.localizedDescription)\")\n }\n }\n```\n\n### Audio Realtime\n\nThe [Realtime API](https://platform.openai.com/docs/api-reference/realtime) enables bidirectional voice conversations with OpenAI's models using WebSockets and low-latency audio streaming. The API supports both audio-to-audio and text-to-audio interactions with built-in voice activity detection, transcription, and function calling.\n\n**Platform Requirements:** iOS 15+, macOS 13+, watchOS 9+. Requires AVFoundation (not available on Linux).\n\n**Permissions Required:**\n- Add `NSMicrophoneUsageDescription` to your Info.plist\n- On macOS: Enable sandbox entitlements for microphone access and outgoing network connections\n\nParameters\n```swift\n/// Configuration for creating a realtime session\npublic struct OpenAIRealtimeSessionConfiguration: Encodable, Sendable {\n\n /// The input audio format. Options: .pcm16, .g711_ulaw, .g711_alaw. Default is .pcm16\n let inputAudioFormat: AudioFormat?\n /// Configuration for input audio transcription using Whisper\n let inputAudioTranscription: InputAudioTranscription?\n /// System instructions for the model. Recommended default provided\n let instructions: String?\n /// Maximum tokens for response output. Can be .value(Int) or .infinite\n let maxResponseOutputTokens: MaxResponseOutputTokens?\n /// Output modalities: [.audio, .text] or [.text] only. Default is [.audio, .text]\n let modalities: [Modality]?\n /// The output audio format. Options: .pcm16, .g711_ulaw, .g711_alaw. Default is .pcm16\n let outputAudioFormat: AudioFormat?\n /// Audio playback speed. Range: 0.25 to 4.0. Default is 1.0\n let speed: Double?\n /// Sampling temperature for model responses. Range: 0.6 to 1.2. Default is 0.8\n let temperature: Double?\n /// Array of tools/functions available for the model to call\n let tools: [Tool]?\n /// Tool selection mode: .none, .auto, .required, or .specific(functionName: String)\n let toolChoice: ToolChoice?\n /// Voice activity detection configuration. Options: .serverVAD or .semanticVAD\n let turnDetection: TurnDetection?\n /// The voice to use. Options: \"alloy\", \"ash\", \"ballad\", \"coral\", \"echo\", \"sage\", \"shimmer\", \"verse\"\n let voice: String?\n\n /// Available audio formats\n public enum AudioFormat: String, Encodable, Sendable {\n case pcm16\n case g711_ulaw = \"g711-ulaw\"\n case g711_alaw = \"g711-alaw\"\n }\n\n /// Output modalities\n public enum Modality: String, Encodable, Sendable {\n case audio\n case text\n }\n\n /// Turn detection configuration\n public struct TurnDetection: Encodable, Sendable {\n /// Server-based VAD with customizable timing\n public static func serverVAD(\n prefixPaddingMs: Int = 300,\n silenceDurationMs: Int = 500,\n threshold: Double = 0.5\n ) -> TurnDetection\n\n /// Semantic VAD with eagerness level\n public static func semanticVAD(eagerness: Eagerness = .medium) -> TurnDetection\n\n public enum Eagerness: String, Encodable, Sendable {\n case low, medium, high\n }\n }\n}\n```\n\nResponse\n```swift\n/// Messages received from the realtime API\npublic enum OpenAIRealtimeMessage: Sendable {\n case error(String?) // Error occurred\n case sessionCreated // Session successfully created\n case sessionUpdated // Configuration updated\n case responseCreated // Model started generating response\n case responseAudioDelta(String) // Audio chunk (base64 PCM16)\n case inputAudioBufferSpeechStarted // User started speaking (VAD detected)\n case responseFunctionCallArgumentsDone(name: String, arguments: String, callId: String)\n case responseTranscriptDelta(String) // Partial AI transcript\n case responseTranscriptDone(String) // Complete AI transcript\n case inputAudioBufferTranscript(String) // User audio transcript\n case inputAudioTranscriptionDelta(String) // Partial user transcription\n case inputAudioTranscriptionCompleted(String) // Complete user transcription\n}\n```\n\nSupporting Types\n```swift\n/// Manages microphone input and audio playback for realtime conversations.\n/// Audio played through AudioController does not interfere with mic input (the model won't hear itself).\n@RealtimeActor\npublic final class AudioController {\n\n /// Initialize with specified modes\n /// - Parameter modes: Array of .record (for microphone) and/or .playback (for audio output)\n public init(modes: [Mode]) async throws\n\n public enum Mode {\n case record // Enable microphone streaming\n case playback // Enable audio playback\n }\n\n /// Returns an AsyncStream of microphone audio buffers\n /// - Throws: OpenAIError if .record mode wasn't enabled during initialization\n public func micStream() throws -> AsyncStream\n\n /// Plays base64-encoded PCM16 audio from the model\n /// - Parameter base64String: Base64-encoded PCM16 audio data\n public func playPCM16Audio(base64String: String)\n\n /// Interrupts current audio playback (useful when user starts speaking)\n public func interruptPlayback()\n\n /// Stops all audio operations\n public func stop()\n}\n\n/// Utility for encoding audio buffers to base64\npublic enum AudioUtils {\n /// Converts AVAudioPCMBuffer to base64 string for transmission\n public static func base64EncodeAudioPCMBuffer(from buffer: AVAudioPCMBuffer) -> String?\n\n /// Checks if headphones are connected\n public static var headphonesConnected: Bool\n}\n```\n\nUsage\n```swift\n// 1. Create session configuration\nlet configuration = OpenAIRealtimeSessionConfiguration(\n voice: \"alloy\",\n instructions: \"You are a helpful AI assistant. Be concise and friendly.\",\n turnDetection: .serverVAD(\n prefixPaddingMs: 300,\n silenceDurationMs: 500,\n threshold: 0.5\n ),\n inputAudioTranscription: .init(model: \"whisper-1\")\n)\n\n// 2. Create realtime session\nlet session = try await service.realtimeSession(\n model: \"gpt-4o-mini-realtime-preview-2024-12-17\",\n configuration: configuration\n)\n\n// 3. Initialize audio controller for recording and playback\nlet audioController = try await AudioController(modes: [.record, .playback])\n\n// 4. Handle incoming messages from OpenAI\nTask {\n for await message in session.receiver {\n switch message {\n case .responseAudioDelta(let audio):\n // Play audio from the model\n audioController.playPCM16Audio(base64String: audio)\n\n case .inputAudioBufferSpeechStarted:\n // User started speaking - interrupt model's audio\n audioController.interruptPlayback()\n\n case .responseTranscriptDelta(let text):\n // Display partial model transcript\n print(\"Model (partial): \\(text)\")\n\n case .responseTranscriptDone(let text):\n // Display complete model transcript\n print(\"Model: \\(text)\")\n\n case .inputAudioTranscriptionCompleted(let text):\n // Display user's transcribed speech\n print(\"User: \\(text)\")\n\n case .responseFunctionCallArgumentsDone(let name, let args, let callId):\n // Handle function call from model\n print(\"Function call: \\(name) with args: \\(args)\")\n // Execute function and send result back\n\n case .error(let error):\n print(\"Error: \\(error ?? \"Unknown error\")\")\n\n default:\n break\n }\n }\n}\n\n// 5. Stream microphone audio to OpenAI\nTask {\n do {\n for try await buffer in audioController.micStream() {\n // Encode audio buffer to base64\n guard let base64Audio = AudioUtils.base64EncodeAudioPCMBuffer(from: buffer) else {\n continue\n }\n\n // Send audio to OpenAI\n try await session.sendMessage(\n OpenAIRealtimeInputAudioBufferAppend(audio: base64Audio)\n )\n }\n } catch {\n print(\"Microphone error: \\(error)\")\n }\n}\n\n// 6. Manually trigger a response (optional - usually VAD handles this)\ntry await session.sendMessage(\n OpenAIRealtimeResponseCreate()\n)\n\n// 7. Update session configuration mid-conversation (optional)\nlet newConfig = OpenAIRealtimeSessionConfiguration(\n voice: \"shimmer\",\n temperature: 0.9\n)\ntry await session.sendMessage(\n OpenAIRealtimeSessionUpdate(sessionConfig: newConfig)\n)\n\n// 8. Cleanup when done\naudioController.stop()\nsession.disconnect()\n```\n\nFunction Calling\n```swift\n// Define tools in configuration\nlet tools: [OpenAIRealtimeSessionConfiguration.Tool] = [\n .init(\n name: \"get_weather\",\n description: \"Get the current weather in a location\",\n parameters: [\n \"type\": \"object\",\n \"properties\": [\n \"location\": [\n \"type\": \"string\",\n \"description\": \"City name, e.g. San Francisco\"\n ]\n ],\n \"required\": [\"location\"]\n ]\n )\n]\n\nlet config = OpenAIRealtimeSessionConfiguration(\n voice: \"alloy\",\n tools: tools,\n toolChoice: .auto\n)\n\n// Handle function calls in message receiver\ncase .responseFunctionCallArgumentsDone(let name, let args, let callId):\n if name == \"get_weather\" {\n // Parse arguments and execute function\n let result = getWeather(arguments: args)\n\n // Send result back to model\n try await session.sendMessage(\n OpenAIRealtimeConversationItemCreate(\n item: .functionCallOutput(\n callId: callId,\n output: result\n )\n )\n )\n }\n```\n\nAdvanced Features\n- **Voice Activity Detection (VAD):** Choose between server-based VAD (with configurable timing) or semantic VAD (with eagerness levels)\n- **Transcription:** Enable Whisper transcription for both user input and model output\n- **Session Updates:** Change voice, instructions, or tools mid-conversation without reconnecting\n- **Response Triggers:** Manually trigger model responses or rely on automatic VAD\n- **Platform-Specific Behavior:** Automatically selects optimal audio API based on platform and headphone connection\n\nFor a complete implementation example, see `Examples/RealtimeExample/RealtimeExample.swift` in the repository.\n\n### Chat\nParameters\n```swift\npublic struct ChatCompletionParameters: Encodable {\n \n /// A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models)\n public var messages: [Message]\n /// ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models/how-we-use-your-data) table for details on which models work with the Chat API.\n /// Supports GPT-4, GPT-4o, GPT-5, and other models. For GPT-5 family: .gpt5, .gpt5Mini, .gpt5Nano\n public var model: String\n /// Whether or not to store the output of this chat completion request for use in our [model distillation](https://platform.openai.com/docs/guides/distillation) or [evals](https://platform.openai.com/docs/guides/evals) products.\n /// Defaults to false\n public var store: Bool?\n /// Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. Defaults to 0\n /// [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)\n public var frequencyPenalty: Double?\n /// Controls how the model responds to function calls. none means the model does not call a function, and responds to the end-user. auto means the model can pick between an end-user or calling a function. Specifying a particular function via {\"name\": \"my_function\"} forces the model to call that function. none is the default when no functions are present. auto is the default if functions are present.\n @available(*, deprecated, message: \"Deprecated in favor of tool_choice.\")\n public var functionCall: FunctionCall?\n /// Controls which (if any) function is called by the model. none means the model will not call a function and instead generates a message. \n /// auto means the model can pick between generating a message or calling a function. Specifying a particular function via `{\"type: \"function\", \"function\": {\"name\": \"my_function\"}}` forces the model to call that function.\n /// `none` is the default when no functions are present. auto is the default if functions are present.\n public var toolChoice: ToolChoice?\n /// A list of functions the model may generate JSON inputs for.\n @available(*, deprecated, message: \"Deprecated in favor of tools.\")\n public var functions: [ChatFunction]?\n /// A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.\n public var tools: [Tool]?\n /// Whether to enable parallel function calling during tool use. Defaults to true.\n public var parallelToolCalls: Bool?\n /// Modify the likelihood of specified tokens appearing in the completion.\n /// Accepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. Defaults to null.\n public var logitBias: [Int: Double]?\n /// Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message. This option is currently not available on the gpt-4-vision-preview model. Defaults to false.\n public var logprobs: Bool?\n /// An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.\n public var topLogprobs: Int?\n /// The maximum number of [tokens](https://platform.openai.com/tokenizer) that can be generated in the chat completion. This value can be used to control [costs](https://openai.com/api/pricing/) for text generated via API.\n /// This value is now deprecated in favor of max_completion_tokens, and is not compatible with [o1 series models](https://platform.openai.com/docs/guides/reasoning)\n public var maxTokens: Int?\n /// An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](https://platform.openai.com/docs/guides/reasoning)\n public var maCompletionTokens: Int?\n /// How many chat completion choices to generate for each input message. Defaults to 1.\n public var n: Int?\n /// Output types that you would like the model to generate for this request. Most models are capable of generating text, which is the default:\n /// [\"text\"]\n ///The gpt-4o-audio-preview model can also be used to [generate audio](https://platform.openai.com/docs/guides/audio). To request that this model generate both text and audio responses, you can use:\n /// [\"text\", \"audio\"]\n public var modalities: [String]?\n /// Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]. [Learn more.](https://platform.openai.com/docs/guides/audio)\n public var audio: Audio?\n /// Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. Defaults to 0\n /// [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/gpt/parameter-details)\n public var presencePenalty: Double?\n /// An object specifying the format that the model must output. Used to enable JSON mode.\n /// Setting to `{ type: \"json_object\" }` enables `JSON` mode, which guarantees the message the model generates is valid JSON.\n ///Important: when using `JSON` mode you must still instruct the model to produce `JSON` yourself via some conversation message, for example via your system message. If you don't do this, the model may generate an unending stream of whitespace until the generation reaches the token limit, which may take a lot of time and give the appearance of a \"stuck\" request. Also note that the message content may be partial (i.e. cut off) if `finish_reason=\"length\"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length.\n public var responseFormat: ResponseFormat?\n /// Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:\n /// If set to 'auto', the system will utilize scale tier credits until they are exhausted.\n /// If set to 'default', the request will be processed in the shared cluster.\n /// When this parameter is set, the response body will include the service_tier utilized.\n public var serviceTier: String?\n /// This feature is in `Beta`. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.\n /// Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.\n public var seed: Int?\n /// Up to 4 sequences where the API will stop generating further tokens. Defaults to null.\n public var stop: [String]?\n /// If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#event_stream_format) as they become available, with the stream terminated by a data: [DONE] message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions ).\n /// Defaults to false.\n var stream: Bool? = nil\n /// Options for streaming response. Only set this when you set stream: true\n var streamOptions: StreamOptions?\n /// What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n /// We generally recommend altering this or `top_p` but not both. Defaults to 1.\n public var temperature: Double?\n /// An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n /// We generally recommend altering this or `temperature` but not both. Defaults to 1\n public var topP: Double?\n /// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.\n /// [Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).\n public var user: String?\n \n public struct Message: Encodable {\n \n /// The role of the messages author. One of system, user, assistant, or tool message.\n let role: String\n /// The contents of the message. content is required for all messages, and may be null for assistant messages with function calls.\n let content: ContentType\n /// The name of the author of this message. name is required if role is function, and it should be the name of the function whose response is in the content. May contain a-z, A-Z, 0-9, and underscores, with a maximum length of 64 characters.\n let name: String?\n /// The name and arguments of a function that should be called, as generated by the model.\n @available(*, deprecated, message: \"Deprecated and replaced by `tool_calls`\")\n let functionCall: FunctionCall?\n /// The tool calls generated by the model, such as function calls.\n let toolCalls: [ToolCall]?\n /// Tool call that this message is responding to.\n let toolCallID: String?\n \n public enum ContentType: Encodable {\n \n case text(String)\n case contentArray([MessageContent])\n \n public func encode(to encoder: Encoder) throws {\n var container = encoder.singleValueContainer()\n switch self {\n case .text(let text):\n try container.encode(text)\n case .contentArray(let contentArray):\n try container.encode(contentArray)\n }\n }\n \n public enum MessageContent: Encodable, Equatable, Hashable {\n \n case text(String)\n case imageUrl(ImageDetail)\n \n public struct ImageDetail: Encodable, Equatable, Hashable {\n \n public let url: URL\n public let detail: String?\n \n enum CodingKeys: String, CodingKey {\n case url\n case detail\n }\n \n public func encode(to encoder: Encoder) throws {\n var container = encoder.container(keyedBy: CodingKeys.self)\n try container.encode(url, forKey: .url)\n try container.encode(detail, forKey: .detail)\n }\n \n public init(url: URL, detail: String? = nil) {\n self.url = url\n self.detail = detail\n }\n }\n \n enum CodingKeys: String, CodingKey {\n case type\n case text\n case imageUrl = \"image_url\"\n }\n \n public func encode(to encoder: Encoder) throws {\n var container = encoder.container(keyedBy: CodingKeys.self)\n switch self {\n case .text(let text):\n try container.encode(\"text\", forKey: .type)\n try container.encode(text, forKey: .text)\n case .imageUrl(let imageDetail):\n try container.encode(\"image_url\", forKey: .type)\n try container.encode(imageDetail, forKey: .imageUrl)\n }\n }\n \n public func hash(into hasher: inout Hasher) {\n switch self {\n case .text(let string):\n hasher.combine(string)\n case .imageUrl(let imageDetail):\n hasher.combine(imageDetail)\n }\n }\n \n public static func ==(lhs: MessageContent, rhs: MessageContent) -> Bool {\n switch (lhs, rhs) {\n case let (.text(a), .text(b)):\n return a == b\n case let (.imageUrl(a), .imageUrl(b)):\n return a == b\n default:\n return false\n }\n }\n }\n }\n \n public enum Role: String {\n case system // content, role\n case user // content, role\n case assistant // content, role, tool_calls\n case tool // content, role, tool_call_id\n }\n \n enum CodingKeys: String, CodingKey {\n case role\n case content\n case name\n case functionCall = \"function_call\"\n case toolCalls = \"tool_calls\"\n case toolCallID = \"tool_call_id\"\n }\n \n public init(\n role: Role,\n content: ContentType,\n name: String? = nil,\n functionCall: FunctionCall? = nil,\n toolCalls: [ToolCall]? = nil,\n toolCallID: String? = nil)\n {\n self.role = role.rawValue\n self.content = content\n self.name = name\n self.functionCall = functionCall\n self.toolCalls = toolCalls\n self.toolCallID = toolCallID\n }\n }\n \n @available(*, deprecated, message: \"Deprecated in favor of ToolChoice.\")\n public enum FunctionCall: Encodable, Equatable {\n case none\n case auto\n case function(String)\n \n enum CodingKeys: String, CodingKey {\n case none = \"none\"\n case auto = \"auto\"\n case function = \"name\"\n }\n \n public func encode(to encoder: Encoder) throws {\n switch self {\n case .none:\n var container = encoder.singleValueContainer()\n try container.encode(CodingKeys.none.rawValue)\n case .auto:\n var container = encoder.singleValueContainer()\n try container.encode(CodingKeys.auto.rawValue)\n case .function(let name):\n var container = encoder.container(keyedBy: CodingKeys.self)\n try container.encode(name, forKey: .function)\n }\n }\n }\n \n /// [Documentation](https://platform.openai.com/docs/api-reference/chat/create#chat-create-tools)\n public struct Tool: Encodable {\n \n /// The type of the tool. Currently, only `function` is supported.\n let type: String\n /// object\n let function: ChatFunction\n \n public init(\n type: String = \"function\",\n function: ChatFunction)\n {\n self.type = type\n self.function = function\n }\n }\n \n public struct ChatFunction: Codable, Equatable {\n \n /// The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.\n let name: String\n /// A description of what the function does, used by the model to choose when and how to call the function.\n let description: String?\n /// The parameters the functions accepts, described as a JSON Schema object. See the [guide](https://platform.openai.com/docs/guides/gpt/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema) for documentation about the format.\n /// Omitting parameters defines a function with an empty parameter list.\n let parameters: JSONSchema?\n /// Defaults to false, Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the [function calling guide].(https://platform.openai.com/docs/api-reference/chat/docs/guides/function-calling)\n let strict: Bool?\n \n public init(\n name: String,\n strict: Bool?,\n description: String?,\n parameters: JSONSchema?)\n {\n self.name = name\n self.strict = strict\n self.description = description\n self.parameters = parameters\n }\n }\n \n public enum ServiceTier: String, Encodable {\n /// Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:\n /// If set to 'auto', the system will utilize scale tier credits until they are exhausted.\n /// If set to 'default', the request will be processed in the shared cluster.\n /// When this parameter is set, the response body will include the service_tier utilized.\n case auto\n case `default`\n }\n \n public struct StreamOptions: Encodable {\n /// If set, an additional chunk will be streamed before the data: [DONE] message.\n /// The usage field on this chunk shows the token usage statistics for the entire request,\n /// and the choices field will always be an empty array. All other chunks will also include\n /// a usage field, but with a null value.\n let includeUsage: Bool\n\n enum CodingKeys: String, CodingKey {\n case includeUsage = \"include_usage\"\n }\n }\n \n /// Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]\n /// [Learn more.](https://platform.openai.com/docs/guides/audio)\n public struct Audio: Encodable {\n /// Specifies the voice type. Supported voices are alloy, echo, fable, onyx, nova, and shimmer.\n public let voice: String\n /// Specifies the output audio format. Must be one of wav, mp3, flac, opus, or pcm16.\n public let format: String\n \n public init(\n voice: String,\n format: String)\n {\n self.voice = voice\n self.format = format\n }\n }\n\n enum CodingKeys: String, CodingKey {\n case messages\n case model\n case store\n case frequencyPenalty = \"frequency_penalty\"\n case toolChoice = \"tool_choice\"\n case functionCall = \"function_call\"\n case tools\n case parallelToolCalls = \"parallel_tool_calls\"\n case functions\n case logitBias = \"logit_bias\"\n case logprobs\n case topLogprobs = \"top_logprobs\"\n case maxTokens = \"max_tokens\"\n case maCompletionTokens = \"max_completion_tokens\"\n case n\n case modalities\n case audio\n case responseFormat = \"response_format\"\n case presencePenalty = \"presence_penalty\"\n case seed\n case serviceTier = \"service_tier\"\n case stop\n case stream\n case streamOptions = \"stream_options\"\n case temperature\n case topP = \"top_p\"\n case user\n }\n \n public init(\n messages: [Message],\n model: Model,\n store: Bool? = nil,\n frequencyPenalty: Double? = nil,\n functionCall: FunctionCall? = nil,\n toolChoice: ToolChoice? = nil,\n functions: [ChatFunction]? = nil,\n tools: [Tool]? = nil,\n parallelToolCalls: Bool? = nil,\n logitBias: [Int: Double]? = nil,\n logProbs: Bool? = nil,\n topLogprobs: Int? = nil,\n maxTokens: Int? = nil,\n n: Int? = nil,\n modalities: [String]? = nil,\n audio: Audio? = nil,\n responseFormat: ResponseFormat? = nil,\n presencePenalty: Double? = nil,\n serviceTier: ServiceTier? = nil,\n seed: Int? = nil,\n stop: [String]? = nil,\n temperature: Double? = nil,\n topProbability: Double? = nil,\n user: String? = nil)\n {\n self.messages = messages\n self.model = model.value\n self.store = store\n self.frequencyPenalty = frequencyPenalty\n self.functionCall = functionCall\n self.toolChoice = toolChoice\n self.functions = functions\n self.tools = tools\n self.parallelToolCalls = parallelToolCalls\n self.logitBias = logitBias\n self.logprobs = logProbs\n self.topLogprobs = topLogprobs\n self.maxTokens = maxTokens\n self.n = n\n self.modalities = modalities\n self.audio = audio\n self.responseFormat = responseFormat\n self.presencePenalty = presencePenalty\n self.serviceTier = serviceTier?.rawValue\n self.seed = seed\n self.stop = stop\n self.temperature = temperature\n self.topP = topProbability\n self.user = user\n }\n}\n```\n\nResponse\n### Chat completion object\n```swift\n/// Represents a chat [completion](https://platform.openai.com/docs/api-reference/chat/object) response returned by model, based on the provided input.\npublic struct ChatCompletionObject: Decodable {\n \n /// A unique identifier for the chat completion.\n public let id: String\n /// A list of chat completion choices. Can be more than one if n is greater than 1.\n public let choices: [ChatChoice]\n /// The Unix timestamp (in seconds) of when the chat completion was created.\n public let created: Int\n /// The model used for the chat completion.\n public let model: String\n /// The service tier used for processing the request. This field is only included if the service_tier parameter is specified in the request.\n public let serviceTier: String?\n /// This fingerprint represents the backend configuration that the model runs with.\n /// Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.\n public let systemFingerprint: String?\n /// The object type, which is always chat.completion.\n public let object: String\n /// Usage statistics for the completion request.\n public let usage: ChatUsage\n \n public struct ChatChoice: Decodable {\n \n /// The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, content_filter if content was omitted due to a flag from our content filters, tool_calls if the model called a tool, or function_call (deprecated) if the model called a function.\n public let finishReason: IntOrStringValue?\n /// The index of the choice in the list of choices.\n public let index: Int\n /// A chat completion message generated by the model.\n public let message: ChatMessage \n /// Log probability information for the choice.\n public let logprobs: LogProb?\n \n public struct ChatMessage: Decodable {\n \n /// The contents of the message.\n public let content: String?\n /// The tool calls generated by the model, such as function calls.\n public let toolCalls: [ToolCall]?\n /// The name and arguments of a function that should be called, as generated by the model.\n @available(*, deprecated, message: \"Deprecated and replaced by `tool_calls`\")\n public let functionCall: FunctionCall?\n /// The role of the author of this message.\n public let role: String\n /// Provided by the Vision API.\n public let finishDetails: FinishDetails?\n /// The refusal message generated by the model.\n public let refusal: String?\n /// If the audio output modality is requested, this object contains data about the audio response from the model. [Learn more](https://platform.openai.com/docs/guides/audio).\n public let audio: Audio?\n \n /// Provided by the Vision API.\n public struct FinishDetails: Decodable {\n let type: String\n }\n \n public struct Audio: Decodable {\n /// Unique identifier for this audio response.\n public let id: String\n /// The Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations.\n public let expiresAt: Int\n /// Base64 encoded audio bytes generated by the model, in the format specified in the request.\n public let data: String\n /// Transcript of the audio generated by the model.\n public let transcript: String\n \n enum CodingKeys: String, CodingKey {\n case id\n case expiresAt = \"expires_at\"\n case data\n case transcript\n }\n }\n }\n \n public struct LogProb: Decodable {\n /// A list of message content tokens with log probability information.\n let content: [TokenDetail]\n }\n \n public struct TokenDetail: Decodable {\n /// The token.\n let token: String\n /// The log probability of this token.\n let logprob: Double\n /// A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.\n let bytes: [Int]?\n /// List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.\n let topLogprobs: [TopLogProb]\n \n enum CodingKeys: String, CodingKey {\n case token, logprob, bytes\n case topLogprobs = \"top_logprobs\"\n }\n \n struct TopLogProb: Decodable {\n /// The token.\n let token: String\n /// The log probability of this token.\n let logprob: Double\n /// A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.\n let bytes: [Int]?\n }\n }\n }\n \n public struct ChatUsage: Decodable {\n \n /// Number of tokens in the generated completion.\n public let completionTokens: Int\n /// Number of tokens in the prompt.\n public let promptTokens: Int\n /// Total number of tokens used in the request (prompt + completion).\n public let totalTokens: Int\n }\n}\n```\n\nUsage\n```swift\nlet prompt = \"Tell me a joke\"\nlet parameters = ChatCompletionParameters(messages: [.init(role: .user, content: .text(prompt))], model: .gpt4o)\nlet chatCompletionObject = service.startChat(parameters: parameters)\n```\n\nResponse\n### Chat completion chunk object\n```swift\n/// Represents a [streamed](https://platform.openai.com/docs/api-reference/chat/streaming) chunk of a chat completion response returned by model, based on the provided input.\npublic struct ChatCompletionChunkObject: Decodable {\n \n /// A unique identifier for the chat completion chunk.\n public let id: String\n /// A list of chat completion choices. Can be more than one if n is greater than 1.\n public let choices: [ChatChoice]\n /// The Unix timestamp (in seconds) of when the chat completion chunk was created.\n public let created: Int\n /// The model to generate the completion.\n public let model: String\n /// The service tier used for processing the request. This field is only included if the service_tier parameter is specified in the request.\n public let serviceTier: String?\n /// This fingerprint represents the backend configuration that the model runs with.\n /// Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.\n public let systemFingerprint: String?\n /// The object type, which is always chat.completion.chunk.\n public let object: String\n \n public struct ChatChoice: Decodable {\n \n /// A chat completion delta generated by streamed model responses.\n public let delta: Delta\n /// The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, content_filter if content was omitted due to a flag from our content filters, tool_calls if the model called a tool, or function_call (deprecated) if the model called a function.\n public let finishReason: IntOrStringValue?\n /// The index of the choice in the list of choices.\n public let index: Int\n /// Provided by the Vision API.\n public let finishDetails: FinishDetails?\n \n public struct Delta: Decodable {\n \n /// The contents of the chunk message.\n public let content: String?\n /// The tool calls generated by the model, such as function calls.\n public let toolCalls: [ToolCall]?\n /// The name and arguments of a function that should be called, as generated by the model.\n @available(*, deprecated, message: \"Deprecated and replaced by `tool_calls`\")\n public let functionCall: FunctionCall?\n /// The role of the author of this message.\n public let role: String?\n }\n \n public struct LogProb: Decodable {\n /// A list of message content tokens with log probability information.\n let content: [TokenDetail]\n }\n \n public struct TokenDetail: Decodable {\n /// The token.\n let token: String\n /// The log probability of this token.\n let logprob: Double\n /// A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.\n let bytes: [Int]?\n /// List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.\n let topLogprobs: [TopLogProb]\n \n enum CodingKeys: String, CodingKey {\n case token, logprob, bytes\n case topLogprobs = \"top_logprobs\"\n }\n \n struct TopLogProb: Decodable {\n /// The token.\n let token: String\n /// The log probability of this token.\n let logprob: Double\n /// A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.\n let bytes: [Int]?\n }\n }\n \n /// Provided by the Vision API.\n public struct FinishDetails: Decodable {\n let type: String\n }\n }\n}\n```\nUsage\n```swift\nlet prompt = \"Tell me a joke\"\nlet parameters = ChatCompletionParameters(messages: [.init(role: .user, content: .text(prompt))], model: .gpt4o)\nlet chatCompletionObject = try await service.startStreamedChat(parameters: parameters)\n```\n\n### Function Calling\n\nChat Completion also supports [Function Calling](https://platform.openai.com/docs/guides/function-calling) and [Parallel Function Calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling). `functions` has been deprecated in favor of `tools` check [OpenAI Documentation](https://platform.openai.com/docs/api-reference/chat/create) for more.\n\n```swift\npublic struct ToolCall: Codable {\n\n public let index: Int\n /// The ID of the tool call.\n public let id: String?\n /// The type of the tool. Currently, only `function` is supported.\n public let type: String?\n /// The function that the model called.\n public let function: FunctionCall\n\n public init(\n index: Int,\n id: String,\n type: String = \"function\",\n function: FunctionCall)\n {\n self.index = index\n self.id = id\n self.type = type\n self.function = function\n }\n}\n\npublic struct FunctionCall: Codable {\n\n /// The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.\n let arguments: String\n /// The name of the function to call.\n let name: String\n\n public init(\n arguments: String,\n name: String)\n {\n self.arguments = arguments\n self.name = name\n }\n}\n```\n\nUsage\n```swift\n/// Define a `ToolCall`\nvar tool: ToolCall {\n .init(\n type: \"function\", // The type of the tool. Currently, only \"function\" is supported.\n function: .init(\n name: \"create_image\",\n description: \"Call this function if the request asks to generate an image\",\n parameters: .init(\n type: .object,\n properties: [\n \"prompt\": .init(type: .string, description: \"The exact prompt passed in.\"),\n \"count\": .init(type: .integer, description: \"The number of images requested\")\n ],\n required: [\"prompt\", \"count\"])))\n}\n\nlet prompt = \"Show me an image of an unicorn eating ice cream\"\nlet content: ChatCompletionParameters.Message.ContentType = .text(prompt)\nlet parameters = ChatCompletionParameters(messages: [.init(role: .user, content: content)], model: .gpt41106Preview, tools: [tool])\nlet chatCompletionObject = try await service.startStreamedChat(parameters: parameters)\n```\nFor more details about how to also uploading base 64 encoded images in iOS check the [ChatFunctionsCalllDemo](https://github.com/jamesrochabrun/SwiftOpenAI/tree/main/Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatFunctionsCall) demo on the Examples section of this package.\n\n### Structured Outputs\n\n#### Documentation:\n\n- [Structured Outputs Guides](https://platform.openai.com/docs/guides/structured-outputs/structured-outputs)\n- [Examples](https://platform.openai.com/docs/guides/structured-outputs/examples)\n- [How to use](https://platform.openai.com/docs/guides/structured-outputs/how-to-use)\n- [Supported schemas](https://platform.openai.com/docs/guides/structured-outputs/supported-schemas)\n\nMust knowns:\n\n- [All fields must be required](https://platform.openai.com/docs/guides/structured-outputs/all-fields-must-be-required) , To use Structured Outputs, all fields or function parameters must be specified as required.\n- Although all fields must be required (and the model will return a value for each parameter), it is possible to emulate an optional parameter by using a union type with null.\n- [Objects have limitations on nesting depth and size](https://platform.openai.com/docs/guides/structured-outputs/objects-have-limitations-on-nesting-depth-and-size), A schema may have up to 100 object properties total, with up to 5 levels of nesting.\n\n- [additionalProperties](https://platform.openai.com/docs/guides/structured-outputs/additionalproperties-false-must-always-be-set-in-objects)): false must always be set in objects\nadditionalProperties controls whether it is allowable for an object to contain additional keys / values that were not defined in the JSON Schema.\nStructured Outputs only supports generating specified keys / values, so we require developers to set additionalProperties: false to opt into Structured Outputs.\n- [Key ordering](https://platform.openai.com/docs/guides/structured-outputs/key-ordering), When using Structured Outputs, outputs will be produced in the same order as the ordering of keys in the schema.\n- [Recursive schemas are supported](https://platform.openai.com/docs/guides/structured-outputs/recursive-schemas-are-supported)\n\n#### How to use Structured Outputs in SwiftOpenAI\n\n1. Function calling: Structured Outputs via tools is available by setting strict: true within your function definition. This feature works with all models that support tools, including all models gpt-4-0613 and gpt-3.5-turbo-0613 and later. When Structured Outputs are enabled, model outputs will match the supplied tool definition.\n\nUsing this schema:\n\n```json\n{\n \"schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"steps\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"explanation\": {\n \"type\": \"string\"\n },\n \"output\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\"explanation\", \"output\"],\n \"additionalProperties\": false\n }\n },\n \"final_answer\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\"steps\", \"final_answer\"],\n \"additionalProperties\": false\n }\n}\n```\n\nYou can use the convenient `JSONSchema` object like this:\n\n```swift\n// 1: Define the Step schema object\n\nlet stepSchema = JSONSchema(\n type: .object,\n properties: [\n \"explanation\": JSONSchema(type: .string),\n \"output\": JSONSchema(\n type: .string)\n ],\n required: [\"explanation\", \"output\"],\n additionalProperties: false\n)\n\n// 2. Define the steps Array schema.\n\nlet stepsArraySchema = JSONSchema(type: .array, items: stepSchema)\n\n// 3. Define the final Answer schema.\n\nlet finalAnswerSchema = JSONSchema(type: .string)\n\n// 4. Define math reponse JSON schema.\n\nlet mathResponseSchema = JSONSchema(\n type: .object,\n properties: [\n \"steps\": stepsArraySchema,\n \"final_answer\": finalAnswerSchema\n ],\n required: [\"steps\", \"final_answer\"],\n additionalProperties: false\n)\n\nlet tool = ChatCompletionParameters.Tool(\n function: .init(\n name: \"math_response\",\n strict: true,\n parameters: mathResponseSchema))\n)\n\nlet prompt = \"solve 8x + 31 = 2\"\nlet systemMessage = ChatCompletionParameters.Message(role: .system, content: .text(\"You are a math tutor\"))\nlet userMessage = ChatCompletionParameters.Message(role: .user, content: .text(prompt))\nlet parameters = ChatCompletionParameters(\n messages: [systemMessage, userMessage],\n model: .gpt4o20240806,\n tools: [tool])\n\nlet chat = try await service.startChat(parameters: parameters)\n```\n\n2. A new option for the `response_format` parameter: developers can now supply a JSON Schema via `json_schema`, a new option for the response_format parameter. This is useful when the model is not calling a tool, but rather, responding to the user in a structured way. This feature works with our newest GPT-4o models: `gpt-4o-2024-08-06`, released today, and `gpt-4o-mini-2024-07-18`. When a response_format is supplied with strict: true, model outputs will match the supplied schema.\n\nUsing the previous schema, this is how you can implement it as json schema using the convenient `JSONSchemaResponseFormat` object:\n\n```swift\n// 1: Define the Step schema object\n\nlet stepSchema = JSONSchema(\n type: .object,\n properties: [\n \"explanation\": JSONSchema(type: .string),\n \"output\": JSONSchema(\n type: .string)\n ],\n required: [\"explanation\", \"output\"],\n additionalProperties: false\n)\n\n// 2. Define the steps Array schema.\n\nlet stepsArraySchema = JSONSchema(type: .array, items: stepSchema)\n\n// 3. Define the final Answer schema.\n\nlet finalAnswerSchema = JSONSchema(type: .string)\n\n// 4. Define the response format JSON schema.\n\nlet responseFormatSchema = JSONSchemaResponseFormat(\n name: \"math_response\",\n strict: true,\n schema: JSONSchema(\n type: .object,\n properties: [\n \"steps\": stepsArraySchema,\n \"final_answer\": finalAnswerSchema\n ],\n required: [\"steps\", \"final_answer\"],\n additionalProperties: false\n )\n)\n\nlet prompt = \"solve 8x + 31 = 2\"\nlet systemMessage = ChatCompletionParameters.Message(role: .system, content: .text(\"You are a math tutor\"))\nlet userMessage = ChatCompletionParameters.Message(role: .user, content: .text(prompt))\nlet parameters = ChatCompletionParameters(\n messages: [systemMessage, userMessage],\n model: .gpt4o20240806,\n responseFormat: .jsonSchema(responseFormatSchema))\n```\n\nSwiftOpenAI Structred outputs supports:\n\n- [x] Tools Structured output.\n- [x] Response format Structure output.\n- [x] Recursive Schema.\n- [x] Optional values Schema.\n- [ ] Pydantic models.\n\nWe don't support Pydantic models, users need tos manually create Schemas using `JSONSchema` or `JSONSchemaResponseFormat` objects.\n\nPro tip 🔥 Use [iosAICodeAssistant GPT](https://chatgpt.com/g/g-qj7RuW7PY-iosai-code-assistant) to construct SwifOpenAI schemas. Just paste your JSON schema and ask the GPT to create SwiftOpenAI schemas for tools and response format.\n\nFor more details visit the Demo project for [tools](https://github.com/jamesrochabrun/SwiftOpenAI/tree/main/Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatStructureOutputTool) and [response format](https://github.com/jamesrochabrun/SwiftOpenAI/tree/main/Examples/SwiftOpenAIExample/SwiftOpenAIExample/ChatStructuredOutputs).\n\n### Vision\n\n[Vision](https://platform.openai.com/docs/guides/vision) API is available for use; developers must access it through the chat completions API, specifically using the gpt-4-vision-preview model or gpt-4o model. Using any other model will not provide an image description\n\nUsage\n```swift\nlet imageURL = \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\nlet prompt = \"What is this?\"\nlet messageContent: [ChatCompletionParameters.Message.ContentType.MessageContent] = [.text(prompt), .imageUrl(.init(url: imageURL)] // Users can add as many `.imageUrl` instances to the service.\nlet parameters = ChatCompletionParameters(messages: [.init(role: .user, content: .contentArray(messageContent))], model: .gpt4o)\nlet chatCompletionObject = try await service.startStreamedChat(parameters: parameters)\n```\n\n\n\nFor more details about how to also uploading base 64 encoded images in iOS check the [ChatVision](https://github.com/jamesrochabrun/SwiftOpenAI/tree/main/Examples/SwiftOpenAIExample/SwiftOpenAIExample/Vision) demo on the Examples section of this package.\n\n### Response\n\nOpenAI's most advanced interface for generating model responses. Supports text and image inputs, and text outputs. Create stateful interactions with the model, using the output of previous responses as input. Extend the model's capabilities with built-in tools for file search, web search, computer use, and more. Allow the model access to external systems and data using function calling.\n\n- Full streaming support with `responseCreateStream` method\n- Comprehensive `ResponseStreamEvent` enum covering 40+ event types\n- Enhanced `InputMessage` with `id` field for response ID tracking\n- Improved conversation state management with `previousResponseId`\n- Real-time text streaming, function calls, and tool usage events\n- Support for reasoning summaries, web search, file search, and image generation events\n- **NEW**: Support for GPT-5 models (gpt-5, gpt-5-mini, gpt-5-nano)\n- **NEW**: Verbosity parameter for controlling response detail level\n\n#### ModelResponseParameter\n\nThe `ModelResponseParameter` provides a comprehensive interface for creating model responses:\n\n```swift\nlet parameters = ModelResponseParameter(\n input: .text(\"What is the answer to life, the universe, and everything?\"),\n model: .gpt5, // Support for GPT-5, GPT-5-mini, GPT-5-nano\n text: TextConfiguration(\n format: .text,\n verbosity: \"low\" // NEW: Control response verbosity (\"low\", \"medium\", \"high\")\n ),\n temperature: 0.7\n)\n\nlet response = try await service.responseCreate(parameters)\n```\n\n#### Available GPT-5 Models\n\n```swift\npublic enum Model {\n case gpt5 // Complex reasoning, broad world knowledge, and code-heavy or multi-step agentic tasks\n case gpt5Mini // Cost-optimized reasoning and chat; balances speed, cost, and capability\n case gpt5Nano // High-throughput tasks, especially simple instruction-following or classification\n // ... other models\n}\n```\n\n#### TextConfiguration with Verbosity\n\n```swift\n// Create a text configuration with verbosity control\nlet textConfig = TextConfiguration(\n format: .text, // Can be .text, .jsonObject, or .jsonSchema\n verbosity: \"medium\" // Controls response detail level\n)\n```\n\nRelated guides:\n\n- [Quickstart](https://platform.openai.com/docs/quickstart?api-mode=responses)\n- [Text inputs and outputs](https://platform.openai.com/docs/guides/text?api-mode=responses)\n- [Image inputs](https://platform.openai.com/docs/guides/images?api-mode=responses)\n- [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses)\n- [Function calling](https://platform.openai.com/docs/guides/function-calling?api-mode=responses)\n- [Conversation state](https://platform.openai.com/docs/guides/conversation-state?api-mode=responses)\n- [Extend the models with tools](https://platform.openai.com/docs/guides/tools?api-mode=responses)\n\nParameters\n```swift\n/// [Creates a model response.](https://platform.openai.com/docs/api-reference/responses/create)\npublic struct ModelResponseParameter: Codable {\n\n /// Text, image, or file inputs to the model, used to generate a response.\n /// A text input to the model, equivalent to a text input with the user role.\n /// A list of one or many input items to the model, containing different content types.\n public var input: InputType\n\n /// Model ID used to generate the response, like gpt-4o or o1. OpenAI offers a wide range of models with\n /// different capabilities, performance characteristics, and price points.\n /// Refer to the model guide to browse and compare available models.\n public var model: String\n\n /// Specify additional output data to include in the model response. Currently supported values are:\n /// file_search_call.results : Include the search results of the file search tool call.\n /// message.input_image.image_url : Include image urls from the input message.\n /// computer_call_output.output.image_url : Include image urls from the computer call output.\n public var include: [String]?\n\n /// Inserts a system (or developer) message as the first item in the model's context.\n /// When using along with previous_response_id, the instructions from a previous response will be not be\n /// carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.\n public var instructions: String?\n\n /// An upper bound for the number of tokens that can be generated for a response, including visible output tokens\n /// and reasoning tokens.\n public var maxOutputTokens: Int?\n\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information\n /// about the object in a structured format, and querying for objects via API or the dashboard.\n /// Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.\n public var metadata: [String: String]?\n\n /// Whether to allow the model to run tool calls in parallel.\n /// Defaults to true\n public var parallelToolCalls: Bool?\n\n /// The unique ID of the previous response to the model. Use this to create multi-turn conversations.\n /// Learn more about conversation state.\n public var previousResponseId: String?\n\n /// o-series models only\n /// Configuration options for reasoning models.\n public var reasoning: Reasoning?\n\n /// Whether to store the generated model response for later retrieval via API.\n /// Defaults to true\n public var store: Bool?\n\n /// If set to true, the model response data will be streamed to the client as it is generated using server-sent events.\n public var stream: Bool?\n\n /// What sampling temperature to use, between 0 and 2.\n /// Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n /// We generally recommend altering this or top_p but not both.\n /// Defaults to 1\n public var temperature: Double?\n\n /// Configuration options for a text response from the model. Can be plain text or structured JSON data.\n public var text: TextConfiguration?\n\n /// How the model should select which tool (or tools) to use when generating a response.\n /// See the tools parameter to see how to specify which tools the model can call.\n public var toolChoice: ToolChoiceMode?\n\n /// An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.\n public var tools: [Tool]?\n\n /// An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.\n /// So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n /// We generally recommend altering this or temperature but not both.\n /// Defaults to 1\n public var topP: Double?\n\n /// The truncation strategy to use for the model response.\n /// Defaults to disabled\n public var truncation: String?\n\n /// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.\n public var user: String?\n}\n```\n\n[The Response object](https://platform.openai.com/docs/api-reference/responses/object)\n\n```swift\n/// The Response object returned when retrieving a model response\npublic struct ResponseModel: Decodable {\n\n /// Unix timestamp (in seconds) of when this Response was created.\n public let createdAt: Int\n\n /// An error object returned when the model fails to generate a Response.\n public let error: ErrorObject?\n\n /// Unique identifier for this Response.\n public let id: String\n\n /// Details about why the response is incomplete.\n public let incompleteDetails: IncompleteDetails?\n\n /// Inserts a system (or developer) message as the first item in the model's context.\n public let instructions: String?\n\n /// An upper bound for the number of tokens that can be generated for a response, including visible output tokens\n /// and reasoning tokens.\n public let maxOutputTokens: Int?\n\n /// Set of 16 key-value pairs that can be attached to an object.\n public let metadata: [String: String]\n\n /// Model ID used to generate the response, like gpt-4o or o1.\n public let model: String\n\n /// The object type of this resource - always set to response.\n public let object: String\n\n /// An array of content items generated by the model.\n public let output: [OutputItem]\n\n /// Whether to allow the model to run tool calls in parallel.\n public let parallelToolCalls: Bool\n\n /// The unique ID of the previous response to the model. Use this to create multi-turn conversations.\n public let previousResponseId: String?\n\n /// Configuration options for reasoning models.\n public let reasoning: Reasoning?\n\n /// The status of the response generation. One of completed, failed, in_progress, or incomplete.\n public let status: String\n\n /// What sampling temperature to use, between 0 and 2.\n public let temperature: Double?\n\n /// Configuration options for a text response from the model.\n public let text: TextConfiguration\n\n /// How the model should select which tool (or tools) to use when generating a response.\n public let toolChoice: ToolChoiceMode\n\n /// An array of tools the model may call while generating a response.\n public let tools: [Tool]\n\n /// An alternative to sampling with temperature, called nucleus sampling.\n public let topP: Double?\n\n /// The truncation strategy to use for the model response.\n public let truncation: String?\n\n /// Represents token usage details.\n public let usage: Usage?\n\n /// A unique identifier representing your end-user.\n public let user: String?\n \n /// Convenience property that aggregates all text output from output_text items in the output array.\n /// Similar to the outputText property in Python and JavaScript SDKs.\n public var outputText: String? \n}\n```\n\nInput Types\n```swift\n// InputType represents the input to the Response API\npublic enum InputType: Codable {\n case string(String) // Simple text input\n case array([InputItem]) // Array of input items for complex conversations\n}\n\n// InputItem represents different types of input\npublic enum InputItem: Codable {\n case message(InputMessage) // User, assistant, system messages\n case functionToolCall(FunctionToolCall) // Function calls\n case functionToolCallOutput(FunctionToolCallOutput) // Function outputs\n // ... other input types\n}\n\n// InputMessage structure with support for response IDs\npublic struct InputMessage: Codable {\n public let role: String // \"user\", \"assistant\", \"system\"\n public let content: MessageContent\n public let type: String? // Always \"message\"\n public let status: String? // \"completed\" for assistant messages\n public let id: String? // Response ID for assistant messages\n}\n\n// MessageContent can be text or array of content items\npublic enum MessageContent: Codable {\n case text(String)\n case array([ContentItem]) // For multimodal content\n}\n```\n\nUsage\n\nSimple text input\n```swift\nlet prompt = \"What is the capital of France?\"\nlet parameters = ModelResponseParameter(input: .string(prompt), model: .gpt4o)\nlet response = try await service.responseCreate(parameters)\n```\n\nText input with reasoning\n```swift\nlet prompt = \"How much wood would a woodchuck chuck?\"\nlet parameters = ModelResponseParameter(\n input: .string(prompt),\n model: .o3Mini,\n reasoning: Reasoning(effort: \"high\")\n)\nlet response = try await service.responseCreate(parameters)\n```\n\nImage input\n```swift\nlet textPrompt = \"What is in this image?\"\nlet imageUrl = \"https://example.com/path/to/image.jpg\"\nlet imageContent = ContentItem.imageUrl(ImageUrlContent(imageUrl: imageUrl))\nlet textContent = ContentItem.text(TextContent(text: textPrompt))\nlet message = InputItem(role: \"user\", content: [textContent, imageContent])\nlet parameters = ModelResponseParameter(input: .array([message]), model: .gpt4o)\nlet response = try await service.responseCreate(parameters)\n```\n\nUsing tools (web search)\n```swift\nlet prompt = \"What was a positive news story from today?\"\nlet parameters = ModelResponseParameter(\n input: .string(prompt),\n model: .gpt4o,\n tools: [Tool(type: \"web_search_preview\", function: nil)]\n)\nlet response = try await service.responseCreate(parameters)\n```\n\nUsing tools (file search)\n```swift\nlet prompt = \"What are the key points in the document?\"\nlet parameters = ModelResponseParameter(\n input: .string(prompt),\n model: .gpt4o,\n tools: [\n Tool(\n type: \"file_search\",\n function: ChatCompletionParameters.ChatFunction(\n name: \"file_search\",\n strict: false,\n description: \"Search through files\",\n parameters: JSONSchema(\n type: .object,\n properties: [\n \"vector_store_ids\": JSONSchema(\n type: .array,\n items: JSONSchema(type: .string)\n ),\n \"max_num_results\": JSONSchema(type: .integer)\n ],\n required: [\"vector_store_ids\"],\n additionalProperties: false\n )\n )\n )\n ]\n)\nlet response = try await service.responseCreate(parameters)\n```\n\nFunction calling\n```swift\nlet prompt = \"What is the weather like in Boston today?\"\nlet parameters = ModelResponseParameter(\n input: .string(prompt),\n model: .gpt4o,\n tools: [\n Tool(\n type: \"function\",\n function: ChatCompletionParameters.ChatFunction(\n name: \"get_current_weather\",\n strict: false,\n description: \"Get the current weather in a given location\",\n parameters: JSONSchema(\n type: .object,\n properties: [\n \"location\": JSONSchema(\n type: .string,\n description: \"The city and state, e.g. San Francisco, CA\"\n ),\n \"unit\": JSONSchema(\n type: .string,\n enum: [\"celsius\", \"fahrenheit\"]\n )\n ],\n required: [\"location\", \"unit\"],\n additionalProperties: false\n )\n )\n )\n ],\n toolChoice: .auto\n)\nlet response = try await service.responseCreate(parameters)\n```\n\nRetrieving a response\n```swift\nlet responseId = \"resp_abc123\"\nlet response = try await service.responseModel(id: responseId)\n```\n\n#### Streaming Responses\n\nThe Response API supports streaming responses using Server-Sent Events (SSE). This allows you to receive partial responses as they are generated, enabling real-time UI updates and better user experience.\n\nStream Events\n```swift\n// The ResponseStreamEvent enum represents all possible streaming events\npublic enum ResponseStreamEvent: Decodable {\n case responseCreated(ResponseCreatedEvent)\n case responseInProgress(ResponseInProgressEvent)\n case responseCompleted(ResponseCompletedEvent)\n case responseFailed(ResponseFailedEvent)\n case outputItemAdded(OutputItemAddedEvent)\n case outputTextDelta(OutputTextDeltaEvent)\n case outputTextDone(OutputTextDoneEvent)\n case functionCallArgumentsDelta(FunctionCallArgumentsDeltaEvent)\n case reasoningSummaryTextDelta(ReasoningSummaryTextDeltaEvent)\n case error(ErrorEvent)\n // ... and many more event types\n}\n```\n\nBasic Streaming Example\n```swift\n// Enable streaming by setting stream: true\nlet parameters = ModelResponseParameter(\n input: .string(\"Tell me a story\"),\n model: .gpt4o,\n stream: true\n)\n\n// Create a stream\nlet stream = try await service.responseCreateStream(parameters)\n\n// Process events as they arrive\nfor try await event in stream {\n switch event {\n case .outputTextDelta(let delta):\n // Append text chunk to your UI\n print(delta.delta, terminator: \"\")\n \n case .responseCompleted(let completed):\n // Response is complete\n print(\"\\nResponse ID: \\(completed.response.id)\")\n \n case .error(let error):\n // Handle errors\n print(\"Error: \\(error.message)\")\n \n default:\n // Handle other events as needed\n break\n }\n}\n```\n\nStreaming with Conversation State\n```swift\n// Maintain conversation continuity with previousResponseId\nvar previousResponseId: String? = nil\nvar messages: [(role: String, content: String)] = []\n\n// First message\nlet firstParams = ModelResponseParameter(\n input: .string(\"Hello!\"),\n model: .gpt4o,\n stream: true\n)\n\nlet firstStream = try await service.responseCreateStream(firstParams)\nvar firstResponse = \"\"\n\nfor try await event in firstStream {\n switch event {\n case .outputTextDelta(let delta):\n firstResponse += delta.delta\n \n case .responseCompleted(let completed):\n previousResponseId = completed.response.id\n messages.append((role: \"user\", content: \"Hello!\"))\n messages.append((role: \"assistant\", content: firstResponse))\n \n default:\n break\n }\n}\n\n// Follow-up message with conversation context\nvar inputArray: [InputItem] = []\n\n// Add conversation history\nfor message in messages {\n inputArray.append(.message(InputMessage(\n role: message.role,\n content: .text(message.content)\n )))\n}\n\n// Add new user message\ninputArray.append(.message(InputMessage(\n role: \"user\",\n content: .text(\"How are you?\")\n)))\n\nlet followUpParams = ModelResponseParameter(\n input: .array(inputArray),\n model: .gpt4o,\n previousResponseId: previousResponseId,\n stream: true\n)\n\nlet followUpStream = try await service.responseCreateStream(followUpParams)\n// Process the follow-up stream...\n```\n\nStreaming with Tools and Function Calling\n```swift\nlet parameters = ModelResponseParameter(\n input: .string(\"What's the weather in San Francisco?\"),\n model: .gpt4o,\n tools: [\n Tool(\n type: \"function\",\n function: ChatCompletionParameters.ChatFunction(\n name: \"get_weather\",\n description: \"Get current weather\",\n parameters: JSONSchema(\n type: .object,\n properties: [\n \"location\": JSONSchema(type: .string)\n ],\n required: [\"location\"]\n )\n )\n )\n ],\n stream: true\n)\n\nlet stream = try await service.responseCreateStream(parameters)\nvar functionCallArguments = \"\"\n\nfor try await event in stream {\n switch event {\n case .functionCallArgumentsDelta(let delta):\n // Accumulate function call arguments\n functionCallArguments += delta.delta\n \n case .functionCallArgumentsDone(let done):\n // Function call is complete\n print(\"Function: \\(done.name)\")\n print(\"Arguments: \\(functionCallArguments)\")\n \n case .outputTextDelta(let delta):\n // Regular text output\n print(delta.delta, terminator: \"\")\n \n default:\n break\n }\n}\n```\n\nCanceling a Stream\n```swift\n// Streams can be canceled using Swift's task cancellation\nlet streamTask = Task {\n let stream = try await service.responseCreateStream(parameters)\n \n for try await event in stream {\n // Check if task is cancelled\n if Task.isCancelled {\n break\n }\n \n // Process events...\n }\n}\n\n// Cancel the stream when needed\nstreamTask.cancel()\n```\n\nComplete Streaming Implementation Example\n```swift\n@MainActor\n@Observable\nclass ResponseStreamProvider {\n var messages: [Message] = []\n var isStreaming = false\n var error: String?\n \n private let service: OpenAIService\n private var previousResponseId: String?\n private var streamTask: Task?\n \n init(service: OpenAIService) {\n self.service = service\n }\n \n func sendMessage(_ text: String) {\n streamTask?.cancel()\n \n // Add user message\n messages.append(Message(role: .user, content: text))\n \n // Start streaming\n streamTask = Task {\n await streamResponse(for: text)\n }\n }\n \n private func streamResponse(for userInput: String) async {\n isStreaming = true\n error = nil\n \n // Create streaming message placeholder\n let streamingMessage = Message(role: .assistant, content: \"\", isStreaming: true)\n messages.append(streamingMessage)\n \n do {\n // Build conversation history\n var inputArray: [InputItem] = []\n for message in messages.dropLast(2) {\n inputArray.append(.message(InputMessage(\n role: message.role.rawValue,\n content: .text(message.content)\n )))\n }\n inputArray.append(.message(InputMessage(\n role: \"user\",\n content: .text(userInput)\n )))\n \n let parameters = ModelResponseParameter(\n input: .array(inputArray),\n model: .gpt4o,\n previousResponseId: previousResponseId,\n stream: true\n )\n \n let stream = try await service.responseCreateStream(parameters)\n var accumulatedText = \"\"\n \n for try await event in stream {\n guard !Task.isCancelled else { break }\n \n switch event {\n case .outputTextDelta(let delta):\n accumulatedText += delta.delta\n updateStreamingMessage(with: accumulatedText)\n \n case .responseCompleted(let completed):\n previousResponseId = completed.response.id\n finalizeStreamingMessage(with: accumulatedText, responseId: completed.response.id)\n \n case .error(let errorEvent):\n throw APIError.requestFailed(description: errorEvent.message)\n \n default:\n break\n }\n }\n } catch {\n self.error = error.localizedDescription\n messages.removeLast() // Remove streaming message on error\n }\n \n isStreaming = false\n }\n \n private func updateStreamingMessage(with content: String) {\n if let index = messages.lastIndex(where: { $0.isStreaming }) {\n messages[index].content = content\n }\n }\n \n private func finalizeStreamingMessage(with content: String, responseId: String) {\n if let index = messages.lastIndex(where: { $0.isStreaming }) {\n messages[index].content = content\n messages[index].isStreaming = false\n messages[index].responseId = responseId\n }\n }\n}\n```\n\n### Embeddings\nParameters\n```swift\n/// [Creates](https://platform.openai.com/docs/api-reference/embeddings/create) an embedding vector representing the input text.\npublic struct EmbeddingParameter: Encodable {\n \n /// ID of the model to use. You can use the List models API to see all of your available models, or see our [Model overview ](https://platform.openai.com/docs/models/overview) for descriptions of them.\n let model: String\n /// Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or an array of token arrays. Each input must not exceed the max input tokens for the model (8191 tokens for text-embedding-ada-002) and cannot be an empty string. [How to Count Tokens with `tiktoken`](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)\n let input: String\n \n /// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more.](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids)\n let user: String?\n \n public enum Model: String {\n case textEmbeddingAda002 = \"text-embedding-ada-002\"\n }\n \n public init(\n model: Model = .textEmbeddingAda002,\n input: String,\n user: String? = nil)\n {\n self.model = model.value\n self.input = input\n self.user = user\n }\n}\n```\nResponse\n```swift\n/// [Represents an embedding vector returned by embedding endpoint.](https://platform.openai.com/docs/api-reference/embeddings/object)\npublic struct EmbeddingObject: Decodable {\n \n /// The object type, which is always \"embedding\".\n public let object: String\n /// The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the embedding guide.[https://platform.openai.com/docs/guides/embeddings]\n public let embedding: [Float]\n /// The index of the embedding in the list of embeddings.\n public let index: Int\n}\n```\n\nUsage\n```swift\nlet prompt = \"Hello world.\"\nlet embeddingObjects = try await service.createEmbeddings(parameters: parameters).data\n```\n\n### Fine-tuning\nParameters\n```swift\n/// [Creates a job](https://platform.openai.com/docs/api-reference/fine-tuning/create) that fine-tunes a specified model from a given dataset.\n///Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete.\npublic struct FineTuningJobParameters: Encodable {\n \n /// The name of the model to fine-tune. You can select one of the [supported models](https://platform.openai.com/docs/models/overview).\n let model: String\n /// The ID of an uploaded file that contains training data.\n /// See [upload file](https://platform.openai.com/docs/api-reference/files/upload) for how to upload a file.\n /// Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose fine-tune.\n /// See the [fine-tuning guide](https://platform.openai.com/docs/guides/fine-tuning) for more details.\n let trainingFile: String\n /// The hyperparameters used for the fine-tuning job.\n let hyperparameters: HyperParameters?\n /// A string of up to 18 characters that will be added to your fine-tuned model name.\n /// For example, a suffix of \"custom-model-name\" would produce a model name like ft:gpt-3.5-turbo:openai:custom-model-name:7p4lURel.\n /// Defaults to null.\n let suffix: String?\n /// The ID of an uploaded file that contains validation data.\n /// If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. These metrics can be viewed in the fine-tuning results file. The same data should not be present in both train and validation files.\n /// Your dataset must be formatted as a JSONL file. You must upload your file with the purpose fine-tune.\n /// See the [fine-tuning guide](https://platform.openai.com/docs/guides/fine-tuning) for more details.\n let validationFile: String?\n /// A list of integrations to enable for your fine-tuning job.\n let integrations: [Integration]?\n /// The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed is not specified, one will be generated for you.\n let seed: Int?\n \n /// Fine-tuning is [currently available](https://platform.openai.com/docs/guides/fine-tuning/what-models-can-be-fine-tuned) for the following models:\n /// gpt-3.5-turbo-0613 (recommended)\n /// babbage-002\n /// davinci-002\n /// OpenAI expects gpt-3.5-turbo to be the right model for most users in terms of results and ease of use, unless you are migrating a legacy fine-tuned model.\n public enum Model: String {\n case gpt35 = \"gpt-3.5-turbo-0613\" /// recommended\n case babbage002 = \"babbage-002\"\n case davinci002 = \"davinci-002\"\n }\n \n public struct HyperParameters: Encodable {\n /// The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.\n /// Defaults to auto.\n let nEpochs: Int?\n \n public init(\n nEpochs: Int?)\n {\n self.nEpochs = nEpochs\n }\n }\n \n public init(\n model: Model,\n trainingFile: String,\n hyperparameters: HyperParameters? = nil,\n suffix: String? = nil,\n validationFile: String? = nil)\n {\n self.model = model.rawValue\n self.trainingFile = trainingFile\n self.hyperparameters = hyperparameters\n self.suffix = suffix\n self.validationFile = validationFile\n }\n}\n```\nResponse\n```swift\n/// The fine_tuning.job object represents a [fine-tuning job](https://platform.openai.com/docs/api-reference/fine-tuning/object) that has been created through the API.\npublic struct FineTuningJobObject: Decodable {\n \n /// The object identifier, which can be referenced in the API endpoints.\n public let id: String\n /// The Unix timestamp (in seconds) for when the fine-tuning job was created.\n public let createdAt: Int\n /// For fine-tuning jobs that have failed, this will contain more information on the cause of the failure.\n public let error: OpenAIErrorResponse.Error?\n /// The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running.\n public let fineTunedModel: String?\n /// The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running.\n public let finishedAt: Int?\n /// The hyperparameters used for the fine-tuning job. See the [fine-tuning guide](https://platform.openai.com/docs/guides/fine-tuning) for more details.\n public let hyperparameters: HyperParameters\n /// The base model that is being fine-tuned.\n public let model: String\n /// The object type, which is always \"fine_tuning.job\".\n public let object: String\n /// The organization that owns the fine-tuning job.\n public let organizationId: String\n /// The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the [Files API](https://platform.openai.com/docs/api-reference/files/retrieve-contents).\n public let resultFiles: [String]\n /// The current status of the fine-tuning job, which can be either `validating_files`, `queued`, `running`, `succeeded`, `failed`, or `cancelled`.\n public let status: String\n /// The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running.\n public let trainedTokens: Int?\n \n /// The file ID used for training. You can retrieve the training data with the [Files API](https://platform.openai.com/docs/api-reference/files/retrieve-contents).\n public let trainingFile: String\n /// The file ID used for validation. You can retrieve the validation results with the [Files API](https://platform.openai.com/docs/api-reference/files/retrieve-contents).\n public let validationFile: String?\n \n public enum Status: String {\n case validatingFiles = \"validating_files\"\n case queued\n case running\n case succeeded\n case failed\n case cancelled\n }\n \n public struct HyperParameters: Decodable {\n /// The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset. \"auto\" decides the optimal number of epochs based on the size of the dataset. If setting the number manually, we support any number between 1 and 50 epochs.\n public let nEpochs: IntOrStringValue\n }\n}\n```\n\nUsage\nList fine-tuning jobs\n```swift\nlet fineTuningJobs = try await service.istFineTuningJobs()\n```\nCreate fine-tuning job\n```swift\nlet trainingFileID = \"file-Atc9okK0MOuQwQzDJCZXnrh6\" // The id of the file that has been uploaded using the `Files` API. https://platform.openai.com/docs/api-reference/fine-tuning/create#fine-tuning/create-training_file\nlet parameters = FineTuningJobParameters(model: .gpt35, trainingFile: trainingFileID)\nlet fineTuningJob = try await service.createFineTuningJob(parameters: parameters)\n```\nRetrieve fine-tuning job\n```swift\nlet fineTuningJobID = \"ftjob-abc123\"\nlet fineTuningJob = try await service.retrieveFineTuningJob(id: fineTuningJobID)\n```\nCancel fine-tuning job\n```swift\nlet fineTuningJobID = \"ftjob-abc123\"\nlet canceledFineTuningJob = try await service.cancelFineTuningJobWith(id: fineTuningJobID)\n```\n#### Fine-tuning job event object\nResponse\n```swift\n/// [Fine-tuning job event object](https://platform.openai.com/docs/api-reference/fine-tuning/event-object)\npublic struct FineTuningJobEventObject: Decodable {\n \n public let id: String\n \n public let createdAt: Int\n \n public let level: String\n \n public let message: String\n \n public let object: String\n \n public let type: String?\n \n public let data: Data?\n \n public struct Data: Decodable {\n public let step: Int\n public let trainLoss: Double\n public let trainMeanTokenAccuracy: Double\n }\n}\n```\nUsage\n```swift\nlet fineTuningJobID = \"ftjob-abc123\"\nlet jobEvents = try await service.listFineTuningEventsForJobWith(id: id, after: nil, limit: nil).data\n```\n\n### Batch\nParameters\n```swift\npublic struct BatchParameter: Encodable {\n \n /// The ID of an uploaded file that contains requests for the new batch.\n /// See [upload file](https://platform.openai.com/docs/api-reference/files/create) for how to upload a file.\n /// Your input file must be formatted as a [JSONL file](https://platform.openai.com/docs/api-reference/batch/requestInput), and must be uploaded with the purpose batch.\n let inputFileID: String\n /// The endpoint to be used for all requests in the batch. Currently only /v1/chat/completions is supported.\n let endpoint: String\n /// The time frame within which the batch should be processed. Currently only 24h is supported.\n let completionWindow: String\n /// Optional custom metadata for the batch.\n let metadata: [String: String]?\n \n enum CodingKeys: String, CodingKey {\n case inputFileID = \"input_file_id\"\n case endpoint\n case completionWindow = \"completion_window\"\n case metadata\n }\n}\n```\nResponse\n```swift\npublic struct BatchObject: Decodable {\n \n let id: String\n /// The object type, which is always batch.\n let object: String\n /// The OpenAI API endpoint used by the batch.\n let endpoint: String\n \n let errors: Error\n /// The ID of the input file for the batch.\n let inputFileID: String\n /// The time frame within which the batch should be processed.\n let completionWindow: String\n /// The current status of the batch.\n let status: String\n /// The ID of the file containing the outputs of successfully executed requests.\n let outputFileID: String\n /// The ID of the file containing the outputs of requests with errors.\n let errorFileID: String\n /// The Unix timestamp (in seconds) for when the batch was created.\n let createdAt: Int\n /// The Unix timestamp (in seconds) for when the batch started processing.\n let inProgressAt: Int\n /// The Unix timestamp (in seconds) for when the batch will expire.\n let expiresAt: Int\n /// The Unix timestamp (in seconds) for when the batch started finalizing.\n let finalizingAt: Int\n /// The Unix timestamp (in seconds) for when the batch was completed.\n let completedAt: Int\n /// The Unix timestamp (in seconds) for when the batch failed.\n let failedAt: Int\n /// The Unix timestamp (in seconds) for when the batch expired.\n let expiredAt: Int\n /// The Unix timestamp (in seconds) for when the batch started cancelling.\n let cancellingAt: Int\n /// The Unix timestamp (in seconds) for when the batch was cancelled.\n let cancelledAt: Int\n /// The request counts for different statuses within the batch.\n let requestCounts: RequestCount\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n let metadata: [String: String]\n \n public struct Error: Decodable {\n \n let object: String\n let data: [Data]\n\n public struct Data: Decodable {\n \n /// An error code identifying the error type.\n let code: String\n /// A human-readable message providing more details about the error.\n let message: String\n /// The name of the parameter that caused the error, if applicable.\n let param: String?\n /// The line number of the input file where the error occurred, if applicable.\n let line: Int?\n }\n }\n \n public struct RequestCount: Decodable {\n \n /// Total number of requests in the batch.\n let total: Int\n /// Number of requests that have been completed successfully.\n let completed: Int\n /// Number of requests that have failed.\n let failed: Int\n }\n}\n```\nUsage\n\nCreate batch\n```swift\nlet inputFileID = \"file-abc123\"\nlet endpoint = \"/v1/chat/completions\"\nlet completionWindow = \"24h\"\nlet parameter = BatchParameter(inputFileID: inputFileID, endpoint: endpoint, completionWindow: completionWindow, metadata: nil)\nlet batch = try await service.createBatch(parameters: parameters)\n```\n\nRetrieve batch\n```swift\nlet batchID = \"batch_abc123\"\nlet batch = try await service.retrieveBatch(id: batchID)\n```\n\nCancel batch\n```swift\nlet batchID = \"batch_abc123\"\nlet batch = try await service.cancelBatch(id: batchID)\n```\n\nList batch\n```swift\nlet batches = try await service.listBatch(after: nil, limit: nil)\n```\n\n### Files\nParameters\n```swift\n/// [Upload a file](https://platform.openai.com/docs/api-reference/files/create) that can be used across various endpoints/features. Currently, the size of all the files uploaded by one organization can be up to 1 GB. Please contact us if you need to increase the storage limit.\npublic struct FileParameters: Encodable {\n \n /// The name of the file asset is not documented in OpenAI's official documentation; however, it is essential for constructing the multipart request.\n let fileName: String\n /// The file object (not file name) to be uploaded.\n /// If the purpose is set to \"fine-tune\", the file will be used for fine-tuning.\n let file: Data\n /// The intended purpose of the uploaded file.\n /// Use \"fine-tune\" for [fine-tuning](https://platform.openai.com/docs/api-reference/fine-tuning). This allows us to validate the format of the uploaded file is correct for fine-tuning.\n let purpose: String\n \n public init(\n fileName: String,\n file: Data,\n purpose: String)\n {\n self.fileName = fileName\n self.file = file\n self.purpose = purpose\n }\n}\n```\nResponse\n```swift\n/// The [File object](https://platform.openai.com/docs/api-reference/files/object) represents a document that has been uploaded to OpenAI.\npublic struct FileObject: Decodable {\n \n /// The file identifier, which can be referenced in the API endpoints.\n public let id: String\n /// The size of the file in bytes.\n public let bytes: Int\n /// The Unix timestamp (in seconds) for when the file was created.\n public let createdAt: Int\n /// The name of the file.\n public let filename: String\n /// The object type, which is always \"file\".\n public let object: String\n /// The intended purpose of the file. Currently, only \"fine-tune\" is supported.\n public let purpose: String\n /// The current status of the file, which can be either uploaded, processed, pending, error, deleting or deleted.\n public let status: String\n /// Additional details about the status of the file. If the file is in the error state, this will include a message describing the error.\n public let statusDetails: String?\n \n public enum Status: String {\n case uploaded\n case processed\n case pending\n case error\n case deleting\n case deleted\n }\n\n public init(\n id: String,\n bytes: Int,\n createdAt: Int,\n filename: String,\n object: String,\n purpose: String,\n status: Status,\n statusDetails: String?)\n {\n self.id = id\n self.bytes = bytes\n self.createdAt = createdAt\n self.filename = filename\n self.object = object\n self.purpose = purpose\n self.status = status.rawValue\n self.statusDetails = statusDetails\n }\n}\n```\nUsage\nList files\n```swift\nlet files = try await service.listFiles().data\n```\n### Upload file\n```swift\nlet fileName = \"worldCupData.jsonl\"\nlet data = Data(contentsOfURL:_) // Data retrieved from the file named \"worldCupData.jsonl\".\nlet parameters = FileParameters(fileName: \"WorldCupData\", file: data, purpose: \"fine-tune\") // Important: make sure to provide a file name.\nlet uploadedFile = try await service.uploadFile(parameters: parameters) \n```\nDelete file\n```swift\nlet fileID = \"file-abc123\"\nlet deletedStatus = try await service.deleteFileWith(id: fileID)\n```\nRetrieve file\n```swift\nlet fileID = \"file-abc123\"\nlet retrievedFile = try await service.retrieveFileWith(id: fileID)\n```\nRetrieve file content\n```swift\nlet fileID = \"file-abc123\"\nlet fileContent = try await service.retrieveContentForFileWith(id: fileID)\n```\n\n### Images\n\nThis library supports latest OpenAI Image generation\n\n- Parameters Create\n\n```swift\n/// 'Create Image':\n/// https://platform.openai.com/docs/api-reference/images/create\npublic struct CreateImageParameters: Encodable {\n \n /// A text description of the desired image(s).\n /// The maximum length is 32000 characters for `gpt-image-1`, 1000 characters for `dall-e-2` and 4000 characters for `dall-e-3`.\n public let prompt: String\n \n // MARK: - Optional properties\n \n /// Allows to set transparency for the background of the generated image(s).\n /// This parameter is only supported for `gpt-image-1`.\n /// Must be one of `transparent`, `opaque` or `auto` (default value).\n /// When `auto` is used, the model will automatically determine the best background for the image.\n /// If `transparent`, the output format needs to support transparency, so it should be set to either `png` (default value) or `webp`.\n public let background: Background?\n \n /// The model to use for image generation. One of `dall-e-2`, `dall-e-3`, or `gpt-image-1`.\n /// Defaults to `dall-e-2` unless a parameter specific to `gpt-image-1` is used.\n public let model: Model?\n \n /// Control the content-moderation level for images generated by `gpt-image-1`.\n /// Must be either low for less restrictive filtering or auto (default value).\n public let moderation: Moderation?\n \n /// The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported.\n /// Defaults to `1`\n public let n: Int?\n \n /// The compression level (0-100%) for the generated images.\n /// This parameter is only supported for `gpt-image-1` with the `webp` or `jpeg` output formats, and defaults to 100.\n public let outputCompression: Int?\n \n /// The format in which the generated images are returned.\n /// This parameter is only supported for `gpt-image-1`.\n /// Must be one of `png`, `jpeg`, or `webp`.\n public let outputFormat: OutputFormat?\n \n /// The quality of the image that will be generated.\n /// - `auto` (default value) will automatically select the best quality for the given model.\n /// - `high`, `medium` and `low` are supported for gpt-image-1.\n /// - `hd` and `standard` are supported for dall-e-3.\n /// - `standard` is the only option for dall-e-2.\n public let quality: Quality?\n \n /// The format in which generated images with dall-e-2 and dall-e-3 are returned.\n /// Must be one of `url` or `b64_json`.\n /// URLs are only valid for 60 minutes after the image has been generated.\n /// This parameter isn't supported for `gpt-image-1` which will always return base64-encoded images.\n public let responseFormat: ResponseFormat?\n \n /// The size of the generated images.\n /// - For gpt-image-1, one of `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto` (default value)\n /// - For dall-e-3, one of `1024x1024`, `1792x1024`, or `1024x1792`\n /// - For dall-e-2, one of `256x256`, `512x512`, or `1024x1024`\n public let size: String?\n \n /// The style of the generated images.\n /// This parameter is only supported for `dall-e-3`.\n /// Must be one of `vivid` or `natural`.\n /// Vivid causes the model to lean towards generating hyper-real and dramatic images.\n /// Natural causes the model to produce more natural, less hyper-real looking images.\n public let style: Style?\n \n /// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.\n public let user: String?\n}\n```\n\n- Parameters Edit\n\n```swift\n/// Creates an edited or extended image given one or more source images and a prompt.\n/// This endpoint only supports `gpt-image-1` and `dall-e-2`.\npublic struct CreateImageEditParameters: Encodable {\n \n /// The image(s) to edit.\n /// For `gpt-image-1`, each image should be a `png`, `webp`, or `jpg` file less than 25MB.\n /// For `dall-e-2`, you can only provide one image, and it should be a square `png` file less than 4MB.\n let image: [Data]\n \n /// A text description of the desired image(s).\n /// The maximum length is 1000 characters for `dall-e-2`, and 32000 characters for `gpt-image-1`.\n let prompt: String\n \n /// An additional image whose fully transparent areas indicate where `image` should be edited.\n /// If there are multiple images provided, the mask will be applied on the first image.\n /// Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`.\n let mask: Data?\n \n /// The model to use for image generation. Only `dall-e-2` and `gpt-image-1` are supported.\n /// Defaults to `dall-e-2` unless a parameter specific to `gpt-image-1` is used.\n let model: String?\n \n /// The number of images to generate. Must be between 1 and 10.\n /// Defaults to 1.\n let n: Int?\n \n /// The quality of the image that will be generated.\n /// `high`, `medium` and `low` are only supported for `gpt-image-1`.\n /// `dall-e-2` only supports `standard` quality.\n /// Defaults to `auto`.\n let quality: String?\n \n /// The format in which the generated images are returned.\n /// Must be one of `url` or `b64_json`.\n /// URLs are only valid for 60 minutes after the image has been generated.\n /// This parameter is only supported for `dall-e-2`, as `gpt-image-1` will always return base64-encoded images.\n let responseFormat: String?\n \n /// The size of the generated images.\n /// Must be one of `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto` (default value) for `gpt-image-1`,\n /// and one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`.\n let size: String?\n \n /// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.\n let user: String?\n}\n```\n\n- Parameters Variations\n\n```swift\n/// Creates a variation of a given image.\n/// This endpoint only supports `dall-e-2`.\npublic struct CreateImageVariationParameters: Encodable {\n \n /// The image to use as the basis for the variation(s).\n /// Must be a valid PNG file, less than 4MB, and square.\n let image: Data\n \n /// The model to use for image generation. Only `dall-e-2` is supported at this time.\n /// Defaults to `dall-e-2`.\n let model: String?\n \n /// The number of images to generate. Must be between 1 and 10.\n /// Defaults to 1.\n let n: Int?\n \n /// The format in which the generated images are returned.\n /// Must be one of `url` or `b64_json`.\n /// URLs are only valid for 60 minutes after the image has been generated.\n /// Defaults to `url`.\n let responseFormat: String?\n \n /// The size of the generated images.\n /// Must be one of `256x256`, `512x512`, or `1024x1024`.\n /// Defaults to `1024x1024`.\n let size: String?\n \n /// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.\n let user: String?\n}\n```\n\n- Request example\n\n```swift\nimport SwiftOpenAI\n\nlet service = OpenAIServiceFactory.service(apiKey: \"\")\n\n// ❶ Describe the image you want\nlet prompt = \"A watercolor dragon-unicorn hybrid flying above snowy mountains\"\n\n// ❷ Build parameters with the brand-new types (commit 880a15c)\nlet params = CreateImageParameters(\n prompt: prompt,\n model: .gptImage1, // .dallE3 / .dallE2 also valid\n n: 1, // 1-10 (only 1 for DALL-E 3)\n quality: .high, // .hd / .standard for DALL-E 3\n size: \"1024x1024\" // use \"1792x1024\" or \"1024x1792\" for wide / tall\n)\n\ndo {\n // ❸ Fire the request – returns a `CreateImageResponse`\n let result = try await service.createImages(parameters: params)\n let url = result.data?.first?.url // or `b64Json` for base-64\n print(\"Image URL:\", url ?? \"none\")\n} catch {\n print(\"Generation failed:\", error)\n}\n```\n\nFor a sample app example go to the `Examples/SwiftOpenAIExample` project on this repo.\n\n⚠️ This library Also keeps compatinility with previous Image generation.\n\n\nFor handling image sizes, we utilize the `Dalle` model. An enum with associated values has been defined to represent its size constraints accurately.\n\n [DALL·E](https://platform.openai.com/docs/models/dall-e)\n \n DALL·E is a AI system that can create realistic images and art from a description in natural language. DALL·E 3 currently supports the ability, given a prompt, to create a new image with a specific size. DALL·E 2 also support the ability to edit an existing image, or create variations of a user provided image.\n \n DALL·E 3 is available through our Images API along with DALL·E 2. You can try DALL·E 3 through ChatGPT Plus.\n \n \n | MODEL | DESCRIPTION |\n |-----------|--------------------------------------------------------------|\n | dall-e-3 | DALL·E 3 New |\n | | The latest DALL·E model released in Nov 2023. Learn more. |\n | dall-e-2 | The previous DALL·E model released in Nov 2022. |\n | | The 2nd iteration of DALL·E with more realistic, accurate, |\n | | and 4x greater resolution images than the original model. |\n\npublic enum Dalle {\n \n case dalle2(Dalle2ImageSize)\n case dalle3(Dalle3ImageSize)\n \n public enum Dalle2ImageSize: String {\n case small = \"256x256\"\n case medium = \"512x512\"\n case large = \"1024x1024\"\n }\n \n public enum Dalle3ImageSize: String {\n case largeSquare = \"1024x1024\"\n case landscape = \"1792x1024\"\n case portrait = \"1024x1792\"\n }\n \n var model: String {\n switch self {\n case .dalle2: return Model.dalle2.rawValue\n case .dalle3: return Model.dalle3.rawValue\n }\n }\n \n var size: String {\n switch self {\n case .dalle2(let dalle2ImageSize):\n return dalle2ImageSize.rawValue\n case .dalle3(let dalle3ImageSize):\n return dalle3ImageSize.rawValue\n }\n }\n}\n\n#### Image create\nParameters\n```swift\npublic struct ImageCreateParameters: Encodable {\n \n /// A text description of the desired image(s). The maximum length is 1000 characters for dall-e-2 and 4000 characters for dall-e-3.\n let prompt: String\n /// The model to use for image generation. Defaults to dall-e-2\n let model: String?\n /// The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.\n let n: Int?\n /// The quality of the image that will be generated. hd creates images with finer details and greater consistency across the image. This param is only supported for dall-e-3. Defaults to standard\n let quality: String?\n /// The format in which the generated images are returned. Must be one of url or b64_json. Defaults to url\n let responseFormat: String?\n /// The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024 for dall-e-2. Must be one of 1024x1024, 1792x1024, or 1024x1792 for dall-e-3 models. Defaults to 1024x1024\n let size: String?\n /// The style of the generated images. Must be one of vivid or natural. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. This param is only supported for dall-e-3. Defaults to vivid\n let style: String?\n /// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices)\n let user: String?\n \n public init(\n prompt: String,\n model: Dalle,\n numberOfImages: Int = 1,\n quality: String? = nil,\n responseFormat: ImageResponseFormat? = nil,\n style: String? = nil,\n user: String? = nil)\n {\n self.prompt = prompt\n self.model = model.model\n self.n = numberOfImages\n self.quality = quality\n self.responseFormat = responseFormat?.rawValue\n self.size = model.size\n self.style = style\n self.user = user\n } \n}\n```\n#### Image Edit \nParameters\n```swift\n/// [Creates an edited or extended image given an original image and a prompt.](https://platform.openai.com/docs/api-reference/images/createEdit)\npublic struct ImageEditParameters: Encodable {\n \n /// The image to edit. Must be a valid PNG file, less than 4MB, and square. If mask is not provided, image must have transparency, which will be used as the mask.\n let image: Data\n /// A text description of the desired image(s). The maximum length is 1000 characters.\n let prompt: String\n /// An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where image should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as image.\n let mask: Data?\n /// The model to use for image generation. Only dall-e-2 is supported at this time. Defaults to dall-e-2\n let model: String?\n /// The number of images to generate. Must be between 1 and 10. Defaults to 1\n let n: Int?\n /// The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024. Defaults to 1024x1024\n let size: String?\n /// The format in which the generated images are returned. Must be one of url or b64_json. Defaults to url\n let responseFormat: String?\n /// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices)\n let user: String?\n \n public init(\n image: UIImage,\n model: Dalle? = nil,\n mask: UIImage? = nil,\n prompt: String,\n numberOfImages: Int? = nil,\n responseFormat: ImageResponseFormat? = nil,\n user: String? = nil)\n {\n if (image.pngData() == nil) {\n assertionFailure(\"Failed to get PNG data from image\")\n }\n if let mask, mask.pngData() == nil {\n assertionFailure(\"Failed to get PNG data from mask\")\n }\n if let model, model.model != Model.dalle2.rawValue {\n assertionFailure(\"Only dall-e-2 is supported at this time [https://platform.openai.com/docs/api-reference/images/createEdit]\")\n }\n self.image = image.pngData()!\n self.model = model?.model\n self.mask = mask?.pngData()\n self.prompt = prompt\n self.n = numberOfImages\n self.size = model?.size\n self.responseFormat = responseFormat?.rawValue\n self.user = user\n }\n}\n```\n#### Image variation\nParameters\n```swift\n/// [Creates a variation of a given image.](https://platform.openai.com/docs/api-reference/images/createVariation)\npublic struct ImageVariationParameters: Encodable {\n \n /// The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.\n let image: Data\n /// The model to use for image generation. Only dall-e-2 is supported at this time. Defaults to dall-e-2\n let model: String?\n /// The number of images to generate. Must be between 1 and 10. Defaults to 1\n let n: Int?\n /// The format in which the generated images are returned. Must be one of url or b64_json. Defaults to url\n let responseFormat: String?\n /// The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024. Defaults to 1024x1024\n let size: String?\n /// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices)\n let user: String?\n \n public init(\n image: UIImage,\n model: Dalle? = nil,\n numberOfImages: Int? = nil,\n responseFormat: ImageResponseFormat? = nil,\n user: String? = nil)\n {\n if let model, model.model != Model.dalle2.rawValue {\n assertionFailure(\"Only dall-e-2 is supported at this time [https://platform.openai.com/docs/api-reference/images/createEdit]\")\n }\n self.image = image.pngData()!\n self.n = numberOfImages\n self.model = model?.model\n self.size = model?.size\n self.responseFormat = responseFormat?.rawValue\n self.user = user\n }\n}\n```\nResponse\n```swift\n/// [Represents the url or the content of an image generated by the OpenAI API.](https://platform.openai.com/docs/api-reference/images/object)\npublic struct ImageObject: Decodable {\n /// The URL of the generated image, if response_format is url (default).\n public let url: URL?\n /// The base64-encoded JSON of the generated image, if response_format is b64_json.\n public let b64Json: String?\n /// The prompt that was used to generate the image, if there was any revision to the prompt.\n public let revisedPrompt: String?\n}\n```\n\nUsage\n```swift\n/// Create image\nlet prompt = \"A mix of a dragon and an unicorn\"\nlet createParameters = ImageCreateParameters(prompt: prompt, model: .dalle3(.largeSquare))\nlet imageURLS = try await service.legacyCreateImages(parameters: createParameters).data.map(\\.url)\n```\n```swift\n/// Edit image\nlet data = Data(contentsOfURL:_) // the data from an image.\nlet image = UIImage(data: data)\nlet prompt = \"Add a background filled with pink balloons.\"\nlet editParameters = ImageEditParameters(image: image, prompt: prompt, numberOfImages: 4) \nlet imageURLS = try await service.legacyEditImage(parameters: parameters).data.map(\\.url)\n```\n```swift\n/// Image variations\nlet data = Data(contentsOfURL:_) // the data from an image.\nlet image = UIImage(data: data)\nlet variationParameters = ImageVariationParameters(image: image, numberOfImages: 4)\nlet imageURLS = try await service.legacyCreateImageVariations(parameters: parameters).data.map(\\.url)\n```\n\n### Models\nResponse\n```swift\n\n/// Describes an OpenAI [model](https://platform.openai.com/docs/api-reference/models/object) offering that can be used with the API.\npublic struct ModelObject: Decodable {\n \n /// The model identifier, which can be referenced in the API endpoints.\n public let id: String\n /// The Unix timestamp (in seconds) when the model was created.\n public let created: Int\n /// The object type, which is always \"model\".\n public let object: String\n /// The organization that owns the model.\n public let ownedBy: String\n /// An array representing the current permissions of a model. Each element in the array corresponds to a specific permission setting. If there are no permissions or if the data is unavailable, the array may be nil.\n public let permission: [Permission]?\n \n public struct Permission: Decodable {\n public let id: String?\n public let object: String?\n public let created: Int?\n public let allowCreateEngine: Bool?\n public let allowSampling: Bool?\n public let allowLogprobs: Bool?\n public let allowSearchIndices: Bool?\n public let allowView: Bool?\n public let allowFineTuning: Bool?\n public let organization: String?\n public let group: String?\n public let isBlocking: Bool?\n }\n \n /// Represents the response from the [delete](https://platform.openai.com/docs/api-reference/models/delete) fine-tuning API\n public struct DeletionStatus: Decodable {\n \n public let id: String\n public let object: String\n public let deleted: Bool\n }\n}\n```\nUsage\n```swift\n/// List models\nlet models = try await service.listModels().data\n```\n```swift\n/// Retrieve model\nlet modelID = \"gpt-3.5-turbo-instruct\"\nlet retrievedModel = try await service.retrieveModelWith(id: modelID)\n```\n```swift\n/// Delete fine tuned model\nlet modelID = \"fine-tune-model-id\"\nlet deletionStatus = try await service.deleteFineTuneModelWith(id: modelID)\n```\n### Moderations\nParameters\n```swift\n/// [Classifies if text violates OpenAI's Content Policy.](https://platform.openai.com/docs/api-reference/moderations/create)\npublic struct ModerationParameter: Encodable {\n \n /// The input text to classify, string or array.\n let input: Input\n /// Two content moderations models are available: text-moderation-stable and text-moderation-latest.\n /// The default is text-moderation-latest which will be automatically upgraded over time. This ensures you are always using our most accurate model. If you use text-moderation-stable, we will provide advanced notice before updating the model. Accuracy of text-moderation-stable may be slightly lower than for text-moderation-latest.\n let model: String?\n \n enum Model: String {\n case stable = \"text-moderation-stable\"\n case latest = \"text-moderation-latest\"\n }\n \n init(\n input: Input,\n model: Model? = nil)\n {\n self.input = input\n self.model = model?.rawValue\n }\n}\n```\nResponse\n```swift\n/// The [moderation object](https://platform.openai.com/docs/api-reference/moderations/object). Represents policy compliance report by OpenAI's content moderation model against a given input.\npublic struct ModerationObject: Decodable {\n \n /// The unique identifier for the moderation request.\n public let id: String\n /// The model used to generate the moderation results.\n public let model: String\n /// A list of moderation objects.\n public let results: [Moderation]\n \n public struct Moderation: Decodable {\n \n /// Whether the content violates OpenAI's usage policies.\n public let flagged: Bool\n /// A list of the categories, and whether they are flagged or not.\n public let categories: Category\n /// A list of the categories along with their scores as predicted by model.\n public let categoryScores: Category\n \n public struct Category: Decodable {\n \n /// Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harrassment.\n public let hate: T\n /// Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.\n public let hateThreatening: T\n /// Content that expresses, incites, or promotes harassing language towards any target.\n public let harassment: T\n /// Harassment content that also includes violence or serious harm towards any target.\n public let harassmentThreatening: T\n /// Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.\n public let selfHarm: T\n /// Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders.\n public let selfHarmIntent: T\n /// Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts.\n public let selfHarmInstructions: T\n /// Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).\n public let sexual: T\n /// Sexual content that includes an individual who is under 18 years old.\n public let sexualMinors: T\n /// Content that depicts death, violence, or physical injury.\n public let violence: T\n /// Content that depicts death, violence, or physical injury in graphic detail.\n public let violenceGraphic: T\n }\n }\n}\n```\nUsage\n```swift\n/// Single prompt\nlet prompt = \"I am going to kill him\"\nlet parameters = ModerationParameter(input: prompt)\nlet isFlagged = try await service.createModerationFromText(parameters: parameters)\n```\n```swift\n/// Multiple prompts\nlet prompts = [\"I am going to kill him\", \"I am going to die\"]\nlet parameters = ModerationParameter(input: prompts)\nlet isFlagged = try await service.createModerationFromTexts(parameters: parameters)\n```\n\n### **BETA**\n### Assistants\nParameters\n```swift\n/// Create an [assistant](https://platform.openai.com/docs/api-reference/assistants/createAssistant) with a model and instructions.\n/// Modifies an [assistant](https://platform.openai.com/docs/api-reference/assistants/modifyAssistant).\npublic struct AssistantParameters: Encodable {\n \n /// ID of the model to use. You can use the [List models](https://platform.openai.com/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](https://platform.openai.com/docs/models/overview) for descriptions of them.\n public var model: String?\n /// The name of the assistant. The maximum length is 256 characters.\n public var name: String?\n /// The description of the assistant. The maximum length is 512 characters.\n public var description: String?\n /// The system instructions that the assistant uses. The maximum length is 32768 characters.\n public var instructions: String?\n /// A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, retrieval, or function. Defaults to []\n public var tools: [AssistantObject.Tool] = []\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n public var metadata: [String: String]?\n /// What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n /// Defaults to 1\n public var temperature: Double?\n /// An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n /// We generally recommend altering this or temperature but not both.\n /// Defaults to 1\n public var topP: Double?\n /// Specifies the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.\n /// Setting to { \"type\": \"json_object\" } enables JSON mode, which guarantees the message the model generates is valid JSON.\n /// Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly \"stuck\" request. Also note that the message content may be partially cut off if finish_reason=\"length\", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.\n /// Defaults to `auto`\n public var responseFormat: ResponseFormat?\n \n public enum Action {\n case create(model: String) // model is required on creation of assistant.\n case modify(model: String?) // model is optional on modification of assistant.\n \n var model: String? {\n switch self {\n case .create(let model): return model\n case .modify(let model): return model\n }\n }\n }\n}\n```\nResponse\n```swift\n/// Represents an [assistant](https://platform.openai.com/docs/api-reference/assistants) that can call the model and use tools.\npublic struct AssistantObject: Decodable {\n \n /// The identifier, which can be referenced in API endpoints.\n public let id: String\n /// The object type, which is always \"assistant\".\n public let object: String\n /// The Unix timestamp (in seconds) for when the assistant was created.\n public let createdAt: Int\n /// The name of the assistant. The maximum length is 256 characters.\n public let name: String?\n /// The description of the assistant. The maximum length is 512 characters.\n public let description: String?\n /// ID of the model to use. You can use the [List models](https://platform.openai.com/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](https://platform.openai.com/docs/models/overview) for descriptions of them.\n public let model: String\n /// The system instructions that the assistant uses. The maximum length is 32768 characters.\n public let instructions: String?\n /// A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, retrieval, or function.\n public let tools: [Tool]\n /// A list of [file](https://platform.openai.com/docs/api-reference/files) IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order.\n /// A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.\n public let toolResources: ToolResources?\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n public let metadata: [String: String]?\n /// What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n /// Defaults to 1\n public var temperature: Double?\n /// An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n /// We generally recommend altering this or temperature but not both.\n /// Defaults to 1\n public var topP: Double?\n /// Specifies the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.\n /// Setting to { \"type\": \"json_object\" } enables JSON mode, which guarantees the message the model generates is valid JSON.\n /// Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly \"stuck\" request. Also note that the message content may be partially cut off if finish_reason=\"length\", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.\n /// Defaults to `auto`\n public var responseFormat: ResponseFormat?\n\n public struct Tool: Codable {\n \n /// The type of tool being defined.\n public let type: String\n public let function: ChatCompletionParameters.ChatFunction?\n \n public enum ToolType: String, CaseIterable {\n case codeInterpreter = \"code_interpreter\"\n case fileSearch = \"file_search\"\n case function\n }\n \n /// Helper.\n public var displayToolType: ToolType? { .init(rawValue: type) }\n \n public init(\n type: ToolType,\n function: ChatCompletionParameters.ChatFunction? = nil)\n {\n self.type = type.rawValue\n self.function = function\n }\n }\n \n public struct DeletionStatus: Decodable {\n public let id: String\n public let object: String\n public let deleted: Bool\n }\n}\n```\n\nUsage\n\nCreate Assistant\n```swift\nlet parameters = AssistantParameters(action: .create(model: Model.gpt41106Preview.rawValue), name: \"Math tutor\")\nlet assistant = try await service.createAssistant(parameters: parameters)\n```\nRetrieve Assistant\n```swift\nlet assistantID = \"asst_abc123\"\nlet assistant = try await service.retrieveAssistant(id: assistantID)\n```\nModify Assistant\n```swift\nlet assistantID = \"asst_abc123\"\nlet parameters = AssistantParameters(action: .modify, name: \"Math tutor for kids\")\nlet assistant = try await service.modifyAssistant(id: assistantID, parameters: parameters)\n```\nDelete Assistant\n```swift\nlet assistantID = \"asst_abc123\"\nlet deletionStatus = try await service.deleteAssistant(id: assistantID)\n```\nList Assistants\n```swift\nlet assistants = try await service.listAssistants()\n```\n\n### Threads\nParameters\n```swift\n/// Create a [Thread](https://platform.openai.com/docs/api-reference/threads/createThread)\npublic struct CreateThreadParameters: Encodable {\n \n /// A list of [messages](https://platform.openai.com/docs/api-reference/messages) to start the thread with.\n public var messages: [MessageObject]?\n /// A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.\n public var toolResources: ToolResources?\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n public var metadata: [String: String]?\n}\n```\nResponse\n```swift\n/// A [thread object](https://platform.openai.com/docs/api-reference/threads) represents a thread that contains [messages](https://platform.openai.com/docs/api-reference/messages).\npublic struct ThreadObject: Decodable {\n \n /// The identifier, which can be referenced in API endpoints.\n public let id: String\n /// The object type, which is always thread.\n public let object: String\n /// The Unix timestamp (in seconds) for when the thread was created.\n public let createdAt: Int\n /// A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.\n public var toolResources: ToolResources?\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n public let metadata: [String: String]\n \n}\n```\n\nUsage\n\nCreate thread.\n```swift\nlet parameters = CreateThreadParameters()\nlet thread = try await service.createThread(parameters: parameters)\n```\nRetrieve thread.\n```swift\nlet threadID = \"thread_abc123\"\nlet thread = try await service.retrieveThread(id: id)\n```\nModify thread.\n```swift\nlet threadID = \"thread_abc123\"\nlet paramaters = CreateThreadParameters(metadata: [\"modified\": \"true\", \"user\": \"abc123\"]\nlet thread = try await service.modifyThread(id: id, parameters: parameters)\n```\nDelete thread.\n```swift\nlet threadID = \"thread_abc123\"\nlet thread = try await service.deleteThread(id: id)\n```\n\n### Messages\nParameters\n[Create a Message](https://platform.openai.com/docs/api-reference/messages/createMessage))\n```swift\npublic struct MessageParameter: Encodable {\n \n /// The role of the entity that is creating the message. Allowed values include:\n /// user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages.\n /// assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation.\n let role: String\n /// The content of the message, which can be a string or an array of content parts (text, image URL, image file).\n let content: Content\n /// A list of files attached to the message, and the tools they should be added to.\n let attachments: [MessageAttachment]?\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n let metadata: [String: String]?\n}\n```\n[Modify a Message](https://platform.openai.com/docs/api-reference/messages/modifyMessage))\n```swift\npublic struct ModifyMessageParameters: Encodable {\n \n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n public var metadata: [String: String]\n}\n```\nResponse\n```swift\n/// Represents a [message](https://platform.openai.com/docs/api-reference/messages) within a [thread](https://platform.openai.com/docs/api-reference/threads).\npublic struct MessageObject: Codable {\n \n /// The identifier, which can be referenced in API endpoints.\n public let id: String\n /// The object type, which is always thread.message.\n public let object: String\n /// The Unix timestamp (in seconds) for when the message was created.\n public let createdAt: Int\n /// The [thread](https://platform.openai.com/docs/api-reference/threads) ID that this message belongs to.\n public let threadID: String\n /// The status of the message, which can be either in_progress, incomplete, or completed.\n public let status: String\n /// On an incomplete message, details about why the message is incomplete.\n public let incompleteDetails: IncompleteDetails?\n /// The Unix timestamp (in seconds) for when the message was completed.\n public let completedAt: Int\n /// The entity that produced the message. One of user or assistant.\n public let role: String\n /// The content of the message in array of text and/or images.\n public let content: [MessageContent]\n /// If applicable, the ID of the [assistant](https://platform.openai.com/docs/api-reference/assistants) that authored this message.\n public let assistantID: String?\n /// If applicable, the ID of the [run](https://platform.openai.com/docs/api-reference/runs) associated with the authoring of this message.\n public let runID: String?\n /// A list of files attached to the message, and the tools they were added to.\n public let attachments: [MessageAttachment]?\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n public let metadata: [String: String]?\n \n enum Role: String {\n case user\n case assistant\n }\n}\n\n// MARK: MessageContent\n\npublic enum MessageContent: Codable {\n \n case imageFile(ImageFile)\n case text(Text)\n}\n\n// MARK: Image File\n\npublic struct ImageFile: Codable {\n /// Always image_file.\n public let type: String\n \n /// References an image [File](https://platform.openai.com/docs/api-reference/files) in the content of a message.\n public let imageFile: ImageFileContent\n \n public struct ImageFileContent: Codable {\n \n /// The [File](https://platform.openai.com/docs/api-reference/files) ID of the image in the message content.\n public let fileID: String\n }\n}\n\n// MARK: Text\n\npublic struct Text: Codable {\n \n /// Always text.\n public let type: String\n /// The text content that is part of a message.\n public let text: TextContent\n \n public struct TextContent: Codable {\n // The data that makes up the text.\n public let value: String\n \n public let annotations: [Annotation]\n }\n}\n\n// MARK: Annotation\n\npublic enum Annotation: Codable {\n \n case fileCitation(FileCitation)\n case filePath(FilePath)\n}\n\n// MARK: FileCitation\n\n/// A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the \"retrieval\" tool to search files.\npublic struct FileCitation: Codable {\n \n /// Always file_citation.\n public let type: String\n /// The text in the message content that needs to be replaced.\n public let text: String\n public let fileCitation: FileCitation\n public let startIndex: Int\n public let endIndex: Int\n \n public struct FileCitation: Codable {\n \n /// The ID of the specific File the citation is from.\n public let fileID: String\n /// The specific quote in the file.\n public let quote: String\n\n }\n}\n\n// MARK: FilePath\n\n/// A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.\npublic struct FilePath: Codable {\n \n /// Always file_path\n public let type: String\n /// The text in the message content that needs to be replaced.\n public let text: String\n public let filePath: FilePath\n public let startIndex: Int\n public let endIndex: Int\n \n public struct FilePath: Codable {\n /// The ID of the file that was generated.\n public let fileID: String\n }\n}\n```\n\nUsage\n\nCreate Message.\n```swift\nlet threadID = \"thread_abc123\"\nlet prompt = \"Give me some ideas for a birthday party.\"\nlet parameters = MessageParameter(role: \"user\", content: .stringContent(prompt)\")\nlet message = try await service.createMessage(threadID: threadID, parameters: parameters)\n```\n\nRetrieve Message.\n```swift\nlet threadID = \"thread_abc123\"\nlet messageID = \"msg_abc123\"\nlet message = try await service.retrieveMessage(threadID: threadID, messageID: messageID)\n```\n\nModify Message.\n```swift\nlet threadID = \"thread_abc123\"\nlet messageID = \"msg_abc123\"\nlet parameters = ModifyMessageParameters(metadata: [\"modified\": \"true\", \"user\": \"abc123\"]\nlet message = try await service.modifyMessage(threadID: threadID, messageID: messageID, parameters: parameters)\n```\n\nList Messages\n```swift\nlet threadID = \"thread_abc123\"\nlet messages = try await service.listMessages(threadID: threadID, limit: nil, order: nil, after: nil, before: nil) \n```\n\n### Runs\nParameters\n\n[Create a run](https://platform.openai.com/docs/api-reference/runs/createRun)\n```swift\npublic struct RunParameter: Encodable {\n \n /// The ID of the [assistant](https://platform.openai.com/docs/api-reference/assistants) to use to execute this run.\n let assistantID: String\n /// The ID of the [Model](https://platform.openai.com/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.\n let model: String?\n /// Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.\n let instructions: String?\n /// Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.\n let additionalInstructions: String?\n /// Adds additional messages to the thread before creating the run.\n let additionalMessages: [MessageParameter]?\n /// Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.\n let tools: [AssistantObject.Tool]?\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n let metadata: [String: String]?\n /// What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n /// Optional Defaults to 1\n let temperature: Double?\n /// If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.\n var stream: Bool\n /// The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status complete. See incomplete_details for more info.\n let maxPromptTokens: Int?\n /// The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status complete. See incomplete_details for more info.\n let maxCompletionTokens: Int?\n /// Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run.\n let truncationStrategy: TruncationStrategy?\n /// Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling a tool. Specifying a particular tool like {\"type\": \"file_search\"} or {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool.\n let toolChoice: ToolChoice?\n /// Specifies the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models newer than gpt-3.5-turbo-1106.\n /// Setting to { \"type\": \"json_object\" } enables JSON mode, which guarantees the message the model generates is valid JSON.\n /// Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly \"stuck\" request. Also note that the message content may be partially cut off if finish_reason=\"length\", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.\n let responseFormat: ResponseFormat?\n}\n```\n[Modify a Run](https://platform.openai.com/docs/api-reference/runs/modifyRun)\n```swift\npublic struct ModifyRunParameters: Encodable {\n \n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n public var metadata: [String: String]\n \n public init(\n metadata: [String : String])\n {\n self.metadata = metadata\n }\n}\n```\n[Creates a Thread and Runs.](https://platform.openai.com/docs/api-reference/runs/createThreadAndRun)\n```swift\npublic struct CreateThreadAndRunParameter: Encodable {\n \n /// The ID of the [assistant](https://platform.openai.com/docs/api-reference/assistants) to use to execute this run.\n let assistantId: String\n /// A thread to create.\n let thread: CreateThreadParameters?\n /// The ID of the [Model](https://platform.openai.com/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.\n let model: String?\n /// Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.\n let instructions: String?\n /// Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.\n let tools: [AssistantObject.Tool]?\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n let metadata: [String: String]?\n /// What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n /// Defaults to 1\n let temperature: Double?\n /// An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n /// We generally recommend altering this or temperature but not both.\n let topP: Double?\n /// If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.\n var stream: Bool = false\n /// The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.\n let maxPromptTokens: Int?\n /// The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status complete. See incomplete_details for more info.\n let maxCompletionTokens: Int?\n /// Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run.\n let truncationStrategy: TruncationStrategy?\n /// Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling a tool. Specifying a particular tool like {\"type\": \"file_search\"} or {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool.\n let toolChoice: ToolChoice?\n /// Specifies the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models newer than gpt-3.5-turbo-1106.\n /// Setting to { \"type\": \"json_object\" } enables JSON mode, which guarantees the message the model generates is valid JSON.\n /// Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly \"stuck\" request. Also note that the message content may be partially cut off if finish_reason=\"length\", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.\n let responseFormat: ResponseFormat?\n}\n```\n[Submit tool outputs to run](https://platform.openai.com/docs/api-reference/runs/submitToolOutputs)\n```swift\npublic struct RunToolsOutputParameter: Encodable {\n \n /// A list of tools for which the outputs are being submitted.\n public let toolOutputs: [ToolOutput]\n /// If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.\n public let stream: Bool\n}\n```\n \nResponse\n```swift\npublic struct RunObject: Decodable {\n \n /// The identifier, which can be referenced in API endpoints.\n public let id: String\n /// The object type, which is always thread.run.\n public let object: String\n /// The Unix timestamp (in seconds) for when the run was created.\n public let createdAt: Int?\n /// The ID of the [thread](https://platform.openai.com/docs/api-reference/threads) that was executed on as a part of this run.\n public let threadID: String\n /// The ID of the [assistant](https://platform.openai.com/docs/api-reference/assistants) used for execution of this run.\n public let assistantID: String\n /// The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, or expired.\n public let status: String\n /// Details on the action required to continue the run. Will be null if no action is required.\n public let requiredAction: RequiredAction?\n /// The last error associated with this run. Will be null if there are no errors.\n public let lastError: LastError?\n /// The Unix timestamp (in seconds) for when the run will expire.\n public let expiresAt: Int?\n /// The Unix timestamp (in seconds) for when the run was started.\n public let startedAt: Int?\n /// The Unix timestamp (in seconds) for when the run was cancelled.\n public let cancelledAt: Int?\n /// The Unix timestamp (in seconds) for when the run failed.\n public let failedAt: Int?\n /// The Unix timestamp (in seconds) for when the run was completed.\n public let completedAt: Int?\n /// Details on why the run is incomplete. Will be null if the run is not incomplete.\n public let incompleteDetails: IncompleteDetails?\n /// The model that the [assistant](https://platform.openai.com/docs/api-reference/assistants) used for this run.\n public let model: String\n /// The instructions that the [assistant](https://platform.openai.com/docs/api-reference/assistants) used for this run.\n public let instructions: String?\n /// The list of tools that the [assistant](https://platform.openai.com/docs/api-reference/assistants) used for this run.\n public let tools: [AssistantObject.Tool]\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n public let metadata: [String: String]\n /// Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).\n public let usage: Usage?\n /// The sampling temperature used for this run. If not set, defaults to 1.\n public let temperature: Double?\n /// The nucleus sampling value used for this run. If not set, defaults to 1.\n public let topP: Double?\n /// The maximum number of prompt tokens specified to have been used over the course of the run.\n public let maxPromptTokens: Int?\n /// The maximum number of completion tokens specified to have been used over the course of the run.\n public let maxCompletionTokens: Int?\n /// Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run.\n public let truncationStrategy: TruncationStrategy?\n /// Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling a tool. Specifying a particular tool like {\"type\": \"TOOL_TYPE\"} or {\"type\": \"function\", \"function\": {\"name\": \"my_function\"}} forces the model to call that tool.\n public let toolChoice: ToolChoice?\n /// Specifies the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models newer than gpt-3.5-turbo-1106.\n /// Setting to { \"type\": \"json_object\" } enables JSON mode, which guarantees the message the model generates is valid JSON.\n /// Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly \"stuck\" request. Also note that the message content may be partially cut off if finish_reason=\"length\", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.\n public let responseFormat: ResponseFormat?\n}\n```\nUsage\n\nCreate a Run\n```swift\nlet assistantID = \"asst_abc123\"\nlet parameters = RunParameter(assistantID: assistantID)\nlet run = try await service.createRun(threadID: threadID, parameters: parameters)\n```\nRetrieve a Run\n```swift\nlet threadID = \"thread_abc123\"\nlet runID = \"run_abc123\"\nlet run = try await service.retrieveRun(threadID: threadID, runID: runID)\n```\nModify a Run\n```swift\nlet threadID = \"thread_abc123\"\nlet runID = \"run_abc123\"\nlet parameters = ModifyRunParameters(metadata: [\"modified\": \"true\", \"user\": \"abc123\"]\nlet message = try await service.modifyRun(threadID: threadID, messageID: messageID, parameters: parameters)\n```\nList runs\n```swift\nlet threadID = \"thread_abc123\"\nlet runs = try await service.listRuns(threadID: threadID, limit: nil, order: nil, after: nil, before: nil) \n```\nSubmit tool outputs to Run\n```swift\nlet threadID = \"thread_abc123\"\nlet runID = \"run_abc123\"\nlet toolCallID = \"call_abc123\"\nlet output = \"28C\"\nlet parameters = RunToolsOutputParameter(toolOutputs: [.init(toolCallId: toolCallID, output: output)])\nlet run = try await service.submitToolOutputsToRun(threadID: threadID\", runID: runID\", parameters: parameters)\n```\nCancel a Run\n```swift\n/// Cancels a run that is in_progress.\nlet threadID = \"thread_abc123\"\nlet runID = \"run_abc123\"\nlet run = try await service.cancelRun(threadID: threadID, runID: runID)\n```\nCreate thread and Run\n```swift\nlet assistantID = \"asst_abc123\"\nlet parameters = CreateThreadAndRunParameter(assistantID: assistantID)\nlet run = service.createThreadAndRun(parameters: parameters)\n```\n\n### Run Step Object\nRepresents a [step](https://platform.openai.com/docs/api-reference/runs/step-object) in execution of a run.\nResponse\n```swift\npublic struct RunStepObject: Decodable {\n \n /// The identifier of the run step, which can be referenced in API endpoints.\n public let id: String\n /// The object type, which is always `thread.run.step``.\n public let object: String\n /// The Unix timestamp (in seconds) for when the run step was created.\n public let createdAt: Int\n /// The ID of the [assistant](https://platform.openai.com/docs/api-reference/assistants) associated with the run step.\n public let assistantId: String\n /// The ID of the [thread](https://platform.openai.com/docs/api-reference/threads) that was run.\n public let threadId: String\n ///The ID of the [run](https://platform.openai.com/docs/api-reference/runs) that this run step is a part of.\n public let runId: String\n /// The type of run step, which can be either message_creation or tool_calls.\n public let type: String\n /// The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.\n public let status: String\n /// The details of the run step.\n public let stepDetails: RunStepDetails\n /// The last error associated with this run step. Will be null if there are no errors.\n public let lastError: RunObject.LastError?\n /// The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.\n public let expiredAt: Int?\n /// The Unix timestamp (in seconds) for when the run step was cancelled.\n public let cancelledAt: Int?\n /// The Unix timestamp (in seconds) for when the run step failed.\n public let failedAt: Int?\n /// The Unix timestamp (in seconds) for when the run step completed.\n public let completedAt: Int?\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n public let metadata: [String: String]?\n /// Usage statistics related to the run step. This value will be null while the run step's status is in_progress.\n public let usage: Usage?\n}\n```\nUsage\nRetrieve a Run step\n```swift\nlet threadID = \"thread_abc123\"\nlet runID = \"run_abc123\"\nlet stepID = \"step_abc123\"\nlet runStep = try await service.retrieveRunstep(threadID: threadID, runID: runID, stepID: stepID)\n```\nList run steps\n```swift\nlet threadID = \"thread_abc123\"\nlet runID = \"run_abc123\"\nlet runSteps = try await service.listRunSteps(threadID: threadID, runID: runID, limit: nil, order: nil, after: nil, before: nil) \n```\n\n### Run Step Detail\n\nThe details of the run step.\n\n```swift\npublic struct RunStepDetails: Codable {\n \n /// `message_creation` or `tool_calls`\n public let type: String\n /// Details of the message creation by the run step.\n public let messageCreation: MessageCreation?\n /// Details of the tool call.\n public let toolCalls: [ToolCall]?\n}\n```\n\n### Assistants Streaming\n\nAssistants API [streaming.](https://platform.openai.com/docs/api-reference/assistants-streaming)\n\nStream the result of executing a Run or resuming a Run after submitting tool outputs.\n\nYou can stream events from the [Create Thread and Run](https://platform.openai.com/docs/api-reference/runs/createThreadAndRun), [Create Run](https://platform.openai.com/docs/api-reference/runs/createRun), and [Submit Tool Outputs](https://platform.openai.com/docs/api-reference/runs/submitToolOutputs) endpoints by passing \"stream\": true. The response will be a Server-Sent events stream.\n\nOpenAI Python tutorial(https://platform.openai.com/docs/assistants/overview?context=with-streaming))\n\n### Message Delta Object\n\n[MessageDeltaObject](https://platform.openai.com/docs/api-reference/assistants-streaming/message-delta-object) Represents a message delta i.e. any changed fields on a message during streaming.\n\n```swift\npublic struct MessageDeltaObject: Decodable {\n \n /// The identifier of the message, which can be referenced in API endpoints.\n public let id: String\n /// The object type, which is always thread.message.delta.\n public let object: String\n /// The delta containing the fields that have changed on the Message.\n public let delta: Delta\n \n public struct Delta: Decodable {\n \n /// The entity that produced the message. One of user or assistant.\n public let role: String\n /// The content of the message in array of text and/or images.\n public let content: [MessageContent]\n }\n}\n```\n\n### Run Step Delta Object\n\nRepresents a [run step delta](https://platform.openai.com/docs/api-reference/assistants-streaming/run-step-delta-object) i.e. any changed fields on a run step during streaming.\n\n```swift\npublic struct RunStepDeltaObject: Decodable {\n \n /// The identifier of the run step, which can be referenced in API endpoints.\n public let id: String\n /// The object type, which is always thread.run.step.delta.\n public let object: String\n /// The delta containing the fields that have changed on the run step.\n public let delta: Delta\n \n public struct Delta: Decodable {\n \n /// The details of the run step.\n public let stepDetails: RunStepDetails\n \n private enum CodingKeys: String, CodingKey {\n case stepDetails = \"step_details\"\n }\n }\n}\n```\n\n⚠️ To utilize the `createRunAndStreamMessage`, first create an assistant and initiate a thread.\n\nUsage\n[Create Run](https://platform.openai.com/docs/api-reference/runs/createRun) with stream.\n\nThe `createRunAndStreamMessage` streams [events](https://platform.openai.com/docs/api-reference/assistants-streaming/events), You can decide which one you need for your implementation. For example, this is how you can access message delta and run step delta objects\n\n```swift\nlet assistantID = \"asst_abc123\"\nlet threadID = \"thread_abc123\"\nlet messageParameter = MessageParameter(role: .user, content: \"Tell me the square root of 1235\")\nlet message = try await service.createMessage(threadID: threadID, parameters: messageParameter)\nlet runParameters = RunParameter(assistantID: assistantID)\nlet stream = try await service.createRunAndStreamMessage(threadID: threadID, parameters: runParameters)\n\n for try await result in stream {\n switch result {\n case .threadMessageDelta(let messageDelta):\n let content = messageDelta.delta.content.first\n switch content {\n case .imageFile, nil:\n break\n case .text(let textContent):\n print(textContent.text.value) // this will print the streamed response for a message.\n }\n \n case .threadRunStepDelta(let runStepDelta):\n if let toolCall = runStepDelta.delta.stepDetails.toolCalls?.first?.toolCall {\n switch toolCall {\n case .codeInterpreterToolCall(let toolCall):\n print(toolCall.input ?? \"\") // this will print the streamed response for code interpreter tool call.\n case .fileSearchToolCall(let toolCall):\n print(\"File search tool call\")\n case .functionToolCall(let toolCall):\n print(\"Function tool call\")\n case nil:\n break\n }\n }\n }\n }\n```\n\nYou can go to the [Examples folder](https://github.com/jamesrochabrun/SwiftOpenAI/tree/main/Examples/SwiftOpenAIExample/SwiftOpenAIExample) in this package, navigate to the 'Configure Assistants' tab, create an assistant, and follow the subsequent steps.\n\n### Stream support has also been added to:\n\n[Create Thread and Run](https://platform.openai.com/docs/api-reference/runs/createThreadAndRun):\n\n```swift\n /// Creates a thread and run with stream enabled.\n ///\n /// - Parameter parameters: The parameters needed to create a thread and run.\n /// - Returns: An AsyncThrowingStream of [AssistantStreamEvent](https://platform.openai.com/docs/api-reference/assistants-streaming/events) objects.\n /// - Throws: An error if the request fails.\n ///\n /// For more information, refer to [OpenAI's Run API documentation](https://platform.openai.com/docs/api-reference/runs/createThreadAndRun).\n func createThreadAndRunStream(\n parameters: CreateThreadAndRunParameter)\n async throws -> AsyncThrowingStream\n```\n\n[Submit Tool Outputs](https://platform.openai.com/docs/api-reference/runs/submitToolOutputs):\n\n```swift\n /// When a run has the status: \"requires_action\" and required_action.type is submit_tool_outputs, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request. Stream enabled\n ///\n /// - Parameter threadID: The ID of the [thread](https://platform.openai.com/docs/api-reference/threads) to which this run belongs.\n /// - Parameter runID: The ID of the run that requires the tool output submission.\n /// - Parameter parameters: The parameters needed for the run tools output.\n /// - Returns: An AsyncThrowingStream of [AssistantStreamEvent](https://platform.openai.com/docs/api-reference/assistants-streaming/events) objects.\n /// - Throws: An error if the request fails.\n ///\n /// For more information, refer to [OpenAI's Run API documentation](https://platform.openai.com/docs/api-reference/runs/submitToolOutputs).\n func submitToolOutputsToRunStream(\n threadID: String,\n runID: String,\n parameters: RunToolsOutputParameter)\n async throws -> AsyncThrowingStream\n```\n\n### Vector Stores\nParameters\n```swift\npublic struct VectorStoreParameter: Encodable {\n \n /// A list of [File](https://platform.openai.com/docs/api-reference/files) IDs that the vector store should use. Useful for tools like file_search that can access files.\n let fileIDS: [String]?\n /// The name of the vector store.\n let name: String?\n /// The expiration policy for a vector store.\n let expiresAfter: ExpirationPolicy?\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n let metadata: [String: String]?\n}\n```\nResponse\n```swift\npublic struct VectorStoreObject: Decodable {\n \n /// The identifier, which can be referenced in API endpoints.\n let id: String\n /// The object type, which is always vector_store.\n let object: String\n /// The Unix timestamp (in seconds) for when the vector store was created.\n let createdAt: Int\n /// The name of the vector store.\n let name: String\n /// The total number of bytes used by the files in the vector store.\n let usageBytes: Int\n \n let fileCounts: FileCount\n /// The status of the vector store, which can be either expired, in_progress, or completed. A status of completed indicates that the vector store is ready for use.\n let status: String\n /// The expiration policy for a vector store.\n let expiresAfter: ExpirationPolicy?\n /// The Unix timestamp (in seconds) for when the vector store will expire.\n let expiresAt: Int?\n /// The Unix timestamp (in seconds) for when the vector store was last active.\n let lastActiveAt: Int?\n /// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.\n let metadata: [String: String]\n \n public struct FileCount: Decodable {\n \n /// The number of files that are currently being processed.\n let inProgress: Int\n /// The number of files that have been successfully processed.\n let completed: Int\n /// The number of files that have failed to process.\n let failed: Int\n /// The number of files that were cancelled.\n let cancelled: Int\n /// The total number of files.\n let total: Int\n }\n}\n```\nUsage\n[Create vector Store](https://platform.openai.com/docs/api-reference/vector-stores/create)\n```swift\nlet name = \"Support FAQ\"\nlet parameters = VectorStoreParameter(name: name)\ntry vectorStore = try await service.createVectorStore(parameters: parameters)\n```\n\n[List Vector stores](https://platform.openai.com/docs/api-reference/vector-stores/list)\n```swift\nlet vectorStores = try await service.listVectorStores(limit: nil, order: nil, after: nil, before: nil)\n```\n\n[Retrieve Vector store](https://platform.openai.com/docs/api-reference/vector-stores/retrieve)\n```swift\nlet vectorStoreID = \"vs_abc123\"\nlet vectorStore = try await service.retrieveVectorStore(id: vectorStoreID)\n```\n\n[Modify Vector store](https://platform.openai.com/docs/api-reference/vector-stores/modify)\n```swift\nlet vectorStoreID = \"vs_abc123\"\nlet vectorStore = try await service.modifyVectorStore(id: vectorStoreID)\n```\n\n[Delete Vector store](https://platform.openai.com/docs/api-reference/vector-stores/delete)\n```swift\nlet vectorStoreID = \"vs_abc123\"\nlet deletionStatus = try await service.deleteVectorStore(id: vectorStoreID)\n```\n\n### Vector Store File\nParameters\n```swift\npublic struct VectorStoreFileParameter: Encodable {\n \n /// A [File](https://platform.openai.com/docs/api-reference/files) ID that the vector store should use. Useful for tools like file_search that can access files.\n let fileID: String\n}\n```\nResponse\n```swift\npublic struct VectorStoreFileObject: Decodable {\n \n /// The identifier, which can be referenced in API endpoints.\n let id: String\n /// The object type, which is always vector_store.file.\n let object: String\n /// The total vector store usage in bytes. Note that this may be different from the original file size.\n let usageBytes: Int\n /// The Unix timestamp (in seconds) for when the vector store file was created.\n let createdAt: Int\n /// The ID of the [vector store](https://platform.openai.com/docs/api-reference/vector-stores/object) that the [File](https://platform.openai.com/docs/api-reference/files) is attached to.\n let vectorStoreID: String\n /// The status of the vector store file, which can be either in_progress, completed, cancelled, or failed. The status completed indicates that the vector store file is ready for use.\n let status: String\n /// The last error associated with this vector store file. Will be null if there are no errors.\n let lastError: LastError?\n}\n```\n\nUsage\n[Create vector store file](https://platform.openai.com/docs/api-reference/vector-stores-files/createFile)\n```swift\nlet vectorStoreID = \"vs_abc123\"\nlet fileID = \"file-abc123\"\nlet parameters = VectorStoreFileParameter(fileID: fileID)\nlet vectoreStoreFile = try await service.createVectorStoreFile(vectorStoreID: vectorStoreID, parameters: parameters)\n```\n\n[List vector store files](https://platform.openai.com/docs/api-reference/vector-stores-files/listFiles)\n```swift\nlet vectorStoreID = \"vs_abc123\"\nlet vectorStoreFiles = try await service.listVectorStoreFiles(vectorStoreID: vectorStoreID, limit: nil, order: nil, aftre: nil, before: nil, filter: nil)\n```\n\n[Retrieve vector store file](https://platform.openai.com/docs/api-reference/vector-stores-files/getFile)\n```swift\nlet vectorStoreID = \"vs_abc123\"\nlet fileID = \"file-abc123\"\nlet vectoreStoreFile = try await service.retrieveVectorStoreFile(vectorStoreID: vectorStoreID, fileID: fileID)\n```\n\n[Delete vector store file](https://platform.openai.com/docs/api-reference/vector-stores-files/deleteFile)\n```swift\nlet vectorStoreID = \"vs_abc123\"\nlet fileID = \"file-abc123\"\nlet deletionStatus = try await service.deleteVectorStoreFile(vectorStoreID: vectorStoreID, fileID: fileID)\n```\n\n### Vector Store File Batch\nParameters\n```swift\npublic struct VectorStoreFileBatchParameter: Encodable {\n \n /// A list of [File](https://platform.openai.com/docs/api-reference/files) IDs that the vector store should use. Useful for tools like file_search that can access files.\n let fileIDS: [String]\n}\n```\nResponse\n```swift\npublic struct VectorStoreFileBatchObject: Decodable {\n \n /// The identifier, which can be referenced in API endpoints.\n let id: String\n /// The object type, which is always vector_store.file_batch.\n let object: String\n /// The Unix timestamp (in seconds) for when the vector store files batch was created.\n let createdAt: Int\n /// The ID of the [vector store](https://platform.openai.com/docs/api-reference/vector-stores/object) that the [File](https://platform.openai.com/docs/api-reference/files) is attached to.\n let vectorStoreID: String\n /// The status of the vector store files batch, which can be either in_progress, completed, cancelled or failed.\n let status: String\n \n let fileCounts: FileCount\n}\n```\nUsage\n\n[Create vector store file batch](https://platform.openai.com/docs/api-reference/vector-stores-file-batches/createBatch)\n```swift\nlet vectorStoreID = \"vs_abc123\"\nlet fileIDS = [\"file-abc123\", \"file-abc456\"]\nlet parameters = VectorStoreFileBatchParameter(fileIDS: fileIDS)\nlet vectorStoreFileBatch = try await service.\n createVectorStoreFileBatch(vectorStoreID: vectorStoreID, parameters: parameters)\n```\n\n[Retrieve vector store file batch](https://platform.openai.com/docs/api-reference/vector-stores-file-batches/getBatch)\n```swift\nlet vectorStoreID = \"vs_abc123\"\nlet batchID = \"vsfb_abc123\"\nlet vectorStoreFileBatch = try await service.retrieveVectorStoreFileBatch(vectorStoreID: vectorStoreID, batchID: batchID)\n```\n\n[Cancel vector store file batch](https://platform.openai.com/docs/api-reference/vector-stores-file-batches/cancelBatch)\n```swift\nlet vectorStoreID = \"vs_abc123\"\nlet batchID = \"vsfb_abc123\"\nlet vectorStoreFileBatch = try await service.cancelVectorStoreFileBatch(vectorStoreID: vectorStoreID, batchID: batchID)\n```\n\n[List vector store files in a batch](https://platform.openai.com/docs/api-reference/vector-stores-file-batches/listBatchFiles)\n```swift\nlet vectorStoreID = \"vs_abc123\"\nlet batchID = \"vsfb_abc123\"\nlet vectorStoreFiles = try await service.listVectorStoreFilesInABatch(vectorStoreID: vectorStoreID, batchID: batchID)\n```\n\n⚠️ We currently support Only Assistants Beta 2. If you need support for Assistants V1, you can access it in the jroch-supported-branch-for-assistants-v1 branch or in the v2.3 release.. [Check OpenAI Documentation for details on migration.](https://platform.openai.com/docs/assistants/migration))\n\n## Anthropic\n\nAnthropic provides OpenAI compatibility, for more, visit the [documentation](https://docs.anthropic.com/en/api/openai-sdk#getting-started-with-the-openai-sdk)\n\nTo use Claude models with `SwiftOpenAI` you can.\n\n```swift\nlet anthropicApiKey = \"\"\nlet openAIService = OpenAIServiceFactory.service(apiKey: anthropicApiKey, \n overrideBaseURL: \"https://api.anthropic.com\", \n overrideVersion: \"v1\")\n```\n\nNow you can create the completio parameters like this:\n\n```swift\nlet parameters = ChatCompletionParameters(\n messages: [.init(\n role: .user,\n content: \"Are you Claude?\")],\n model: .custom(\"claude-3-7-sonnet-20250219\"))\n```\n\nFor a more complete Anthropic Swift Package, you can use [SwiftAnthropic](https://github.com/jamesrochabrun/SwiftAnthropic)\n\n## Azure OpenAI\n\nThis library provides support for both chat completions and chat stream completions through Azure OpenAI. Currently, `DefaultOpenAIAzureService` supports chat completions, including both streamed and non-streamed options.\n\nFor more information about Azure configuration refer to the [documentation.](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference)\n\nTo instantiate `DefaultOpenAIAzureService` you need to provide a `AzureOpenAIConfiguration`\n\n```swift\nlet azureConfiguration = AzureOpenAIConfiguration(\n resourceName: \"YOUR_RESOURCE_NAME\", \n openAIAPIKey: .apiKey(\"YOUR_OPENAI_APIKEY), \n apiVersion: \"THE_API_VERSION\")\n \nlet service = OpenAIServiceFactory.service(azureConfiguration: azureConfiguration) \n```\n\nsupported api version can be found on the azure [documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#completions)\n\nCurrent Supported versions\n\n```2022-12-01```\n```2023-03-15-preview```\n```2023-05-15```\n```2023-06-01-preview```\n```2023-07-01-preview```\n```2023-08-01-preview```\n```2023-09-01-preview```\n\n### Usage on [Chat completions](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#chat-completions):\n\n```swift\nlet parameters = ChatCompletionParameters(\n messages: [.init(role: .user, content: .text(prompt))], \n model: .custom(\"DEPLOYMENT_NAME\") /// The deployment name you chose when you deployed the model. e.g: \"gpt-35-turbo-0613\"\nlet completionObject = try await service.startChat(parameters: parameters)\n```\n\n## AIProxy\n\n### What is it?\n\n[AIProxy](https://www.aiproxy.pro) is a backend for iOS apps that proxies requests from your app to OpenAI.\nUsing a proxy keeps your OpenAI key secret, protecting you from unexpectedly high bills due to key theft.\nRequests are only proxied if they pass your defined rate limits and Apple's [DeviceCheck](https://developer.apple.com/documentation/devicecheck) verification.\nWe offer AIProxy support so you can safely distribute apps built with SwiftOpenAI.\n\n### How does my SwiftOpenAI code change?\n\nProxy requests through AIProxy with two changes to your Xcode project:\n\n1. Instead of initializing `service` with:\n\n let apiKey = \"your_openai_api_key_here\"\n let service = OpenAIServiceFactory.service(apiKey: apiKey)\n\nUse:\n\n let service = OpenAIServiceFactory.service(\n aiproxyPartialKey: \"your_partial_key_goes_here\",\n aiproxyServiceURL: \"your_service_url_goes_here\"\n )\n\nThe `aiproxyPartialKey` and `aiproxyServiceURL` values are provided to you on the [AIProxy developer dashboard](https://developer.aiproxy.pro)\n\n2. Add an `AIPROXY_DEVICE_CHECK_BYPASS' env variable to Xcode. This token is provided to you in the AIProxy\n developer dashboard, and is necessary for the iOS simulator to communicate with the AIProxy backend.\n - Type `cmd shift ,` to open up the \"Edit Schemes\" menu in Xcode\n - Select `Run` in the sidebar\n - Select `Arguments` from the top nav\n - Add to the \"Environment Variables\" section (not the \"Arguments Passed on Launch\" section) an env\n variable with name `AIPROXY_DEVICE_CHECK_BYPASS` and value that we provided you in the AIProxy dashboard\n\n\n⚠️ The `AIPROXY_DEVICE_CHECK_BYPASS` is intended for the simulator only. Do not let it leak into\na distribution build of your app (including a TestFlight distribution). If you follow the steps above,\nthen the constant won't leak because env variables are not packaged into the app bundle.\n\n#### What is the `AIPROXY_DEVICE_CHECK_BYPASS` constant?\n\nAIProxy uses Apple's [DeviceCheck](https://developer.apple.com/documentation/devicecheck) to ensure\nthat requests received by the backend originated from your app on a legitimate Apple device.\nHowever, the iOS simulator cannot produce DeviceCheck tokens. Rather than requiring you to\nconstantly build and run on device during development, AIProxy provides a way to skip the\nDeviceCheck integrity check. The token is intended for use by developers only. If an attacker gets\nthe token, they can make requests to your AIProxy project without including a DeviceCheck token, and\nthus remove one level of protection.\n\n#### What is the `aiproxyPartialKey` constant?\n\nThis constant is safe to include in distributed version of your app. It is one part of an\nencrypted representation of your real secret key. The other part resides on AIProxy's backend.\nAs your app makes requests to AIProxy, the two encrypted parts are paired, decrypted, and used\nto fulfill the request to OpenAI.\n\n#### How to setup my project on AIProxy?\n\nPlease see the [AIProxy integration guide](https://www.aiproxy.pro/docs/integration-guide.html)\n\n\n### ⚠️ Disclaimer\n\nContributors of SwiftOpenAI shall not be liable for any damages or losses caused by third parties.\nContributors of this library provide third party integrations as a convenience. Any use of a third\nparty's services are assumed at your own risk.\n\n\n## Ollama\n\nOllama now has built-in compatibility with the OpenAI [Chat Completions API](https://github.com/ollama/ollama/blob/main/docs/openai.md), making it possible to use more tooling and applications with Ollama locally.\n\n![\"Screenshot](\"https://github.com/jamesrochabrun/SwiftOpenAI/assets/5378604/db2264cb-408c-471d-b65b-912795c082ed\")
\n\n### ⚠️ Important\n\nRemember that these models run locally, so you need to download them. If you want to use llama3, you can open the terminal and run the following command:\n\n```python\nollama pull llama3\n```\n\nyou can follow [Ollama documentation](https://github.com/ollama/ollama/blob/main/docs/openai.md) for more.\n\n### How to use this models locally using SwiftOpenAI?\n\nTo use local models with an `OpenAIService` in your application, you need to provide a URL. \n\n```swift\nlet service = OpenAIServiceFactory.service(baseURL: \"http://localhost:11434\")\n```\n\nThen you can use the completions API as follows:\n\n```swift\nlet prompt = \"Tell me a joke\"\nlet parameters = ChatCompletionParameters(messages: [.init(role: .user, content: .text(prompt))], model: .custom(\"llama3\"))\nlet chatCompletionObject = service.startStreamedChat(parameters: parameters)\n```\n\n⚠️ Note: You can probably use the `OpenAIServiceFactory.service(apiKey:overrideBaseURL:proxyPath)` for any OpenAI compatible service.\n\n### Resources:\n\n[Ollama OpenAI compatibility docs.](https://github.com/ollama/ollama/blob/main/docs/openai.md)\n[Ollama OpenAI compatibility blog post.](https://ollama.com/blog/openai-compatibility)\n\n### Notes\n\nYou can also use this service constructor to provide any URL or apiKey if you need.\n\n```swift\nlet service = OpenAIServiceFactory.service(apiKey: \"YOUR_API_KEY\", baseURL: \"http://localhost:11434\")\n```\n\n## Groq\n\n![\"Screenshot](\"https://github.com/user-attachments/assets/7afb36a2-b2d8-4f89-9592-f4cece20d469\")
\n\nGroq API is mostly compatible with OpenAI's client libraries like `SwiftOpenAI` to use Groq using this library you just need to create an instance of `OpenAIService` like this:\n\n```swift\nlet apiKey = \"your_api_key\"\nlet service = OpenAIServiceFactory.service(apiKey: apiKey, overrideBaseURL: \"https://api.groq.com/\", proxyPath: \"openai\")\n\n```\n\nFor Supported API's using Groq visit its [documentation](https://console.groq.com/docs/openai).\n\n## xAI\n\n![\"xAI](\"https://github.com/user-attachments/assets/596ef28a-b8ea-4868-b37c-36ae28d77a30\")
\n\nxAI provides an OpenAI-compatible completion API to its Grok models. You can use the OpenAI SDK to access these models.\n\n```swift\nlet apiKey = \"your_api_xai_key\"\nlet service = OpenAIServiceFactory.service(apiKey: apiKey, overrideBaseURL: \"https://api.x.ai\", overrideVersion: \"v1\")\n```\n\nFor more information about the `xAI` api visit its [documentation](https://docs.x.ai/docs/overview).\n\n## OpenRouter\n\n![\"Image\"](\"https://github.com/user-attachments/assets/2d658d07-0b41-4b5f-a094-ec7856f6fe98\")
\n\n[OpenRouter](https://openrouter.ai/docs/quick-start) provides an OpenAI-compatible completion API to 314 models & providers that you can call directly, or using the OpenAI SDK. Additionally, some third-party SDKs are available.\n\n```swift\n\n// Creating the service\n\nlet apiKey = \"your_api_key\"\nlet servcie = OpenAIServiceFactory.service(apiKey: apiKey, \n overrideBaseURL: \"https://openrouter.ai\", \n proxyPath: \"api\",\n extraHeaders: [\n \"HTTP-Referer\": \"\", // Optional. Site URL for rankings on openrouter.ai.\n \"X-Title\": \"\" // Optional. Site title for rankings on openrouter.ai.\n ])\n\n// Making a request\n\nlet prompt = \"What is the Manhattan project?\"\nlet parameters = ChatCompletionParameters(messages: [.init(role: .user, content: .text(prompt))], model: .custom(\"deepseek/deepseek-r1:free\"))\nlet stream = service.startStreamedChat(parameters: parameters)\n```\n\nFor more inofrmation about the `OpenRouter` api visit its [documentation](https://openrouter.ai/docs/quick-start).\n\n## DeepSeek\n\n\n\nThe [DeepSeek](https://api-docs.deepseek.com/) API uses an API format compatible with OpenAI. By modifying the configuration, you can use SwiftOpenAI to access the DeepSeek API.\n\nCreating the service\n\n```swift\n\nlet apiKey = \"your_api_key\"\nlet service = OpenAIServiceFactory.service(\n apiKey: apiKey,\n overrideBaseURL: \"https://api.deepseek.com\")\n```\n\nNon-Streaming Example\n\n```swift\nlet prompt = \"What is the Manhattan project?\"\nlet parameters = ChatCompletionParameters(\n messages: [.init(role: .user, content: .text(prompt))],\n model: .custom(\"deepseek-reasoner\")\n)\n\ndo {\n let result = try await service.chat(parameters: parameters)\n \n // Access the response content\n if let content = result.choices.first?.message.content {\n print(\"Response: \\(content)\")\n }\n \n // Access reasoning content if available\n if let reasoning = result.choices.first?.message.reasoningContent {\n print(\"Reasoning: \\(reasoning)\")\n }\n} catch {\n print(\"Error: \\(error)\")\n}\n```\n\nStreaming Example\n\n```swift\nlet prompt = \"What is the Manhattan project?\"\nlet parameters = ChatCompletionParameters(\n messages: [.init(role: .user, content: .text(prompt))],\n model: .custom(\"deepseek-reasoner\")\n)\n\n// Start the stream\ndo {\n let stream = try await service.startStreamedChat(parameters: parameters)\n for try await result in stream {\n let content = result.choices.first?.delta.content ?? \"\"\n self.message += content\n \n // Optional: Handle reasoning content if available\n if let reasoning = result.choices.first?.delta.reasoningContent {\n self.reasoningMessage += reasoning\n }\n }\n} catch APIError.responseUnsuccessful(let description, let statusCode) {\n self.errorMessage = \"Network error with status code: \\(statusCode) and description: \\(description)\"\n} catch {\n self.errorMessage = error.localizedDescription\n}\n```\n\nNotes\n\n- The DeepSeek API is compatible with OpenAI's format but uses different model names\n- Use .custom(\"deepseek-reasoner\") to specify the DeepSeek model\n- The `reasoningContent` field is optional and specific to DeepSeek's API\n- Error handling follows the same pattern as standard OpenAI requests.\n\nFor more inofrmation about the `DeepSeek` api visit its [documentation](https://api-docs.deepseek.com).\n\n## Gemini\n\n![\"Screenshot](\"https://github.com/user-attachments/assets/cebc18fe-b96d-4ffe-912e-77d625249cf2\")
\n\nGemini is now accessible from the OpenAI Library. Announcement .\n`SwiftOpenAI` support all OpenAI endpoints, however Please refer to Gemini documentation to understand which API's are currently compatible' \n\nGemini is now accessible through the OpenAI Library. See the announcement [here](https://developers.googleblog.com/en/gemini-is-now-accessible-from-the-openai-library/).\nSwiftOpenAI supports all OpenAI endpoints. However, please refer to the [Gemini documentation](https://ai.google.dev/gemini-api/docs/openai) to understand which APIs are currently compatible.\"\n\n\nYou can instantiate a `OpenAIService` using your Gemini token like this...\n\n```swift\nlet geminiAPIKey = \"your_api_key\"\nlet baseURL = \"https://generativelanguage.googleapis.com\"\nlet version = \"v1beta\"\n\nlet service = OpenAIServiceFactory.service(\n apiKey: apiKey, \n overrideBaseURL: baseURL, \n overrideVersion: version)\n```\n\nYou can now create a chat request using the .custom model parameter and pass the model name as a string.\n\n```swift\nlet parameters = ChatCompletionParameters(\n messages: [.init(\n role: .user,\n content: content)],\n model: .custom(\"gemini-1.5-flash\"))\n\nlet stream = try await service.startStreamedChat(parameters: parameters)\n```\n\n## Collaboration\nOpen a PR for any proposed change pointing it to `main` branch. Unit tests are highly appreciated ❤️\n\n"
},
{
"path": "Sources/OpenAI/AIProxy/AIProxyCertificatePinning.swift",
"content": "//\n// AIProxyCertificatePinning.swift\n//\n//\n// Created by Lou Zell on 6/23/24.\n//\n#if !os(Linux)\nimport Foundation\nimport OSLog\n\nprivate let aiproxyLogger = Logger(\n subsystem: Bundle.main.bundleIdentifier ?? \"UnknownApp\",\n category: \"SwiftOpenAI+AIProxyCertificatePinning\")\n\n// MARK: - AIProxyCertificatePinningDelegate\n\n/// ## About\n/// Use this class in conjunction with a URLSession to adopt certificate pinning in your app.\n/// Cert pinning greatly reduces the ability for an attacker to snoop on your traffic.\n///\n/// A common misunderstanding about https is that it's hard for an attacker to read your traffic.\n/// Unfortunately, that is only true if you, as the developer, control both sides of the pipe.\n/// As an app developer, this is almost never the case. You ship your apps to the app store, and\n/// attackers install them. When an attacker has your app on hardware they control (e.g. an iPhone),\n/// it is trivial for them to MITM your app and read encrypted traffic.\n///\n/// Certificate pinning adds an additional layer of security by only allowing the TLS handshake to\n/// succeed if your app recognizes the public key from the other side. I have baked in several AIProxy\n/// public keys to this implementation.\n///\n/// This also functions as a reference implementation for any other libraries that want to interact\n/// with the aiproxy.pro service using certificate pinning.\n///\n/// ## Implementor's note, and a gotcha\n/// Use an instance of this class as the delegate to URLSession. For example:\n///\n/// let mySession = URLSession(\n/// configuration: .default,\n/// delegate: AIProxyCertificatePinningDelegate(),\n/// delegateQueue: nil\n/// )\n///\n/// In a perfect world, this would be all that is required of you. In fact, it is all that is required to protect requests made\n/// with `await mySession.data(for:)`, because Foundation calls `urlSession:didReceiveChallenge:`\n/// internally. However, `await mySession.bytes(for:)` is not protected, which is rather odd. As a workaround,\n/// change your callsites from:\n///\n/// await mySession.bytes(for: request)\n///\n/// to:\n///\n/// await mySession.bytes(\n/// for: request,\n/// delegate: mySession.delegate as? URLSessionTaskDelegate\n/// )\n///\n/// If you encounter other calls in the wild that do not invoke `urlSession:didReceiveChallenge:` on this class,\n/// please report them to me.\nfinal class AIProxyCertificatePinningDelegate: NSObject, URLSessionDelegate, URLSessionTaskDelegate {\n func urlSession(\n _: URLSession,\n task _: URLSessionTask,\n didReceive challenge: URLAuthenticationChallenge)\n async -> (URLSession.AuthChallengeDisposition, URLCredential?)\n {\n answerChallenge(challenge)\n }\n\n func urlSession(\n _: URLSession,\n didReceive challenge: URLAuthenticationChallenge)\n async -> (URLSession.AuthChallengeDisposition, URLCredential?)\n {\n answerChallenge(challenge)\n }\n\n private func answerChallenge(\n _ challenge: URLAuthenticationChallenge)\n -> (URLSession.AuthChallengeDisposition, URLCredential?)\n {\n guard let secTrust = challenge.protectionSpace.serverTrust else {\n aiproxyLogger.error(\"Could not access the server's security space\")\n return (.cancelAuthenticationChallenge, nil)\n }\n\n guard let certificate = getServerCert(secTrust: secTrust) else {\n aiproxyLogger.error(\"Could not access the server's TLS cert\")\n return (.cancelAuthenticationChallenge, nil)\n }\n\n let serverPublicKey = SecCertificateCopyKey(certificate)!\n let serverPublicKeyData = SecKeyCopyExternalRepresentation(serverPublicKey, nil)!\n\n for publicKeyData in publicKeysAsData {\n if serverPublicKeyData as Data == publicKeyData {\n let credential = URLCredential(trust: secTrust)\n return (.useCredential, credential)\n }\n }\n return (.cancelAuthenticationChallenge, nil)\n }\n}\n\n// MARK: - Private\n\nprivate var publicKeysAsData: [Data] = publicKeysAsHex.map { publicKeyAsHex in\n let keyData = Data(publicKeyAsHex)\n\n let attributes: [String: Any] = [\n kSecAttrKeyType as String: kSecAttrKeyTypeECSECPrimeRandom,\n kSecAttrKeyClass as String: kSecAttrKeyClassPublic,\n kSecAttrKeySizeInBits as String: 256,\n ]\n\n var error: Unmanaged?\n let publicKey = SecKeyCreateWithData(keyData as CFData, attributes as CFDictionary, &error)!\n\n let localPublicKeyData = SecKeyCopyExternalRepresentation(publicKey, nil)! as Data\n\n if let error {\n print(\"Failed to create public key: \\(error.takeRetainedValue() as Error)\")\n fatalError()\n }\n return localPublicKeyData\n}\n\nprivate let publicKeysAsHex: [[UInt8]] = [\n // live on api.aiproxy.com\n [\n 0x04, 0x4A, 0x42, 0x12, 0xE7, 0xED, 0x36, 0xB4, 0xA9, 0x1F, 0x96, 0x7E, 0xCF, 0xBD, 0xE0,\n 0x9D, 0xEA, 0x4B, 0xFB, 0xAF, 0xE7, 0xC6, 0x93, 0xF0, 0xBF, 0x92, 0x0F, 0x12, 0x7A, 0x22,\n 0x7D, 0x00, 0x77, 0x81, 0xA5, 0x06, 0x26, 0x06, 0x5C, 0x47, 0x8F, 0x57, 0xEF, 0x41, 0x39,\n 0x0B, 0x3D, 0x41, 0x72, 0x68, 0x33, 0x86, 0x69, 0x14, 0x2A, 0x36, 0x4D, 0x74, 0x7D, 0xBC,\n 0x60, 0x91, 0xFF, 0xCC, 0x29,\n ],\n\n // live on api.aiproxy.pro\n [\n 0x04, 0x25, 0xA2, 0xD1, 0x81, 0xC0, 0x38, 0xCE, 0x57, 0xAA, 0x6E, 0xF0, 0x5A, 0xC3, 0x6A,\n 0xA7, 0xC4, 0x69, 0x69, 0xCB, 0xEB, 0x24, 0xE5, 0x20, 0x7D, 0x06, 0xCB, 0xC7, 0x49, 0xD5,\n 0x0C, 0xAC, 0xE6, 0x96, 0xC5, 0xC9, 0x28, 0x00, 0x8E, 0x69, 0xFF, 0x9D, 0x32, 0x01, 0x53,\n 0x74, 0xAB, 0xFD, 0x46, 0x03, 0x32, 0xED, 0x93, 0x7F, 0x0F, 0xE9, 0xD9, 0xC3, 0xAF, 0xE7,\n 0xA5, 0xCB, 0xC1, 0x29, 0x35,\n ],\n\n // live on beta-api.aiproxy.pro\n [\n 0x04, 0xAF, 0xB2, 0xCC, 0xE2, 0x51, 0x92, 0xCF, 0xB8, 0x01, 0x25, 0xC1, 0xB8, 0xDA, 0x29,\n 0x51, 0x9F, 0x91, 0x4C, 0xAA, 0x09, 0x66, 0x3D, 0x81, 0xD7, 0xAD, 0x6F, 0xDB, 0x78, 0x10,\n 0xD4, 0xBE, 0xCD, 0x4F, 0xE3, 0xAF, 0x4F, 0xB6, 0xD2, 0xCA, 0x85, 0xB6, 0xC7, 0x3E, 0xB4,\n 0x61, 0x62, 0xE1, 0xFC, 0x90, 0xD6, 0x84, 0x1F, 0x98, 0xCA, 0x83, 0x60, 0x8B, 0x65, 0xCB,\n 0x1A, 0x57, 0x6E, 0x32, 0x35,\n ],\n\n // backup-EC-key-A.key\n [\n 0x04, 0x2C, 0x25, 0x74, 0xBC, 0x7E, 0x18, 0x10, 0x27, 0xBD, 0x03, 0x56, 0x4A, 0x7B, 0x32,\n 0xD2, 0xC1, 0xB0, 0x2E, 0x58, 0x85, 0x9A, 0xB0, 0x7D, 0xCD, 0x7E, 0x23, 0x33, 0x88, 0x2F,\n 0xC0, 0xFE, 0xCE, 0x2E, 0xBF, 0x36, 0x67, 0xC6, 0x81, 0xF6, 0x52, 0x2B, 0x9B, 0xAF, 0x97,\n 0x3C, 0xAC, 0x00, 0x39, 0xD8, 0xCC, 0x43, 0x6B, 0x1D, 0x65, 0xA5, 0xAD, 0xD1, 0x57, 0x4B,\n 0xAD, 0xB1, 0x17, 0xD3, 0x10,\n ],\n\n // backup-EC-key-B.key\n [\n 0x04, 0x34, 0xAE, 0x84, 0x94, 0xE9, 0x02, 0xF0, 0x78, 0x0E, 0xEE, 0xE6, 0x4E, 0x39, 0x7F,\n 0xB4, 0x84, 0xF6, 0xEC, 0x55, 0x20, 0x0D, 0x36, 0xE9, 0xA6, 0x44, 0x6B, 0x9B, 0xE1, 0xEF,\n 0x19, 0xE7, 0x90, 0x5B, 0xF4, 0xA3, 0x29, 0xF3, 0x56, 0x7C, 0x60, 0x97, 0xF0, 0xC6, 0x61,\n 0x83, 0x31, 0x5D, 0x2D, 0xC9, 0xCC, 0x40, 0x43, 0xAD, 0x81, 0x63, 0xFD, 0xCF, 0xE2, 0x8E,\n 0xFA, 0x07, 0x09, 0xF6, 0xF2,\n ],\n\n // backup-EC-key-C.key\n [\n 0x04, 0x84, 0x4E, 0x33, 0xC8, 0x60, 0xE7, 0x78, 0xAA, 0xA2, 0xB6, 0x0B, 0xCF, 0x7A, 0x52,\n 0x43, 0xD1, 0x6D, 0x58, 0xFF, 0x17, 0xB8, 0xEA, 0x8A, 0x39, 0x53, 0xFB, 0x8B, 0x66, 0x7D,\n 0x10, 0x39, 0x80, 0x2C, 0x8D, 0xC9, 0xC3, 0x34, 0x33, 0x98, 0x14, 0xEB, 0x88, 0x7B, 0xF5,\n 0x4D, 0x1F, 0x07, 0xAE, 0x6A, 0x02, 0x6B, 0xF5, 0x9B, 0xA8, 0xC6, 0x55, 0x5C, 0x27, 0xCD,\n 0x1B, 0xC0, 0x27, 0x2D, 0x82,\n ],\n]\n\nprivate func getServerCert(secTrust: SecTrust) -> SecCertificate? {\n if #available(macOS 12.0, iOS 15.0, *) {\n guard let certs = SecTrustCopyCertificateChain(secTrust) as? [SecCertificate] else {\n return nil\n }\n return certs[0]\n } else {\n return SecTrustGetCertificateAtIndex(secTrust, 0)\n }\n}\n#endif\n"
},
{
"path": "Sources/OpenAI/AIProxy/AIProxyService.swift",
"content": "//\n// AIProxyService.swift\n//\n//\n// Created by Lou Zell on 3/27/24.\n//\n#if !os(Linux)\nimport Foundation\n\nprivate let aiproxySecureDelegate = AIProxyCertificatePinningDelegate()\n\n// MARK: - AIProxyService\n\nstruct AIProxyService: OpenAIService {\n /// Initializes an instance of the OpenAI service with the required configurations.\n ///\n /// - Parameters:\n /// - partialKey: Your partial key provided during the integration process at `dashboard.aiproxy.pro`.\n /// Refer to the [integration guide](https://www.aiproxy.pro/docs/integration-guide.html)\n /// for details on acquiring your partial key. This is required.\n /// - serviceURL: Your service URL, also provided during the integration process. If you integrated before\n /// July 22nd, 2024, you can leave this parameter blank, and it will default to\n /// `\"https://api.aiproxy.pro\"`. This is optional.\n /// - clientID: An optional client ID to annotate requests in the AIProxy developer dashboard.\n /// If left blank, AIProxy generates client IDs for you. Most users can safely leave this blank.\n /// - organizationID: An optional OpenAI organization ID. Refer to the [organization documentation](https://platform.openai.com/docs/api-reference/organization-optional)\n /// for details on its usage. Defaults to `nil`.\n /// - debugEnabled: A flag to enable printing request events during DEBUG builds. Set this to `true` for debugging.\n init(\n partialKey: String,\n serviceURL: String? = nil,\n clientID: String? = nil,\n organizationID: String? = nil,\n debugEnabled: Bool)\n {\n decoder = JSONDecoder()\n self.partialKey = partialKey\n self.clientID = clientID\n self.organizationID = organizationID\n self.debugEnabled = debugEnabled\n openAIEnvironment = .init(baseURL: serviceURL ?? \"https://api.aiproxy.pro\", proxyPath: nil, version: \"v1\")\n httpClient = URLSessionHTTPClientAdapter(\n urlSession: URLSession(\n configuration: .default,\n delegate: aiproxySecureDelegate,\n delegateQueue: nil))\n }\n\n let httpClient: HTTPClient\n let decoder: JSONDecoder\n let openAIEnvironment: OpenAIEnvironment\n\n // MARK: Audio\n\n func createTranscription(\n parameters: AudioTranscriptionParameters)\n async throws -> AudioObject\n {\n let request = try await OpenAIAPI.audio(.transcriptions).multiPartRequest(\n aiproxyPartialKey: partialKey,\n openAIEnvironment: openAIEnvironment,\n clientID: clientID,\n organizationID: organizationID,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: AudioObject.self, with: request)\n }\n\n func createTranslation(\n parameters: AudioTranslationParameters)\n async throws -> AudioObject\n {\n let request = try await OpenAIAPI.audio(.translations).multiPartRequest(\n aiproxyPartialKey: partialKey,\n openAIEnvironment: openAIEnvironment,\n clientID: clientID,\n organizationID: organizationID,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: AudioObject.self, with: request)\n }\n\n func createSpeech(\n parameters: AudioSpeechParameters)\n async throws -> AudioSpeechObject\n {\n let request = try await OpenAIAPI.audio(.speech).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters)\n let data = try await fetchAudio(with: request)\n return AudioSpeechObject(output: data)\n }\n\n #if canImport(AVFoundation)\n func realtimeSession(\n model _: String,\n configuration _: OpenAIRealtimeSessionConfiguration)\n async throws -> OpenAIRealtimeSession\n {\n fatalError(\"Realtime API is not yet supported for AIProxy. Please use DefaultOpenAIService instead.\")\n }\n #endif\n\n // MARK: Chat\n\n func startChat(\n parameters: ChatCompletionParameters)\n async throws -> ChatCompletionObject\n {\n var chatParameters = parameters\n chatParameters.stream = false\n let request = try await OpenAIAPI.chat.request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: chatParameters)\n return try await fetch(debugEnabled: debugEnabled, type: ChatCompletionObject.self, with: request)\n }\n\n func startStreamedChat(\n parameters: ChatCompletionParameters)\n async throws -> AsyncThrowingStream\n {\n var chatParameters = parameters\n chatParameters.stream = true\n chatParameters.streamOptions = .init(includeUsage: true)\n let request = try await OpenAIAPI.chat.request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: chatParameters)\n return try await fetchStream(debugEnabled: debugEnabled, type: ChatCompletionChunkObject.self, with: request)\n }\n\n // MARK: Embeddings\n\n func createEmbeddings(\n parameters: EmbeddingParameter)\n async throws -> OpenAIResponse\n {\n let request = try await OpenAIAPI.embeddings.request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n // MARK: Fine-tuning\n\n func createFineTuningJob(\n parameters: FineTuningJobParameters)\n async throws -> FineTuningJobObject\n {\n let request = try await OpenAIAPI.fineTuning(.create).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: FineTuningJobObject.self, with: request)\n }\n\n func listFineTuningJobs(\n after lastJobID: String? = nil,\n limit: Int? = nil)\n async throws -> OpenAIResponse\n {\n var queryItems = [URLQueryItem]()\n if let lastJobID, let limit {\n queryItems = [.init(name: \"after\", value: lastJobID), .init(name: \"limit\", value: \"\\(limit)\")]\n } else if let lastJobID {\n queryItems = [.init(name: \"after\", value: lastJobID)]\n } else if let limit {\n queryItems = [.init(name: \"limit\", value: \"\\(limit)\")]\n }\n\n let request = try await OpenAIAPI.fineTuning(.list).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n queryItems: queryItems)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n func retrieveFineTuningJob(\n id: String)\n async throws -> FineTuningJobObject\n {\n let request = try await OpenAIAPI.fineTuning(.retrieve(jobID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get)\n return try await fetch(debugEnabled: debugEnabled, type: FineTuningJobObject.self, with: request)\n }\n\n func cancelFineTuningJobWith(\n id: String)\n async throws -> FineTuningJobObject\n {\n let request = try await OpenAIAPI.fineTuning(.cancel(jobID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post)\n return try await fetch(debugEnabled: debugEnabled, type: FineTuningJobObject.self, with: request)\n }\n\n func listFineTuningEventsForJobWith(\n id: String,\n after lastEventId: String? = nil,\n limit: Int? = nil)\n async throws -> OpenAIResponse\n {\n var queryItems = [URLQueryItem]()\n if let lastEventId, let limit {\n queryItems = [.init(name: \"after\", value: lastEventId), .init(name: \"limit\", value: \"\\(limit)\")]\n } else if let lastEventId {\n queryItems = [.init(name: \"after\", value: lastEventId)]\n } else if let limit {\n queryItems = [.init(name: \"limit\", value: \"\\(limit)\")]\n }\n let request = try await OpenAIAPI.fineTuning(.events(jobID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n queryItems: queryItems)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n // MARK: Files\n\n func listFiles()\n async throws -> OpenAIResponse\n {\n let request = try await OpenAIAPI.file(.list).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n func uploadFile(\n parameters: FileParameters)\n async throws -> FileObject\n {\n let request = try await OpenAIAPI.file(.upload).multiPartRequest(\n aiproxyPartialKey: partialKey,\n openAIEnvironment: openAIEnvironment,\n clientID: clientID,\n organizationID: organizationID,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: FileObject.self, with: request)\n }\n\n func deleteFileWith(\n id: String)\n async throws -> DeletionStatus\n {\n let request = try await OpenAIAPI.file(.delete(fileID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .delete)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n func retrieveFileWith(\n id: String)\n async throws -> FileObject\n {\n let request = try await OpenAIAPI.file(.retrieve(fileID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get)\n return try await fetch(debugEnabled: debugEnabled, type: FileObject.self, with: request)\n }\n\n func retrieveContentForFileWith(\n id: String)\n async throws -> [[String: Any]]\n {\n let request = try await OpenAIAPI.file(.retrieveFileContent(fileID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get)\n return try await fetchContentsOfFile(request: request)\n }\n\n // MARK: Images\n\n func legacyCreateImages(\n parameters: ImageCreateParameters)\n async throws -> OpenAIResponse\n {\n let request = try await OpenAIAPI.images(.generations).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n func legacyEditImage(\n parameters: ImageEditParameters)\n async throws -> OpenAIResponse\n {\n let request = try await OpenAIAPI.images(.edits).multiPartRequest(\n aiproxyPartialKey: partialKey,\n openAIEnvironment: openAIEnvironment,\n clientID: clientID,\n organizationID: organizationID,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n func legacyCreateImageVariations(\n parameters: ImageVariationParameters)\n async throws -> OpenAIResponse\n {\n let request = try await OpenAIAPI.images(.variations).multiPartRequest(\n aiproxyPartialKey: partialKey,\n openAIEnvironment: openAIEnvironment,\n clientID: clientID,\n organizationID: organizationID,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n func createImages(\n parameters: CreateImageParameters)\n async throws -> CreateImageResponse\n {\n let request = try await OpenAIAPI.images(.generations).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: CreateImageResponse.self, with: request)\n }\n\n func editImage(\n parameters: CreateImageEditParameters)\n async throws -> CreateImageResponse\n {\n let request = try await OpenAIAPI.images(.edits).multiPartRequest(\n aiproxyPartialKey: partialKey,\n openAIEnvironment: openAIEnvironment,\n clientID: clientID,\n organizationID: organizationID,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: CreateImageResponse.self, with: request)\n }\n\n func createImageVariations(\n parameters: CreateImageVariationParameters)\n async throws -> CreateImageResponse\n {\n let request = try await OpenAIAPI.images(.variations).multiPartRequest(\n aiproxyPartialKey: partialKey,\n openAIEnvironment: openAIEnvironment,\n clientID: clientID,\n organizationID: organizationID,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: CreateImageResponse.self, with: request)\n }\n\n // MARK: Models\n\n func listModels()\n async throws -> OpenAIResponse\n {\n let request = try await OpenAIAPI.model(.list).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n func retrieveModelWith(\n id: String)\n async throws -> ModelObject\n {\n let request = try await OpenAIAPI.model(.retrieve(modelID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get)\n return try await fetch(debugEnabled: debugEnabled, type: ModelObject.self, with: request)\n }\n\n func deleteFineTuneModelWith(\n id: String)\n async throws -> DeletionStatus\n {\n let request = try await OpenAIAPI.model(.deleteFineTuneModel(modelID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .delete)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n // MARK: Moderations\n\n func createModerationFromText(\n parameters: ModerationParameter)\n async throws -> ModerationObject\n {\n let request = try await OpenAIAPI.moderations.request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: ModerationObject.self, with: request)\n }\n\n func createModerationFromTexts(\n parameters: ModerationParameter<[String]>)\n async throws -> ModerationObject\n {\n let request = try await OpenAIAPI.moderations.request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: ModerationObject.self, with: request)\n }\n\n // MARK: Assistants [BETA]\n\n func createAssistant(\n parameters: AssistantParameters)\n async throws -> AssistantObject\n {\n let request = try await OpenAIAPI.assistant(.create).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: AssistantObject.self, with: request)\n }\n\n func retrieveAssistant(\n id: String)\n async throws -> AssistantObject\n {\n let request = try await OpenAIAPI.assistant(.retrieve(assistantID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: AssistantObject.self, with: request)\n }\n\n func modifyAssistant(\n id: String,\n parameters: AssistantParameters)\n async throws -> AssistantObject\n {\n let request = try await OpenAIAPI.assistant(.modify(assistantID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: AssistantObject.self, with: request)\n }\n\n func deleteAssistant(\n id: String)\n async throws -> DeletionStatus\n {\n let request = try await OpenAIAPI.assistant(.delete(assistantID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .delete,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n func listAssistants(\n limit: Int? = nil,\n order: String? = nil,\n after: String? = nil,\n before: String? = nil)\n async throws -> OpenAIResponse\n {\n var queryItems = [URLQueryItem]()\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n let request = try await OpenAIAPI.assistant(.list).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n // MARK: Thread [BETA]\n\n func createThread(\n parameters: CreateThreadParameters)\n async throws -> ThreadObject\n {\n let request = try await OpenAIAPI.thread(.create).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: ThreadObject.self, with: request)\n }\n\n func retrieveThread(id: String)\n async throws -> ThreadObject\n {\n let request = try await OpenAIAPI.thread(.retrieve(threadID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: ThreadObject.self, with: request)\n }\n\n func modifyThread(\n id: String,\n parameters: ModifyThreadParameters)\n async throws -> ThreadObject\n {\n let request = try await OpenAIAPI.thread(.modify(threadID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: ThreadObject.self, with: request)\n }\n\n func deleteThread(\n id: String)\n async throws -> DeletionStatus\n {\n let request = try await OpenAIAPI.thread(.delete(threadID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .delete,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n // MARK: Message [BETA]\n\n func createMessage(\n threadID: String,\n parameters: MessageParameter)\n async throws -> MessageObject\n {\n let request = try await OpenAIAPI.message(.create(threadID: threadID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: MessageObject.self, with: request)\n }\n\n func retrieveMessage(\n threadID: String,\n messageID: String)\n async throws -> MessageObject\n {\n let request = try await OpenAIAPI.message(.retrieve(threadID: threadID, messageID: messageID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: MessageObject.self, with: request)\n }\n\n func modifyMessage(\n threadID: String,\n messageID: String,\n parameters: ModifyMessageParameters)\n async throws -> MessageObject\n {\n let request = try await OpenAIAPI.message(.modify(threadID: threadID, messageID: messageID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: MessageObject.self, with: request)\n }\n\n func deleteMessage(\n threadID: String,\n messageID: String)\n async throws -> DeletionStatus\n {\n let request = try await OpenAIAPI.message(.delete(threadID: threadID, messageID: messageID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .delete,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n func listMessages(\n threadID: String,\n limit: Int? = nil,\n order: String? = nil,\n after: String? = nil,\n before: String? = nil,\n runID _: String? = nil)\n async throws -> OpenAIResponse\n {\n var queryItems = [URLQueryItem]()\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n let request = try await OpenAIAPI.message(.list(threadID: threadID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n // MARK: Run [BETA]\n\n func createRun(\n threadID: String,\n parameters: RunParameter)\n async throws -> RunObject\n {\n let request = try await OpenAIAPI.run(.create(threadID: threadID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n func retrieveRun(\n threadID: String,\n runID: String)\n async throws -> RunObject\n {\n let request = try await OpenAIAPI.run(.retrieve(threadID: threadID, runID: runID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n func modifyRun(\n threadID: String,\n runID: String,\n parameters: ModifyRunParameters)\n async throws -> RunObject\n {\n let request = try await OpenAIAPI.run(.modify(threadID: threadID, runID: runID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n func listRuns(\n threadID: String,\n limit: Int? = nil,\n order: String? = nil,\n after: String? = nil,\n before: String? = nil)\n async throws -> OpenAIResponse\n {\n var queryItems = [URLQueryItem]()\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n let request = try await OpenAIAPI.run(.list(threadID: threadID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n func cancelRun(\n threadID: String,\n runID: String)\n async throws -> RunObject\n {\n let request = try await OpenAIAPI.run(.cancel(threadID: threadID, runID: runID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n func submitToolOutputsToRun(\n threadID: String,\n runID: String,\n parameters: RunToolsOutputParameter)\n async throws -> RunObject\n {\n let request = try await OpenAIAPI.run(.submitToolOutput(threadID: threadID, runID: runID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n func createThreadAndRun(\n parameters: CreateThreadAndRunParameter)\n async throws -> RunObject\n {\n let request = try await OpenAIAPI.run(.createThreadAndRun).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n // MARK: Run Step [BETA]\n\n func retrieveRunstep(\n threadID: String,\n runID: String,\n stepID: String)\n async throws -> RunStepObject\n {\n let request = try await OpenAIAPI.runStep(.retrieve(threadID: threadID, runID: runID, stepID: stepID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: RunStepObject.self, with: request)\n }\n\n func listRunSteps(\n threadID: String,\n runID: String,\n limit: Int? = nil,\n order: String? = nil,\n after: String? = nil,\n before: String? = nil)\n async throws -> OpenAIResponse\n {\n var queryItems = [URLQueryItem]()\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n let request = try await OpenAIAPI.runStep(.list(threadID: threadID, runID: runID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n func createRunStream(\n threadID: String,\n parameters: RunParameter)\n async throws -> AsyncThrowingStream\n {\n var runParameters = parameters\n runParameters.stream = true\n let request = try await OpenAIAPI.run(.create(threadID: threadID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: runParameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetchAssistantStreamEvents(with: request, debugEnabled: debugEnabled)\n }\n\n func createThreadAndRunStream(\n parameters: CreateThreadAndRunParameter)\n async throws -> AsyncThrowingStream\n {\n var runParameters = parameters\n runParameters.stream = true\n let request = try await OpenAIAPI.run(.createThreadAndRun).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetchAssistantStreamEvents(with: request, debugEnabled: debugEnabled)\n }\n\n func submitToolOutputsToRunStream(\n threadID: String,\n runID: String,\n parameters: RunToolsOutputParameter)\n async throws -> AsyncThrowingStream\n {\n var runToolsOutputParameter = parameters\n runToolsOutputParameter.stream = true\n let request = try await OpenAIAPI.run(.submitToolOutput(threadID: threadID, runID: runID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: runToolsOutputParameter,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetchAssistantStreamEvents(with: request, debugEnabled: debugEnabled)\n }\n\n // MARK: Batch\n\n func createBatch(\n parameters: BatchParameter)\n async throws -> BatchObject\n {\n let request = try await OpenAIAPI.batch(.create).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters)\n return try await fetch(debugEnabled: debugEnabled, type: BatchObject.self, with: request)\n }\n\n func retrieveBatch(\n id: String)\n async throws -> BatchObject\n {\n let request = try await OpenAIAPI.batch(.retrieve(batchID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get)\n return try await fetch(debugEnabled: debugEnabled, type: BatchObject.self, with: request)\n }\n\n func cancelBatch(\n id: String)\n async throws -> BatchObject\n {\n let request = try await OpenAIAPI.batch(.cancel(batchID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post)\n return try await fetch(debugEnabled: debugEnabled, type: BatchObject.self, with: request)\n }\n\n func listBatch(\n after: String? = nil,\n limit: Int? = nil)\n async throws -> OpenAIResponse\n {\n var queryItems = [URLQueryItem]()\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n let request = try await OpenAIAPI.batch(.list).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n queryItems: queryItems)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n // MARK: Vector Store\n\n func createVectorStore(\n parameters: VectorStoreParameter)\n async throws -> VectorStoreObject\n {\n let request = try await OpenAIAPI.vectorStore(.create).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreObject.self, with: request)\n }\n\n func listVectorStores(\n limit: Int? = nil,\n order: String? = nil,\n after: String? = nil,\n before: String? = nil)\n async throws -> OpenAIResponse\n {\n var queryItems = [URLQueryItem]()\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n let request = try await OpenAIAPI.vectorStore(.list).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n func retrieveVectorStore(\n id: String)\n async throws -> VectorStoreObject\n {\n let request = try await OpenAIAPI.vectorStore(.retrieve(vectorStoreID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreObject.self, with: request)\n }\n\n func modifyVectorStore(\n parameters: VectorStoreParameter,\n id: String)\n async throws -> VectorStoreObject\n {\n let request = try await OpenAIAPI.vectorStore(.modify(vectorStoreID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreObject.self, with: request)\n }\n\n func deleteVectorStore(\n id: String)\n async throws -> DeletionStatus\n {\n let request = try await OpenAIAPI.vectorStore(.modify(vectorStoreID: id)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .delete,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n // MARK: Vector Store Files\n\n func createVectorStoreFile(\n vectorStoreID _: String,\n parameters: VectorStoreFileParameter)\n async throws -> VectorStoreFileObject\n {\n let request = try await OpenAIAPI.vectorStore(.create).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreFileObject.self, with: request)\n }\n\n func listVectorStoreFiles(\n vectorStoreID: String,\n limit: Int? = nil,\n order: String? = nil,\n after: String? = nil,\n before: String? = nil,\n filter: String? = nil)\n async throws -> OpenAIResponse\n {\n var queryItems = [URLQueryItem]()\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n if let filter {\n queryItems.append(.init(name: \"filter\", value: filter))\n }\n let request = try await OpenAIAPI.vectorStoreFile(.list(vectorStoreID: vectorStoreID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n func retrieveVectorStoreFile(\n vectorStoreID: String,\n fileID: String)\n async throws -> VectorStoreFileObject\n {\n let request = try await OpenAIAPI.vectorStoreFile(.retrieve(vectorStoreID: vectorStoreID, fileID: fileID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreFileObject.self, with: request)\n }\n\n func deleteVectorStoreFile(\n vectorStoreID: String,\n fileID: String)\n async throws -> DeletionStatus\n {\n let request = try await OpenAIAPI.vectorStoreFile(.delete(vectorStoreID: vectorStoreID, fileID: fileID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .delete,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n // MARK: Vector Store File Batch\n\n func createVectorStoreFileBatch(\n vectorStoreID: String,\n parameters: VectorStoreFileBatchParameter)\n async throws -> VectorStoreFileBatchObject\n {\n let request = try await OpenAIAPI.vectorStoreFileBatch(.create(vectorStoreID: vectorStoreID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: parameters,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreFileBatchObject.self, with: request)\n }\n\n func retrieveVectorStoreFileBatch(\n vectorStoreID: String,\n batchID: String)\n async throws -> VectorStoreFileBatchObject\n {\n let request = try await OpenAIAPI.vectorStoreFileBatch(.retrieve(vectorStoreID: vectorStoreID, batchID: batchID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreFileBatchObject.self, with: request)\n }\n\n func cancelVectorStoreFileBatch(\n vectorStoreID: String,\n batchID: String)\n async throws -> VectorStoreFileBatchObject\n {\n let request = try await OpenAIAPI.vectorStoreFileBatch(.cancel(vectorStoreID: vectorStoreID, batchID: batchID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreFileBatchObject.self, with: request)\n }\n\n func listVectorStoreFilesInABatch(\n vectorStoreID: String,\n batchID: String,\n limit: Int? = nil,\n order: String? = nil,\n after: String? = nil,\n before: String? = nil,\n filter: String? = nil)\n async throws -> OpenAIResponse\n {\n var queryItems = [URLQueryItem]()\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n if let filter {\n queryItems.append(.init(name: \"filter\", value: filter))\n }\n let request = try await OpenAIAPI.vectorStoreFileBatch(.list(vectorStoreID: vectorStoreID, batchID: batchID)).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n // MARK: Response\n\n func responseCreate(\n _ parameters: ModelResponseParameter)\n async throws -> ResponseModel\n {\n var responseParameters = parameters\n responseParameters.stream = false\n let request = try await OpenAIAPI.chat.request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: responseParameters)\n return try await fetch(debugEnabled: debugEnabled, type: ResponseModel.self, with: request)\n }\n\n func responseModel(\n id _: String,\n parameters _: GetResponseParameter?)\n async throws -> ResponseModel\n {\n let request = try await OpenAIAPI.chat.request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post)\n return try await fetch(debugEnabled: debugEnabled, type: ResponseModel.self, with: request)\n }\n\n func responseModelStream(\n id _: String,\n parameters _: GetResponseParameter?)\n async throws -> AsyncThrowingStream\n {\n fatalError(\"responseModelStream not implemented for AIProxy Service\")\n }\n\n func responseCreateStream(\n _ parameters: ModelResponseParameter)\n async throws -> AsyncThrowingStream\n {\n var responseParameters = parameters\n responseParameters.stream = true\n let request = try await OpenAIAPI.response(.create).request(\n aiproxyPartialKey: partialKey,\n clientID: clientID,\n organizationID: organizationID,\n openAIEnvironment: openAIEnvironment,\n method: .post,\n params: responseParameters)\n return try await fetchStream(debugEnabled: debugEnabled, type: ResponseStreamEvent.self, with: request)\n }\n\n func responseDelete(\n id _: String)\n async throws -> DeletionStatus\n {\n fatalError(\"responseDelete not implemented for AIProxy Service\")\n }\n\n func responseCancel(\n id _: String)\n async throws -> ResponseModel\n {\n fatalError(\"responseCancel not implemented for AIProxy Service\")\n }\n\n func responseInputItems(\n id _: String,\n parameters _: GetInputItemsParameter?)\n async throws -> OpenAIResponse\n {\n fatalError(\"responseInputItems not implemented for AIProxy Service\")\n }\n\n // MARK: - Conversations\n\n func conversationCreate(\n parameters _: CreateConversationParameter?)\n async throws -> ConversationModel\n {\n fatalError(\"conversationCreate not implemented for AIProxy Service\")\n }\n\n func getConversation(\n id _: String)\n async throws -> ConversationModel\n {\n fatalError(\"getConversation not implemented for AIProxy Service\")\n }\n\n func updateConversation(\n id _: String,\n parameters _: UpdateConversationParameter)\n async throws -> ConversationModel\n {\n fatalError(\"updateConversation not implemented for AIProxy Service\")\n }\n\n func deleteConversation(\n id _: String)\n async throws -> DeletionStatus\n {\n fatalError(\"deleteConversation not implemented for AIProxy Service\")\n }\n\n func getConversationItems(\n id _: String,\n parameters _: GetConversationItemsParameter?)\n async throws -> OpenAIResponse\n {\n fatalError(\"getConversationItems not implemented for AIProxy Service\")\n }\n\n func createConversationItems(\n id _: String,\n parameters _: CreateConversationItemsParameter)\n async throws -> OpenAIResponse\n {\n fatalError(\"createConversationItems not implemented for AIProxy Service\")\n }\n\n func getConversationItem(\n conversationID _: String,\n itemID _: String,\n parameters _: GetConversationItemParameter?)\n async throws -> InputItem\n {\n fatalError(\"getConversationItem not implemented for AIProxy Service\")\n }\n\n func deleteConversationItem(\n conversationID _: String,\n itemID _: String)\n async throws -> ConversationModel\n {\n fatalError(\"deleteConversationItem not implemented for AIProxy Service\")\n }\n\n private static let assistantsBetaV2 = \"assistants=v2\"\n\n /// Your partial key is provided during the integration process at dashboard.aiproxy.pro\n /// Please see the [integration guide](https://www.aiproxy.pro/docs/integration-guide.html) for acquiring your partial key\n private let partialKey: String\n /// Optionally supply your own client IDs to annotate requests with in the AIProxy developer dashboard.\n /// It is safe to leave this blank (most people do). If you leave it blank, AIProxy generates client IDs for you.\n private let clientID: String?\n /// Set this flag to TRUE if you need to print request events in DEBUG builds.\n private let debugEnabled: Bool\n\n /// [organization](https://platform.openai.com/docs/api-reference/organization-optional)\n private let organizationID: String?\n}\n#endif\n"
},
{
"path": "Sources/OpenAI/AIProxy/Endpoint+AIProxy.swift",
"content": "//\n// Endpoint+AIProxy.swift\n//\n//\n// Created by Lou Zell on 3/26/24.\n//\n#if !os(Linux)\nimport DeviceCheck\nimport Foundation\nimport OSLog\n#if canImport(UIKit)\nimport UIKit\n#endif\n#if canImport(IOKit)\nimport IOKit\n#endif\n#if os(watchOS)\nimport WatchKit\n#endif\n\nprivate let aiproxyLogger = Logger(\n subsystem: Bundle.main.bundleIdentifier ?? \"UnknownApp\",\n category: \"SwiftOpenAI+AIProxy\")\n\nprivate let deviceCheckWarning = \"\"\"\n AIProxy warning: DeviceCheck is not available on this device.\n\n To use AIProxy on an iOS simulator, set an AIPROXY_DEVICE_CHECK_BYPASS environment variable.\n\n See the AIProxy section of the README at https://github.com/jamesrochabrun/SwiftOpenAI for instructions.\n \"\"\"\n\n// MARK: Endpoint+AIProxy\n\nextension Endpoint {\n func request(\n aiproxyPartialKey: String,\n clientID: String?,\n organizationID: String?,\n openAIEnvironment: OpenAIEnvironment,\n method: HTTPMethod,\n params: Encodable? = nil,\n queryItems: [URLQueryItem] = [],\n betaHeaderField: String? = nil)\n async throws -> URLRequest\n {\n let finalPath = path(in: openAIEnvironment)\n var request = URLRequest(url: urlComponents(serviceURL: openAIEnvironment.baseURL, path: finalPath, queryItems: queryItems)\n .url!)\n request.addValue(\"application/json\", forHTTPHeaderField: \"Content-Type\")\n request.addValue(aiproxyPartialKey, forHTTPHeaderField: \"aiproxy-partial-key\")\n if let organizationID {\n request.addValue(organizationID, forHTTPHeaderField: \"OpenAI-Organization\")\n }\n if let betaHeaderField {\n request.addValue(betaHeaderField, forHTTPHeaderField: \"OpenAI-Beta\")\n }\n if let clientID = clientID ?? getClientID() {\n request.addValue(clientID, forHTTPHeaderField: \"aiproxy-client-id\")\n }\n if let deviceCheckToken = await getDeviceCheckToken() {\n request.addValue(deviceCheckToken, forHTTPHeaderField: \"aiproxy-devicecheck\")\n }\n #if DEBUG && targetEnvironment(simulator)\n if let deviceCheckBypass = ProcessInfo.processInfo.environment[\"AIPROXY_DEVICE_CHECK_BYPASS\"] {\n request.addValue(deviceCheckBypass, forHTTPHeaderField: \"aiproxy-devicecheck-bypass\")\n }\n #endif\n request.httpMethod = method.rawValue\n if let params {\n request.httpBody = try JSONEncoder().encode(params)\n }\n return request\n }\n\n func multiPartRequest(\n aiproxyPartialKey: String,\n openAIEnvironment: OpenAIEnvironment,\n clientID: String?,\n organizationID: String?,\n method: HTTPMethod,\n params: MultipartFormDataParameters,\n queryItems: [URLQueryItem] = [])\n async throws -> URLRequest\n {\n let finalPath = path(in: openAIEnvironment)\n var request = URLRequest(url: urlComponents(serviceURL: openAIEnvironment.baseURL, path: finalPath, queryItems: queryItems)\n .url!)\n request.httpMethod = method.rawValue\n request.addValue(aiproxyPartialKey, forHTTPHeaderField: \"aiproxy-partial-key\")\n if let organizationID {\n request.addValue(organizationID, forHTTPHeaderField: \"OpenAI-Organization\")\n }\n if let clientID = clientID ?? getClientID() {\n request.addValue(clientID, forHTTPHeaderField: \"aiproxy-client-id\")\n }\n if let deviceCheckToken = await getDeviceCheckToken() {\n request.addValue(deviceCheckToken, forHTTPHeaderField: \"aiproxy-devicecheck\")\n }\n #if DEBUG && targetEnvironment(simulator)\n if let deviceCheckBypass = ProcessInfo.processInfo.environment[\"AIPROXY_DEVICE_CHECK_BYPASS\"] {\n request.addValue(deviceCheckBypass, forHTTPHeaderField: \"aiproxy-devicecheck-bypass\")\n }\n #endif\n let boundary = UUID().uuidString\n request.addValue(\"multipart/form-data; boundary=\\(boundary)\", forHTTPHeaderField: \"Content-Type\")\n request.httpBody = params.encode(boundary: boundary)\n return request\n }\n\n private func urlComponents(\n serviceURL: String,\n path: String,\n queryItems: [URLQueryItem])\n -> URLComponents\n {\n var components = URLComponents(string: serviceURL)!\n components.path = components.path.appending(path)\n if !queryItems.isEmpty {\n components.queryItems = queryItems\n }\n return components\n }\n}\n\n// MARK: Private Helpers\n\n/// Gets a device check token for use in your calls to aiproxy.\n/// The device token may be nil when targeting the iOS simulator.\nprivate func getDeviceCheckToken() async -> String? {\n guard DCDevice.current.isSupported else {\n if ProcessInfo.processInfo.environment[\"AIPROXY_DEVICE_CHECK_BYPASS\"] == nil {\n aiproxyLogger.warning(\"\\(deviceCheckWarning, privacy: .public)\")\n }\n return nil\n }\n\n do {\n let data = try await DCDevice.current.generateToken()\n return data.base64EncodedString()\n } catch {\n aiproxyLogger.error(\"Could not create DeviceCheck token. Are you using an explicit bundle identifier?\")\n return nil\n }\n}\n\n/// Get a unique ID for this client\nprivate func getClientID() -> String? {\n #if os(watchOS)\n return WKInterfaceDevice.current().identifierForVendor?.uuidString\n #elseif canImport(UIKit)\n return UIDevice.current.identifierForVendor?.uuidString\n #elseif canImport(IOKit)\n return getIdentifierFromIOKit()\n #else\n return nil\n #endif\n}\n\n // MARK: IOKit conditional dependency\n\n/// These functions are used on macOS for creating a client identifier.\n/// Unfortunately, macOS does not have a straightforward helper like UIKit's `identifierForVendor`\n#if canImport(IOKit)\nprivate func getIdentifierFromIOKit() -> String? {\n guard let macBytes = copy_mac_address() as? Data else {\n return nil\n }\n let macHex = macBytes.map { String(format: \"%02X\", $0) }\n return macHex.joined(separator: \":\")\n}\n\n/// This function is taken from the Apple sample code at:\n/// https://developer.apple.com/documentation/appstorereceipts/validating_receipts_on_the_device#3744656\nprivate func io_service(named name: String, wantBuiltIn: Bool) -> io_service_t? {\n let default_port = kIOMainPortDefault\n var iterator = io_iterator_t()\n defer {\n if iterator != IO_OBJECT_NULL {\n IOObjectRelease(iterator)\n }\n }\n\n guard\n let matchingDict = IOBSDNameMatching(default_port, 0, name),\n IOServiceGetMatchingServices(\n default_port,\n matchingDict as CFDictionary,\n &iterator) == KERN_SUCCESS,\n iterator != IO_OBJECT_NULL\n else {\n return nil\n }\n\n var candidate = IOIteratorNext(iterator)\n while candidate != IO_OBJECT_NULL {\n if\n let cftype = IORegistryEntryCreateCFProperty(\n candidate,\n \"IOBuiltin\" as CFString,\n kCFAllocatorDefault,\n 0)\n {\n let isBuiltIn = cftype.takeRetainedValue() as! CFBoolean\n if wantBuiltIn == CFBooleanGetValue(isBuiltIn) {\n return candidate\n }\n }\n\n IOObjectRelease(candidate)\n candidate = IOIteratorNext(iterator)\n }\n\n return nil\n}\n\n/// This function is taken from the Apple sample code at:\n/// https://developer.apple.com/documentation/appstorereceipts/validating_receipts_on_the_device#3744656\nprivate func copy_mac_address() -> CFData? {\n // Prefer built-in network interfaces.\n // For example, an external Ethernet adaptor can displace\n // the built-in Wi-Fi as en0.\n guard\n let service = io_service(named: \"en0\", wantBuiltIn: true)\n ?? io_service(named: \"en1\", wantBuiltIn: true)\n ?? io_service(named: \"en0\", wantBuiltIn: false)\n else { return nil }\n defer { IOObjectRelease(service) }\n\n if\n let cftype = IORegistryEntrySearchCFProperty(\n service,\n kIOServicePlane,\n \"IOMACAddress\" as CFString,\n kCFAllocatorDefault,\n IOOptionBits(kIORegistryIterateRecursively | kIORegistryIterateParents))\n {\n return (cftype as! CFData)\n }\n\n return nil\n}\n#endif\n#endif\n"
},
{
"path": "Sources/OpenAI/Azure/AzureOpenAIAPI.swift",
"content": "//\n// AzureOpenAIAPI.swift\n//\n//\n// Created by James Rochabrun on 1/23/24.\n//\n\nimport Foundation\n\n// MARK: - AzureOpenAIAPI\n\nenum AzureOpenAIAPI {\n /// https://learn.microsoft.com/en-us/azure/ai-services/openai/assistants-reference?tabs=python\n /// https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/assistant\n case assistant(AssistantCategory)\n /// https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#chat-completions\n case chat(deploymentID: String)\n /// https://learn.microsoft.com/en-us/azure/ai-services/openai/assistants-reference-messages?tabs=python\n case message(MessageCategory)\n /// https://learn.microsoft.com/en-us/azure/ai-services/openai/assistants-reference-runs?tabs=python\n case run(RunCategory)\n /// https://learn.microsoft.com/en-us/azure/ai-services/openai/assistants-reference-runs?tabs=python#list-run-steps\n case runStep(RunStepCategory)\n /// https://learn.microsoft.com/en-us/azure/ai-services/openai/assistants-reference-threads?tabs=python#create-a-thread\n case thread(ThreadCategory)\n /// https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/file-search?tabs=python#vector-stores\n case vectorStore(VectorStoreCategory)\n /// https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/file-search?tabs=python#vector-stores\n case vectorStoreFile(VectorStoreFileCategory)\n\n /// OpenAI's most advanced interface for generating model responses. Supports text and image inputs, and text outputs. Create stateful interactions with the model, using the output of previous responses as input. Extend the model's capabilities with built-in tools for file search, web search, computer use, and more. Allow the model access to external systems and data using function calling.\n case response(ResponseCategory) // https://platform.openai.com/docs/api-reference/responses\n\n enum AssistantCategory {\n case create\n case list\n case retrieve(assistantID: String)\n case modify(assistantID: String)\n case delete(assistantID: String)\n }\n\n enum MessageCategory {\n case create(threadID: String)\n case retrieve(threadID: String, messageID: String)\n case modify(threadID: String, messageID: String)\n case delete(threadID: String, messageID: String)\n case list(threadID: String)\n }\n\n enum RunCategory {\n case create(threadID: String)\n case retrieve(threadID: String, runID: String)\n case modify(threadID: String, runID: String)\n case list(threadID: String)\n case cancel(threadID: String, runID: String)\n case submitToolOutput(threadID: String, runID: String)\n case createThreadAndRun\n }\n\n enum RunStepCategory {\n case retrieve(threadID: String, runID: String, stepID: String)\n case list(threadID: String, runID: String)\n }\n\n enum ThreadCategory {\n case create\n case retrieve(threadID: String)\n case modify(threadID: String)\n case delete(threadID: String)\n }\n\n enum VectorStoreCategory {\n case create\n case list\n case retrieve(vectorStoreID: String)\n case modify(vectorStoreID: String)\n case delete(vectorStoreID: String)\n }\n\n /// https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/file-search?tabs=python#file-search-support\n enum VectorStoreFileCategory {\n case create(vectorStoreID: String)\n case list(vectorStoreID: String)\n case retrieve(vectorStoreID: String, fileID: String)\n case delete(vectorStoreID: String, fileID: String)\n }\n\n enum ResponseCategory {\n case create(deploymentID: String)\n case retrieve(responseID: String)\n }\n}\n\n// MARK: Endpoint\n\nextension AzureOpenAIAPI: Endpoint {\n func path(in _: OpenAIEnvironment) -> String {\n switch self {\n case .chat(let deploymentID): \"/openai/deployments/\\(deploymentID)/chat/completions\"\n\n case .assistant(let category):\n switch category {\n case .create, .list: \"/openai/assistants\"\n case .retrieve(let assistantID), .modify(let assistantID), .delete(let assistantID): \"/openai/assistants/\\(assistantID)\"\n }\n\n case .message(let category):\n switch category {\n case .create(let threadID), .list(let threadID): \"/openai/threads/\\(threadID)/messages\"\n case .retrieve(let threadID, let messageID), .modify(let threadID, let messageID),\n .delete(let threadID, let messageID): \"/openai/threads/\\(threadID)/messages/\\(messageID)\"\n }\n\n case .run(let category):\n switch category {\n case .create(let threadID), .list(let threadID): \"/openai/threads/\\(threadID)/runs\"\n case .retrieve(let threadID, let runID), .modify(let threadID, let runID): \"/openai/threads/\\(threadID)/runs/\\(runID)\"\n case .cancel(let threadID, let runID): \"/openai/threads/\\(threadID)/runs/\\(runID)/cancel\"\n case .submitToolOutput(let threadID, let runID): \"/openai/threads/\\(threadID)/runs/\\(runID)/submit_tool_outputs\"\n case .createThreadAndRun: \"/openai/threads/runs\"\n }\n\n case .runStep(let category):\n switch category {\n case .retrieve(let threadID, let runID, let stepID): \"/openai/threads/\\(threadID)/runs/\\(runID)/steps/\\(stepID)\"\n case .list(let threadID, let runID): \"/openai/threads/\\(threadID)/runs/\\(runID)/steps\"\n }\n\n case .thread(let category):\n switch category {\n case .create: \"/openai/threads\"\n case .retrieve(let threadID), .modify(let threadID), .delete(let threadID): \"/openai/threads/\\(threadID)\"\n }\n\n case .vectorStore(let category):\n switch category {\n case .create, .list: \"/openai/vector_stores\"\n case .retrieve(let vectorStoreID), .modify(let vectorStoreID),\n .delete(let vectorStoreID): \"/openai/vector_stores/\\(vectorStoreID)\"\n }\n\n case .vectorStoreFile(let category):\n switch category {\n case .create(let vectorStoreID), .list(let vectorStoreID): \"/openai/vector_stores/\\(vectorStoreID)/files\"\n case .retrieve(let vectorStoreID, let fileID),\n .delete(let vectorStoreID, let fileID): \"/openai/vector_stores/\\(vectorStoreID)/files/\\(fileID)\"\n }\n\n case .response(let category):\n switch category {\n case .create(let deploymentID): \"/openai/deployments/\\(deploymentID)/responses\"\n case .retrieve(let responseID): \"/openai/responses/\\(responseID)\"\n }\n }\n }\n}\n"
},
{
"path": "Sources/OpenAI/Azure/AzureOpenAIConfiguration.swift",
"content": "//\n// AzureOpenAIConfiguration.swift\n//\n//\n// Created by James Rochabrun on 1/23/24.\n//\n\nimport Foundation\n\n/// [Reference](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference)\npublic struct AzureOpenAIConfiguration {\n public init(\n resourceName: String,\n openAIAPIKey: Authorization,\n apiVersion: String,\n extraHeaders: [String: String]? = nil)\n {\n self.resourceName = resourceName\n self.openAIAPIKey = openAIAPIKey\n self.apiVersion = apiVersion\n self.extraHeaders = extraHeaders\n }\n\n /// The name of your Azure OpenAI Resource.\n let resourceName: String\n\n /// The OpenAI API Key\n let openAIAPIKey: Authorization\n\n /// The API version to use for this operation. This follows the YYYY-MM-DD format.\n let apiVersion: String\n\n /// Azure configuration extra headers for a request.\n let extraHeaders: [String: String]?\n}\n"
},
{
"path": "Sources/OpenAI/Azure/DefaultOpenAIAzureService.swift",
"content": "//\n// DefaultOpenAIAzureService.swift\n//\n//\n// Created by James Rochabrun on 1/23/24.\n//\n\nimport Foundation\n#if os(Linux)\nimport FoundationNetworking\n#endif\n\n// MARK: - DefaultOpenAIAzureService\n\npublic final class DefaultOpenAIAzureService: OpenAIService {\n public init(\n azureConfiguration: AzureOpenAIConfiguration,\n httpClient: HTTPClient,\n decoder: JSONDecoder = .init(),\n debugEnabled: Bool)\n {\n self.httpClient = httpClient\n self.decoder = decoder\n openAIEnvironment = OpenAIEnvironment(\n baseURL: \"https://\\(azureConfiguration.resourceName).openai.azure.com\",\n proxyPath: nil,\n version: nil)\n apiKey = azureConfiguration.openAIAPIKey\n extraHeaders = azureConfiguration.extraHeaders\n initialQueryItems = [.init(name: \"api-version\", value: azureConfiguration.apiVersion)]\n self.debugEnabled = debugEnabled\n }\n\n public let httpClient: HTTPClient\n public let decoder: JSONDecoder\n public let openAIEnvironment: OpenAIEnvironment\n\n public func createTranscription(parameters _: AudioTranscriptionParameters) async throws -> AudioObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func createTranslation(parameters _: AudioTranslationParameters) async throws -> AudioObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func createSpeech(parameters _: AudioSpeechParameters) async throws -> AudioSpeechObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n #if canImport(AVFoundation)\n public func realtimeSession(\n model _: String,\n configuration _: OpenAIRealtimeSessionConfiguration)\n async throws -> OpenAIRealtimeSession\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n #endif\n\n public func startChat(parameters: ChatCompletionParameters) async throws -> ChatCompletionObject {\n var chatParameters = parameters\n chatParameters.stream = false\n let request = try AzureOpenAIAPI.chat(deploymentID: parameters.model).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: chatParameters,\n queryItems: initialQueryItems)\n return try await fetch(debugEnabled: debugEnabled, type: ChatCompletionObject.self, with: request)\n }\n\n public func startStreamedChat(parameters: ChatCompletionParameters) async throws\n -> AsyncThrowingStream\n {\n var chatParameters = parameters\n chatParameters.stream = true\n let request = try AzureOpenAIAPI.chat(deploymentID: parameters.model).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: chatParameters,\n queryItems: initialQueryItems)\n return try await fetchStream(debugEnabled: debugEnabled, type: ChatCompletionChunkObject.self, with: request)\n }\n\n public func createEmbeddings(parameters _: EmbeddingParameter) async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func createFineTuningJob(parameters _: FineTuningJobParameters) async throws -> FineTuningJobObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func listFineTuningJobs(after _: String?, limit _: Int?) async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func retrieveFineTuningJob(id _: String) async throws -> FineTuningJobObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func cancelFineTuningJobWith(id _: String) async throws -> FineTuningJobObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func listFineTuningEventsForJobWith(\n id _: String,\n after _: String?,\n limit _: Int?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func listFiles() async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func uploadFile(parameters _: FileParameters) async throws -> FileObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func deleteFileWith(id _: String) async throws -> DeletionStatus {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func retrieveFileWith(id _: String) async throws -> FileObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func retrieveContentForFileWith(id _: String) async throws -> [[String: Any]] {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func legacyCreateImages(parameters _: ImageCreateParameters) async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func legacyEditImage(parameters _: ImageEditParameters) async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func legacyCreateImageVariations(parameters _: ImageVariationParameters) async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func createImages(\n parameters _: CreateImageParameters)\n async throws -> CreateImageResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func editImage(\n parameters _: CreateImageEditParameters)\n async throws -> CreateImageResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func createImageVariations(\n parameters _: CreateImageVariationParameters)\n async throws -> CreateImageResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func listModels() async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func retrieveModelWith(id _: String) async throws -> ModelObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func deleteFineTuneModelWith(id _: String) async throws -> DeletionStatus {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func createModerationFromText(parameters _: ModerationParameter) async throws -> ModerationObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func createModerationFromTexts(parameters _: ModerationParameter<[String]>) async throws -> ModerationObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func createAssistant(parameters: AssistantParameters) async throws -> AssistantObject {\n let request = try AzureOpenAIAPI.assistant(.create).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: AssistantObject.self, with: request)\n }\n\n public func retrieveAssistant(id: String) async throws -> AssistantObject {\n let request = try AzureOpenAIAPI.assistant(.retrieve(assistantID: id)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .get,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: AssistantObject.self, with: request)\n }\n\n public func modifyAssistant(id: String, parameters: AssistantParameters) async throws -> AssistantObject {\n let request = try AzureOpenAIAPI.assistant(.modify(assistantID: id)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: AssistantObject.self, with: request)\n }\n\n public func deleteAssistant(id: String) async throws -> DeletionStatus {\n let request = try AzureOpenAIAPI.assistant(.delete(assistantID: id)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .delete,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n public func listAssistants(\n limit: Int?,\n order: String?,\n after: String?,\n before: String?)\n async throws -> OpenAIResponse\n {\n var queryItems: [URLQueryItem] = initialQueryItems\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n let request = try AzureOpenAIAPI.assistant(.list).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n public func createThread(parameters: CreateThreadParameters) async throws -> ThreadObject {\n let request = try AzureOpenAIAPI.thread(.create).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: ThreadObject.self, with: request)\n }\n\n public func retrieveThread(id: String) async throws -> ThreadObject {\n let request = try AzureOpenAIAPI.thread(.retrieve(threadID: id)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .get,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: ThreadObject.self, with: request)\n }\n\n public func modifyThread(id: String, parameters: ModifyThreadParameters) async throws -> ThreadObject {\n let request = try AzureOpenAIAPI.thread(.modify(threadID: id)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: ThreadObject.self, with: request)\n }\n\n public func deleteThread(id: String) async throws -> DeletionStatus {\n let request = try AzureOpenAIAPI.thread(.delete(threadID: id)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .delete,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n public func createMessage(threadID: String, parameters: MessageParameter) async throws -> MessageObject {\n let request = try AzureOpenAIAPI.message(.create(threadID: threadID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: MessageObject.self, with: request)\n }\n\n public func retrieveMessage(threadID: String, messageID: String) async throws -> MessageObject {\n let request = try AzureOpenAIAPI.message(.retrieve(threadID: threadID, messageID: messageID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .get,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: MessageObject.self, with: request)\n }\n\n public func modifyMessage(\n threadID: String,\n messageID: String,\n parameters: ModifyMessageParameters)\n async throws -> MessageObject\n {\n let request = try AzureOpenAIAPI.message(.modify(threadID: threadID, messageID: messageID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: MessageObject.self, with: request)\n }\n\n public func deleteMessage(\n threadID: String,\n messageID: String)\n async throws -> DeletionStatus\n {\n let request = try AzureOpenAIAPI.message(.delete(threadID: threadID, messageID: messageID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .delete,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n public func listMessages(\n threadID: String,\n limit: Int?,\n order: String?,\n after: String?,\n before: String?,\n runID: String?)\n async throws -> OpenAIResponse\n {\n var queryItems: [URLQueryItem] = initialQueryItems\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n if let runID {\n queryItems.append(.init(name: \"run_id\", value: runID))\n }\n let request = try AzureOpenAIAPI.message(.list(threadID: threadID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n public func createRun(threadID: String, parameters: RunParameter) async throws -> RunObject {\n let request = try AzureOpenAIAPI.run(.create(threadID: threadID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n public func retrieveRun(threadID: String, runID: String) async throws -> RunObject {\n let request = try AzureOpenAIAPI.run(.retrieve(threadID: threadID, runID: runID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n public func modifyRun(threadID: String, runID: String, parameters: ModifyRunParameters) async throws -> RunObject {\n let request = try AzureOpenAIAPI.run(.modify(threadID: threadID, runID: runID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n public func listRuns(\n threadID: String,\n limit: Int?,\n order: String?,\n after: String?,\n before: String?)\n async throws -> OpenAIResponse\n {\n var queryItems: [URLQueryItem] = initialQueryItems\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n let request = try AzureOpenAIAPI.run(.list(threadID: threadID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n public func cancelRun(threadID: String, runID: String) async throws -> RunObject {\n let request = try AzureOpenAIAPI.run(.cancel(threadID: threadID, runID: runID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n public func submitToolOutputsToRun(\n threadID: String,\n runID: String,\n parameters: RunToolsOutputParameter)\n async throws -> RunObject\n {\n let request = try AzureOpenAIAPI.run(.submitToolOutput(threadID: threadID, runID: runID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n public func createThreadAndRun(parameters: CreateThreadAndRunParameter) async throws -> RunObject {\n let request = try AzureOpenAIAPI.run(.createThreadAndRun).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: RunObject.self, with: request)\n }\n\n public func retrieveRunstep(threadID: String, runID: String, stepID: String) async throws -> RunStepObject {\n let request = try OpenAIAPI.runStep(.retrieve(threadID: threadID, runID: runID, stepID: stepID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .get,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: RunStepObject.self, with: request)\n }\n\n public func listRunSteps(\n threadID: String,\n runID: String,\n limit: Int?,\n order: String?,\n after: String?,\n before: String?)\n async throws -> OpenAIResponse\n {\n var queryItems: [URLQueryItem] = initialQueryItems\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n let request = try AzureOpenAIAPI.runStep(.list(threadID: threadID, runID: runID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n public func createThreadAndRunStream(\n parameters: CreateThreadAndRunParameter)\n async throws -> AsyncThrowingStream\n {\n var runParameters = parameters\n runParameters.stream = true\n let request = try AzureOpenAIAPI.run(.createThreadAndRun).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: runParameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetchAssistantStreamEvents(with: request, debugEnabled: debugEnabled)\n }\n\n public func createRunStream(\n threadID: String,\n parameters: RunParameter)\n async throws -> AsyncThrowingStream\n {\n var runParameters = parameters\n runParameters.stream = true\n let request = try AzureOpenAIAPI.run(.create(threadID: threadID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: runParameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetchAssistantStreamEvents(with: request, debugEnabled: debugEnabled)\n }\n\n public func submitToolOutputsToRunStream(\n threadID: String,\n runID: String,\n parameters: RunToolsOutputParameter)\n async throws -> AsyncThrowingStream\n {\n var runToolsOutputParameter = parameters\n runToolsOutputParameter.stream = true\n let request = try AzureOpenAIAPI.run(.submitToolOutput(threadID: threadID, runID: runID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: runToolsOutputParameter,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetchAssistantStreamEvents(with: request, debugEnabled: debugEnabled)\n }\n\n // MARK: Batch\n\n public func createBatch(\n parameters _: BatchParameter)\n async throws -> BatchObject\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func retrieveBatch(\n id _: String)\n async throws -> BatchObject\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func cancelBatch(\n id _: String)\n async throws -> BatchObject\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func listBatch(\n after _: String?,\n limit _: Int?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n // MARK: Vector Store\n\n public func createVectorStore(\n parameters: VectorStoreParameter)\n async throws -> VectorStoreObject\n {\n let request = try AzureOpenAIAPI.vectorStore(.create).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreObject.self, with: request)\n }\n\n public func listVectorStores(\n limit: Int?,\n order: String?,\n after: String?,\n before: String?)\n async throws -> OpenAIResponse\n {\n var queryItems: [URLQueryItem] = initialQueryItems\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n let request = try AzureOpenAIAPI.vectorStore(.list).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n public func retrieveVectorStore(\n id: String)\n async throws -> VectorStoreObject\n {\n let request = try AzureOpenAIAPI.vectorStore(.retrieve(vectorStoreID: id)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .get,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreObject.self, with: request)\n }\n\n public func modifyVectorStore(\n parameters: VectorStoreParameter,\n id: String)\n async throws -> VectorStoreObject\n {\n let request = try AzureOpenAIAPI.vectorStore(.modify(vectorStoreID: id)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreObject.self, with: request)\n }\n\n public func deleteVectorStore(\n id: String)\n async throws -> DeletionStatus\n {\n let request = try AzureOpenAIAPI.vectorStore(.delete(vectorStoreID: id)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .delete,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n // MARK: Vector Store Files\n\n public func createVectorStoreFile(\n vectorStoreID: String,\n parameters: VectorStoreFileParameter)\n async throws -> VectorStoreFileObject\n {\n let request = try AzureOpenAIAPI.vectorStoreFile(.create(vectorStoreID: vectorStoreID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: parameters,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreFileObject.self, with: request)\n }\n\n public func listVectorStoreFiles(\n vectorStoreID: String,\n limit: Int?,\n order: String?,\n after: String?,\n before: String?,\n filter: String?)\n async throws -> OpenAIResponse\n {\n var queryItems: [URLQueryItem] = initialQueryItems\n if let limit {\n queryItems.append(.init(name: \"limit\", value: \"\\(limit)\"))\n }\n if let order {\n queryItems.append(.init(name: \"order\", value: order))\n }\n if let after {\n queryItems.append(.init(name: \"after\", value: after))\n }\n if let before {\n queryItems.append(.init(name: \"before\", value: before))\n }\n if let filter {\n queryItems.append(.init(name: \"filter\", value: filter))\n }\n let request = try AzureOpenAIAPI.vectorStoreFile(.list(vectorStoreID: vectorStoreID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .get,\n queryItems: queryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: OpenAIResponse.self, with: request)\n }\n\n public func retrieveVectorStoreFile(vectorStoreID: String, fileID: String) async throws -> VectorStoreFileObject {\n let request = try AzureOpenAIAPI.vectorStoreFile(.retrieve(vectorStoreID: vectorStoreID, fileID: fileID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .get,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: VectorStoreFileObject.self, with: request)\n }\n\n public func deleteVectorStoreFile(vectorStoreID: String, fileID: String) async throws -> DeletionStatus {\n let request = try AzureOpenAIAPI.vectorStoreFile(.delete(vectorStoreID: vectorStoreID, fileID: fileID)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .delete,\n queryItems: initialQueryItems,\n betaHeaderField: Self.assistantsBetaV2,\n extraHeaders: extraHeaders)\n return try await fetch(debugEnabled: debugEnabled, type: DeletionStatus.self, with: request)\n }\n\n public func createVectorStoreFileBatch(\n vectorStoreID _: String,\n parameters _: VectorStoreFileBatchParameter)\n async throws -> VectorStoreFileBatchObject\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func retrieveVectorStoreFileBatch(\n vectorStoreID _: String,\n batchID _: String)\n async throws -> VectorStoreFileBatchObject\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func cancelVectorStoreFileBatch(vectorStoreID _: String, batchID _: String) async throws -> VectorStoreFileBatchObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n public func listVectorStoreFilesInABatch(\n vectorStoreID _: String,\n batchID _: String,\n limit _: Int?,\n order _: String?,\n after _: String?,\n before _: String?,\n filter _: String?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n // MARK: Response\n\n public func responseCreate(\n _ parameters: ModelResponseParameter)\n async throws -> ResponseModel\n {\n var responseParameters = parameters\n responseParameters.stream = false\n let request = try AzureOpenAIAPI.response(.create(deploymentID: parameters.model)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: responseParameters,\n queryItems: initialQueryItems)\n return try await fetch(debugEnabled: debugEnabled, type: ResponseModel.self, with: request)\n }\n\n public func responseModel(\n id: String,\n parameters _: GetResponseParameter?)\n async throws -> ResponseModel\n {\n let request = try AzureOpenAIAPI.response(.retrieve(responseID: id)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n queryItems: initialQueryItems)\n return try await fetch(debugEnabled: debugEnabled, type: ResponseModel.self, with: request)\n }\n\n public func responseModelStream(\n id _: String,\n parameters _: GetResponseParameter?)\n async throws -> AsyncThrowingStream\n {\n fatalError(\"responseModelStream not implemented for Azure OpenAI Service\")\n }\n\n public func responseCreateStream(\n _ parameters: ModelResponseParameter)\n async throws -> AsyncThrowingStream\n {\n var responseParameters = parameters\n responseParameters.stream = true\n let request = try AzureOpenAIAPI.response(.create(deploymentID: parameters.model)).request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: responseParameters,\n queryItems: initialQueryItems)\n return try await fetchStream(debugEnabled: debugEnabled, type: ResponseStreamEvent.self, with: request)\n }\n\n public func responseDelete(\n id _: String)\n async throws -> DeletionStatus\n {\n fatalError(\"responseDelete not implemented for Azure OpenAI Service\")\n }\n\n public func responseCancel(\n id _: String)\n async throws -> ResponseModel\n {\n fatalError(\"responseCancel not implemented for Azure OpenAI Service\")\n }\n\n public func responseInputItems(\n id _: String,\n parameters _: GetInputItemsParameter?)\n async throws -> OpenAIResponse\n {\n fatalError(\"responseInputItems not implemented for Azure OpenAI Service\")\n }\n\n // MARK: - Conversations\n\n public func conversationCreate(\n parameters _: CreateConversationParameter?)\n async throws -> ConversationModel\n {\n fatalError(\"conversationCreate not implemented for Azure OpenAI Service\")\n }\n\n public func getConversation(\n id _: String)\n async throws -> ConversationModel\n {\n fatalError(\"getConversation not implemented for Azure OpenAI Service\")\n }\n\n public func updateConversation(\n id _: String,\n parameters _: UpdateConversationParameter)\n async throws -> ConversationModel\n {\n fatalError(\"updateConversation not implemented for Azure OpenAI Service\")\n }\n\n public func deleteConversation(\n id _: String)\n async throws -> DeletionStatus\n {\n fatalError(\"deleteConversation not implemented for Azure OpenAI Service\")\n }\n\n public func getConversationItems(\n id _: String,\n parameters _: GetConversationItemsParameter?)\n async throws -> OpenAIResponse\n {\n fatalError(\"getConversationItems not implemented for Azure OpenAI Service\")\n }\n\n public func createConversationItems(\n id _: String,\n parameters _: CreateConversationItemsParameter)\n async throws -> OpenAIResponse\n {\n fatalError(\"createConversationItems not implemented for Azure OpenAI Service\")\n }\n\n public func getConversationItem(\n conversationID _: String,\n itemID _: String,\n parameters _: GetConversationItemParameter?)\n async throws -> InputItem\n {\n fatalError(\"getConversationItem not implemented for Azure OpenAI Service\")\n }\n\n public func deleteConversationItem(\n conversationID _: String,\n itemID _: String)\n async throws -> ConversationModel\n {\n fatalError(\"deleteConversationItem not implemented for Azure OpenAI Service\")\n }\n\n private static let assistantsBetaV2 = \"assistants=v2\"\n\n private let apiKey: Authorization\n private let initialQueryItems: [URLQueryItem]\n /// Set this flag to TRUE if you need to print request events in DEBUG builds.\n private let debugEnabled: Bool\n\n /// Assistants API\n private let extraHeaders: [String: String]?\n}\n"
},
{
"path": "Sources/OpenAI/LocalModelService/LocalModelAPI.swift",
"content": "//\n// LocalModelAPI.swift\n//\n//\n// Created by James Rochabrun on 6/30/24.\n//\n\nimport Foundation\n\n// MARK: - LocalModelAPI\n\nenum LocalModelAPI {\n case chat\n}\n\n// MARK: Endpoint\n\nextension LocalModelAPI: Endpoint {\n /// Builds the final path that includes:\n /// - optional proxy path (e.g. \"/my-proxy\")\n /// - version if non-nil (e.g. \"/v1\")\n /// - then the specific endpoint path (e.g. \"/assistants\")\n func path(in openAIEnvironment: OpenAIEnvironment) -> String {\n // 1) Potentially prepend proxy path if `proxyPath` is non-empty\n let proxyPart =\n if let envProxyPart = openAIEnvironment.proxyPath, !envProxyPart.isEmpty {\n \"/\\(envProxyPart)\"\n } else {\n \"\"\n }\n let mainPart = openAIPath(in: openAIEnvironment)\n\n return proxyPart + mainPart // e.g. \"/my-proxy/v1/assistants\"\n }\n\n func openAIPath(in openAIEnvironment: OpenAIEnvironment) -> String {\n let version =\n if let envOverrideVersion = openAIEnvironment.version, !envOverrideVersion.isEmpty {\n \"/\\(envOverrideVersion)\"\n } else {\n \"\"\n }\n switch self {\n case .chat: return \"\\(version)/chat/completions\"\n }\n }\n}\n"
},
{
"path": "Sources/OpenAI/LocalModelService/LocalModelService.swift",
"content": "//\n// LocalModelService.swift\n//\n//\n// Created by James Rochabrun on 6/30/24.\n//\n\nimport Foundation\n\nstruct LocalModelService: OpenAIService {\n init(\n apiKey: Authorization = .apiKey(\"\"),\n baseURL: String,\n proxyPath: String? = nil,\n overrideVersion: String? = nil,\n httpClient: HTTPClient,\n decoder: JSONDecoder = .init(),\n debugEnabled: Bool)\n {\n self.httpClient = httpClient\n self.decoder = decoder\n self.apiKey = apiKey\n openAIEnvironment = OpenAIEnvironment(baseURL: baseURL, proxyPath: proxyPath, version: overrideVersion ?? \"v1\")\n self.debugEnabled = debugEnabled\n }\n\n let httpClient: HTTPClient\n let decoder: JSONDecoder\n let openAIEnvironment: OpenAIEnvironment\n\n func createImages(\n parameters _: CreateImageParameters)\n async throws -> CreateImageResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func editImage(\n parameters _: CreateImageEditParameters)\n async throws -> CreateImageResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createImageVariations(\n parameters _: CreateImageVariationParameters)\n async throws -> CreateImageResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createTranscription(parameters _: AudioTranscriptionParameters) async throws -> AudioObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createTranslation(parameters _: AudioTranslationParameters) async throws -> AudioObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createSpeech(parameters _: AudioSpeechParameters) async throws -> AudioSpeechObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n #if canImport(AVFoundation)\n func realtimeSession(\n model _: String,\n configuration _: OpenAIRealtimeSessionConfiguration)\n async throws -> OpenAIRealtimeSession\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n #endif\n\n func startChat(\n parameters: ChatCompletionParameters)\n async throws -> ChatCompletionObject\n {\n var chatParameters = parameters\n chatParameters.stream = false\n let request = try LocalModelAPI.chat.request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: chatParameters)\n return try await fetch(debugEnabled: debugEnabled, type: ChatCompletionObject.self, with: request)\n }\n\n func startStreamedChat(\n parameters: ChatCompletionParameters)\n async throws -> AsyncThrowingStream\n {\n var chatParameters = parameters\n chatParameters.stream = true\n chatParameters.streamOptions = .init(includeUsage: true)\n let request = try LocalModelAPI.chat.request(\n apiKey: apiKey,\n openAIEnvironment: openAIEnvironment,\n organizationID: nil,\n method: .post,\n params: chatParameters)\n return try await fetchStream(debugEnabled: debugEnabled, type: ChatCompletionChunkObject.self, with: request)\n }\n\n func createEmbeddings(parameters _: EmbeddingParameter) async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createFineTuningJob(parameters _: FineTuningJobParameters) async throws -> FineTuningJobObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listFineTuningJobs(after _: String?, limit _: Int?) async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveFineTuningJob(id _: String) async throws -> FineTuningJobObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func cancelFineTuningJobWith(id _: String) async throws -> FineTuningJobObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listFineTuningEventsForJobWith(\n id _: String,\n after _: String?,\n limit _: Int?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listFiles() async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func uploadFile(parameters _: FileParameters) async throws -> FileObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func deleteFileWith(id _: String) async throws -> DeletionStatus {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveFileWith(id _: String) async throws -> FileObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveContentForFileWith(id _: String) async throws -> [[String: Any]] {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func legacyCreateImages(parameters _: ImageCreateParameters) async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func legacyEditImage(parameters _: ImageEditParameters) async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func legacyCreateImageVariations(parameters _: ImageVariationParameters) async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listModels() async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveModelWith(id _: String) async throws -> ModelObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func deleteFineTuneModelWith(id _: String) async throws -> DeletionStatus {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createModerationFromText(parameters _: ModerationParameter) async throws -> ModerationObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createModerationFromTexts(parameters _: ModerationParameter<[String]>) async throws -> ModerationObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createAssistant(parameters _: AssistantParameters) async throws -> AssistantObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveAssistant(id _: String) async throws -> AssistantObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func modifyAssistant(id _: String, parameters _: AssistantParameters) async throws -> AssistantObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func deleteAssistant(id _: String) async throws -> DeletionStatus {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listAssistants(\n limit _: Int?,\n order _: String?,\n after _: String?,\n before _: String?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createThread(parameters _: CreateThreadParameters) async throws -> ThreadObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveThread(id _: String) async throws -> ThreadObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func modifyThread(id _: String, parameters _: ModifyThreadParameters) async throws -> ThreadObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func deleteThread(id _: String) async throws -> DeletionStatus {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createMessage(threadID _: String, parameters _: MessageParameter) async throws -> MessageObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveMessage(threadID _: String, messageID _: String) async throws -> MessageObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func modifyMessage(\n threadID _: String,\n messageID _: String,\n parameters _: ModifyMessageParameters)\n async throws -> MessageObject\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func deleteMessage(threadID _: String, messageID _: String) async throws -> DeletionStatus {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listMessages(\n threadID _: String,\n limit _: Int?,\n order _: String?,\n after _: String?,\n before _: String?,\n runID _: String?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createRun(threadID _: String, parameters _: RunParameter) async throws -> RunObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveRun(threadID _: String, runID _: String) async throws -> RunObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func modifyRun(threadID _: String, runID _: String, parameters _: ModifyRunParameters) async throws -> RunObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listRuns(\n threadID _: String,\n limit _: Int?,\n order _: String?,\n after _: String?,\n before _: String?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func cancelRun(threadID _: String, runID _: String) async throws -> RunObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func submitToolOutputsToRun(\n threadID _: String,\n runID _: String,\n parameters _: RunToolsOutputParameter)\n async throws -> RunObject\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createThreadAndRun(parameters _: CreateThreadAndRunParameter) async throws -> RunObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveRunstep(threadID _: String, runID _: String, stepID _: String) async throws -> RunStepObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listRunSteps(\n threadID _: String,\n runID _: String,\n limit _: Int?,\n order _: String?,\n after _: String?,\n before _: String?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createThreadAndRunStream(parameters _: CreateThreadAndRunParameter) async throws\n -> AsyncThrowingStream\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createRunStream(\n threadID _: String,\n parameters _: RunParameter)\n async throws -> AsyncThrowingStream\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func submitToolOutputsToRunStream(\n threadID _: String,\n runID _: String,\n parameters _: RunToolsOutputParameter)\n async throws -> AsyncThrowingStream\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createBatch(parameters _: BatchParameter) async throws -> BatchObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveBatch(id _: String) async throws -> BatchObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func cancelBatch(id _: String) async throws -> BatchObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listBatch(after _: String?, limit _: Int?) async throws -> OpenAIResponse {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createVectorStore(parameters _: VectorStoreParameter) async throws -> VectorStoreObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listVectorStores(\n limit _: Int?,\n order _: String?,\n after _: String?,\n before _: String?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveVectorStore(id _: String) async throws -> VectorStoreObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func modifyVectorStore(parameters _: VectorStoreParameter, id _: String) async throws -> VectorStoreObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func deleteVectorStore(id _: String) async throws -> DeletionStatus {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createVectorStoreFile(\n vectorStoreID _: String,\n parameters _: VectorStoreFileParameter)\n async throws -> VectorStoreFileObject\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listVectorStoreFiles(\n vectorStoreID _: String,\n limit _: Int?,\n order _: String?,\n after _: String?,\n before _: String?,\n filter _: String?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveVectorStoreFile(vectorStoreID _: String, fileID _: String) async throws -> VectorStoreFileObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func deleteVectorStoreFile(vectorStoreID _: String, fileID _: String) async throws -> DeletionStatus {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createVectorStoreFileBatch(\n vectorStoreID _: String,\n parameters _: VectorStoreFileBatchParameter)\n async throws -> VectorStoreFileBatchObject\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func retrieveVectorStoreFileBatch(vectorStoreID _: String, batchID _: String) async throws -> VectorStoreFileBatchObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func cancelVectorStoreFileBatch(vectorStoreID _: String, batchID _: String) async throws -> VectorStoreFileBatchObject {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func listVectorStoreFilesInABatch(\n vectorStoreID _: String,\n batchID _: String,\n limit _: Int?,\n order _: String?,\n after _: String?,\n before _: String?,\n filter _: String?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n // MARK: Response\n\n func responseCreate(\n _: ModelResponseParameter)\n async throws -> ResponseModel\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func responseModel(\n id _: String,\n parameters _: GetResponseParameter?)\n async throws -> ResponseModel\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func responseModelStream(\n id _: String,\n parameters _: GetResponseParameter?)\n async throws -> AsyncThrowingStream\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func responseCreateStream(\n _: ModelResponseParameter)\n async throws -> AsyncThrowingStream\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func responseDelete(\n id _: String)\n async throws -> DeletionStatus\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func responseCancel(\n id _: String)\n async throws -> ResponseModel\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func responseInputItems(\n id _: String,\n parameters _: GetInputItemsParameter?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n // MARK: - Conversations\n\n func conversationCreate(\n parameters _: CreateConversationParameter?)\n async throws -> ConversationModel\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func getConversation(\n id _: String)\n async throws -> ConversationModel\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func updateConversation(\n id _: String,\n parameters _: UpdateConversationParameter)\n async throws -> ConversationModel\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func deleteConversation(\n id _: String)\n async throws -> DeletionStatus\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func getConversationItems(\n id _: String,\n parameters _: GetConversationItemsParameter?)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func createConversationItems(\n id _: String,\n parameters _: CreateConversationItemsParameter)\n async throws -> OpenAIResponse\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func getConversationItem(\n conversationID _: String,\n itemID _: String,\n parameters _: GetConversationItemParameter?)\n async throws -> InputItem\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n func deleteConversationItem(\n conversationID _: String,\n itemID _: String)\n async throws -> ConversationModel\n {\n fatalError(\n \"Currently, this API is not supported. We welcome and encourage contributions to our open-source project. Please consider opening an issue or submitting a pull request to add support for this feature.\")\n }\n\n /// [authentication](https://platform.openai.com/docs/api-reference/authentication)\n private let apiKey: Authorization\n /// Set this flag to TRUE if you need to print request events in DEBUG builds.\n private let debugEnabled: Bool\n}\n"
},
{
"path": "Sources/OpenAI/Private/Audio/AudioPCMPlayer.swift",
"content": "//\n// AudioPCMPlayer.swift\n// SwiftOpenAI\n//\n// Created from AIProxySwift\n// Original: https://github.com/lzell/AIProxySwift\n//\n\n#if canImport(AVFoundation)\nimport AVFoundation\nimport Foundation\nimport OSLog\n\nprivate let logger = Logger(subsystem: \"com.swiftopenai\", category: \"Audio\")\n\n// MARK: - AudioPCMPlayer\n\n/// # Warning\n/// The order that you initialize `AudioPCMPlayer()` and `MicrophonePCMSampleVendor()` matters, unfortunately.\n///\n/// The voice processing audio unit on iOS has a volume bug that is not present on macOS.\n/// The volume of playback depends on the initialization order of AVAudioEngine and the `kAudioUnitSubType_VoiceProcessingIO` Audio Unit.\n/// We use AudioEngine for playback in this file, and the voice processing audio unit in MicrophonePCMSampleVendor.\n///\n/// I find the best result to be initializing `AudioPCMPlayer()` first. Otherwise, the playback volume is too quiet on iOS.\n@RealtimeActor\nfinal class AudioPCMPlayer {\n\n init(audioEngine: AVAudioEngine) async throws {\n self.audioEngine = audioEngine\n guard\n let inputFormat = AVAudioFormat(\n commonFormat: .pcmFormatInt16,\n sampleRate: 24000,\n channels: 1,\n interleaved: true)\n else {\n throw AudioPCMPlayerError.couldNotConfigureAudioEngine(\n \"Could not create input format for AudioPCMPlayer\")\n }\n\n guard\n let playableFormat = AVAudioFormat(\n commonFormat: .pcmFormatFloat32,\n sampleRate: 24000,\n channels: 1,\n interleaved: true)\n else {\n throw AudioPCMPlayerError.couldNotConfigureAudioEngine(\n \"Could not create playback format for AudioPCMPlayer\")\n }\n\n let node = AVAudioPlayerNode()\n\n audioEngine.attach(node)\n audioEngine.connect(node, to: audioEngine.outputNode, format: playableFormat)\n\n playerNode = node\n self.inputFormat = inputFormat\n self.playableFormat = playableFormat\n }\n\n deinit {\n logger.debug(\"AudioPCMPlayer is being freed\")\n }\n\n public func playPCM16Audio(from base64String: String) {\n guard let audioData = Data(base64Encoded: base64String) else {\n logger.error(\"Could not decode base64 string for audio playback\")\n return\n }\n\n var bufferList = AudioBufferList(\n mNumberBuffers: 1,\n mBuffers:\n AudioBuffer(\n mNumberChannels: 1,\n mDataByteSize: UInt32(audioData.count),\n mData: UnsafeMutableRawPointer(mutating: (audioData as NSData).bytes)))\n\n guard\n let inPCMBuf = AVAudioPCMBuffer(\n pcmFormat: inputFormat,\n bufferListNoCopy: &bufferList)\n else {\n logger.error(\"Could not create input buffer for audio playback\")\n return\n }\n\n guard\n let outPCMBuf = AVAudioPCMBuffer(\n pcmFormat: playableFormat,\n frameCapacity: AVAudioFrameCount(UInt32(audioData.count) * 2))\n else {\n logger.error(\"Could not create output buffer for audio playback\")\n return\n }\n\n guard let converter = AVAudioConverter(from: inputFormat, to: playableFormat) else {\n logger.error(\"Could not create audio converter needed to map from pcm16int to pcm32float\")\n return\n }\n\n do {\n try converter.convert(to: outPCMBuf, from: inPCMBuf)\n } catch {\n logger.error(\"Could not map from pcm16int to pcm32float: \\(error.localizedDescription)\")\n return\n }\n\n if audioEngine.isRunning {\n playerNode.scheduleBuffer(outPCMBuf, at: nil, options: [], completionHandler: { })\n playerNode.play()\n }\n }\n\n public func interruptPlayback() {\n logger.debug(\"Interrupting playback\")\n playerNode.stop()\n }\n\n let audioEngine: AVAudioEngine\n\n private let inputFormat: AVAudioFormat\n private let playableFormat: AVAudioFormat\n private let playerNode: AVAudioPlayerNode\n\n}\n#endif\n"
},
{
"path": "Sources/OpenAI/Private/Audio/AudioPCMPlayerError.swift",
"content": "//\n// AudioPCMPlayerError.swift\n// SwiftOpenAI\n//\n// Created from AIProxySwift\n// Original: https://github.com/lzell/AIProxySwift\n//\n\nimport Foundation\n\npublic enum AudioPCMPlayerError: LocalizedError, Sendable {\n case couldNotConfigureAudioEngine(String)\n\n public var errorDescription: String? {\n switch self {\n case .couldNotConfigureAudioEngine(let message):\n message\n }\n }\n}\n"
},
{
"path": "Sources/OpenAI/Private/Audio/AudioUtils.swift",
"content": "//\n// AudioUtils.swift\n// SwiftOpenAI\n//\n// Created from AIProxySwift\n// Original: https://github.com/lzell/AIProxySwift\n//\n\n#if canImport(AVFoundation)\nimport AVFoundation\nimport Foundation\nimport OSLog\n\n#if canImport(AudioToolbox)\nimport AudioToolbox\n#endif\n\nprivate let logger = Logger(subsystem: \"com.swiftopenai\", category: \"Audio\")\n\n// MARK: - AudioUtils\n\npublic enum AudioUtils {\n\n nonisolated public static var headphonesConnected: Bool {\n #if os(macOS)\n return audioToolboxHeadphonesConnected()\n #else\n return audioSessionHeadphonesConnected()\n #endif\n }\n\n /// Encodes an AVAudioPCMBuffer to base64 string for transmission to OpenAI\n nonisolated public static func base64EncodeAudioPCMBuffer(from buffer: AVAudioPCMBuffer) -> String? {\n guard buffer.format.channelCount == 1 else {\n logger.error(\"This encoding routine assumes a single channel\")\n return nil\n }\n\n guard let audioBufferPtr = buffer.audioBufferList.pointee.mBuffers.mData else {\n logger.error(\"No audio buffer list available to encode\")\n return nil\n }\n\n let audioBufferLength = Int(buffer.audioBufferList.pointee.mBuffers.mDataByteSize)\n return Data(bytes: audioBufferPtr, count: audioBufferLength).base64EncodedString()\n }\n\n #if os(macOS)\n nonisolated static func getDefaultAudioInputDevice() -> AudioDeviceID? {\n var deviceID = AudioDeviceID()\n var propSize = UInt32(MemoryLayout.size)\n var address = AudioObjectPropertyAddress(\n mSelector: kAudioHardwarePropertyDefaultInputDevice,\n mScope: kAudioObjectPropertyScopeGlobal,\n mElement: kAudioObjectPropertyElementMain)\n let err = AudioObjectGetPropertyData(\n AudioObjectID(kAudioObjectSystemObject),\n &address,\n 0,\n nil,\n &propSize,\n &deviceID)\n guard err == noErr else {\n logger.error(\"Could not query for default audio input device\")\n return nil\n }\n return deviceID\n }\n\n nonisolated static func getAllAudioInputDevices() -> [AudioDeviceID] {\n var propSize: UInt32 = 0\n var address = AudioObjectPropertyAddress(\n mSelector: kAudioHardwarePropertyDevices,\n mScope: kAudioObjectPropertyScopeGlobal,\n mElement: kAudioObjectPropertyElementMain)\n var err = AudioObjectGetPropertyDataSize(\n AudioObjectID(kAudioObjectSystemObject),\n &address,\n 0,\n nil,\n &propSize)\n guard err == noErr else {\n logger.error(\"Could not set propSize, needed for querying all audio devices\")\n return []\n }\n\n var devices = [AudioDeviceID](\n repeating: 0,\n count: Int(propSize / UInt32(MemoryLayout.size)))\n err = AudioObjectGetPropertyData(\n AudioObjectID(kAudioObjectSystemObject),\n &address,\n 0,\n nil,\n &propSize,\n &devices)\n guard err == noErr else {\n logger.error(\"Could not query for all audio devices\")\n return []\n }\n return devices\n }\n #endif\n\n}\n\n#if !os(macOS)\nnonisolated private func audioSessionHeadphonesConnected() -> Bool {\n let session = AVAudioSession.sharedInstance()\n let outputs = session.currentRoute.outputs\n\n for output in outputs {\n if\n output.portType == .headphones ||\n output.portType == .bluetoothA2DP ||\n output.portType == .bluetoothLE ||\n output.portType == .bluetoothHFP\n {\n return true\n }\n }\n return false\n}\n#endif\n\n#if os(macOS)\nnonisolated private func audioToolboxHeadphonesConnected() -> Bool {\n for deviceID in AudioUtils.getAllAudioInputDevices() {\n if isHeadphoneDevice(deviceID: deviceID), isDeviceAlive(deviceID: deviceID) {\n return true\n }\n }\n return false\n}\n\nnonisolated private func isHeadphoneDevice(deviceID: AudioDeviceID) -> Bool {\n guard hasOutputStreams(deviceID: deviceID) else {\n return false\n }\n\n let transportType = getTransportType(deviceID: deviceID)\n\n if\n [\n kAudioDeviceTransportTypeBluetooth,\n kAudioDeviceTransportTypeBluetoothLE,\n kAudioDeviceTransportTypeUSB,\n ].contains(transportType)\n {\n return true\n }\n\n // For built-in devices, we need to check the device name or UID\n if transportType == kAudioDeviceTransportTypeBuiltIn {\n return isBuiltInHeadphonePort(deviceID: deviceID)\n }\n\n return false\n}\n\nnonisolated private func getTransportType(deviceID: AudioDeviceID) -> UInt32 {\n var transportType = UInt32(0)\n var propSize = UInt32(MemoryLayout.size)\n var address = AudioObjectPropertyAddress(\n mSelector: kAudioDevicePropertyTransportType,\n mScope: kAudioObjectPropertyScopeGlobal,\n mElement: kAudioObjectPropertyElementMain)\n let err = AudioObjectGetPropertyData(\n deviceID,\n &address,\n 0,\n nil,\n &propSize,\n &transportType)\n guard err == noErr else {\n logger.error(\"Could not get transport type for audio device\")\n return 0\n }\n return transportType\n}\n\nnonisolated private func isBuiltInHeadphonePort(deviceID: AudioDeviceID) -> Bool {\n var deviceUID: CFString? = nil\n var propSize = UInt32(MemoryLayout.size)\n var address = AudioObjectPropertyAddress(\n mSelector: kAudioDevicePropertyDeviceUID,\n mScope: kAudioObjectPropertyScopeGlobal,\n mElement: kAudioObjectPropertyElementMain)\n\n let err = withUnsafeMutablePointer(to: &deviceUID) { ptr -> OSStatus in\n return AudioObjectGetPropertyData(\n deviceID,\n &address,\n 0,\n nil,\n &propSize,\n ptr)\n }\n\n guard err == noErr, let uidString = deviceUID as? String else {\n logger.error(\"Could not get mic's uidString from CFString\")\n return false\n }\n\n return [\"headphone\", \"lineout\"].contains { uidString.lowercased().contains($0) }\n}\n\nnonisolated private func hasOutputStreams(deviceID: AudioDeviceID) -> Bool {\n var address = AudioObjectPropertyAddress(\n mSelector: kAudioDevicePropertyStreams,\n mScope: kAudioObjectPropertyScopeOutput,\n mElement: kAudioObjectPropertyElementMain)\n var propSize: UInt32 = 0\n let err = AudioObjectGetPropertyDataSize(\n deviceID,\n &address,\n 0,\n nil,\n &propSize)\n guard err == noErr else {\n logger.error(\"Could not check for output streams on audio device\")\n return false\n }\n return propSize > 0\n}\n\nnonisolated private func isDeviceAlive(deviceID: AudioDeviceID) -> Bool {\n var isAlive: UInt32 = 0\n var propSize = UInt32(MemoryLayout.size)\n var address = AudioObjectPropertyAddress(\n mSelector: kAudioDevicePropertyDeviceIsAlive,\n mScope: kAudioObjectPropertyScopeGlobal,\n mElement: kAudioObjectPropertyElementMain)\n let err = AudioObjectGetPropertyData(\n deviceID,\n &address,\n 0,\n nil,\n &propSize,\n &isAlive)\n guard err == noErr else {\n logger.error(\"Could not check if the audio input is alive\")\n return false\n }\n return isAlive != 0\n}\n#endif\n#endif\n"
},
{
"path": "Sources/OpenAI/Private/Audio/MicrophonePCMSampleVendor.swift",
"content": "//\n// MicrophonePCMSampleVendor.swift\n// SwiftOpenAI\n//\n// Created from AIProxySwift\n// Original: https://github.com/lzell/AIProxySwift\n//\n\n#if canImport(AVFoundation)\nimport AVFoundation\n\n@RealtimeActor\nprotocol MicrophonePCMSampleVendor: AnyObject {\n func start() throws -> AsyncStream\n func stop()\n}\n#endif\n"
},
{
"path": "Sources/OpenAI/Private/Audio/MicrophonePCMSampleVendorAE.swift",
"content": "//\n// MicrophonePCMSampleVendorAE.swift\n// SwiftOpenAI\n//\n// Created from AIProxySwift\n// Original: https://github.com/lzell/AIProxySwift\n//\n\n#if canImport(AVFoundation)\n@preconcurrency import AVFoundation\nimport Foundation\nimport OSLog\n\nprivate let logger = Logger(subsystem: \"com.swiftopenai\", category: \"Audio\")\n\n// MARK: - MicrophonePCMSampleVendorAE\n\n/// This is an AVAudioEngine-based implementation that vends PCM16 microphone samples.\n///\n/// ## Requirements\n///\n/// - Assumes an `NSMicrophoneUsageDescription` description has been added to Target > Info\n/// - Assumes that microphone permissions have already been granted\n///\n/// #Usage\n///\n/// ```\n/// let microphoneVendor = try MicrophonePCMSampleVendorAE()\n/// let micStream = try microphoneVendor.start()\n/// Task {\n/// for await buffer in micStream {\n/// // Use buffer\n/// }\n/// }\n/// // ... some time later ...\n/// microphoneVendor.stop()\n/// ```\n///\n/// References:\n/// Apple sample code: https://developer.apple.com/documentation/avfaudio/using-voice-processing\n/// Apple technical note: https://developer.apple.com/documentation/technotes/tn3136-avaudioconverter-performing-sample-rate-conversions\n/// My apple forum question: https://developer.apple.com/forums/thread/771530\n@RealtimeActor\nclass MicrophonePCMSampleVendorAE: MicrophonePCMSampleVendor {\n init(audioEngine: AVAudioEngine) throws {\n self.audioEngine = audioEngine\n inputNode = self.audioEngine.inputNode\n\n if !AudioUtils.headphonesConnected {\n try inputNode.setVoiceProcessingEnabled(true)\n }\n\n let debugText = \"\"\"\n Using AudioEngine based PCM sample vendor.\n The input node's input format is: \\(inputNode.inputFormat(forBus: 0))\n The input node's output format is: \\(inputNode.outputFormat(forBus: 0))\n \"\"\"\n logger.debug(\"\\(debugText)\")\n }\n\n deinit {\n logger.debug(\"MicrophonePCMSampleVendorAE is being freed\")\n }\n\n func start() throws -> AsyncStream {\n guard\n let desiredTapFormat = AVAudioFormat(\n commonFormat: .pcmFormatInt16,\n sampleRate: inputNode.outputFormat(forBus: 0).sampleRate,\n channels: 1,\n interleaved: false)\n else {\n throw OpenAIError.audioConfigurationError(\"Could not create the desired tap format for realtime\")\n }\n\n // The buffer size argument specifies the target number of audio frames.\n // For a single channel, a single audio frame has a single audio sample.\n //\n // Try to get 50ms updates.\n // 50ms is half the granularity of our target accumulator (we accumulate into 100ms payloads that we send up to OpenAI)\n //\n // There is a note on the installTap documentation that says AudioEngine may\n // adjust the bufferSize internally.\n let targetBufferSize = UInt32(desiredTapFormat.sampleRate / 20) // 50ms buffers\n logger.info(\"PCMSampleVendorAE target buffer size is: \\(targetBufferSize)\")\n\n return AsyncStream { [weak self] continuation in\n guard let this = self else { return }\n this.continuation = continuation\n this.installTapNonIsolated(\n inputNode: this.inputNode,\n bufferSize: targetBufferSize,\n format: desiredTapFormat)\n }\n }\n\n func stop() {\n continuation?.finish()\n continuation = nil\n inputNode.removeTap(onBus: 0)\n try? inputNode.setVoiceProcessingEnabled(false)\n microphonePCMSampleVendorCommon.audioConverter = nil\n }\n\n private let audioEngine: AVAudioEngine\n private let inputNode: AVAudioInputNode\n private let microphonePCMSampleVendorCommon = MicrophonePCMSampleVendorCommon()\n private var continuation: AsyncStream.Continuation?\n\n private nonisolated func installTapNonIsolated(\n inputNode: AVAudioInputNode,\n bufferSize: AVAudioFrameCount,\n format: AVAudioFormat)\n {\n inputNode.installTap(onBus: 0, bufferSize: bufferSize, format: format) { [weak self] sampleBuffer, _ in\n guard let self else { return }\n Task { await self.processBuffer(sampleBuffer) }\n }\n }\n\n private func processBuffer(_ buffer: AVAudioPCMBuffer) {\n if let accumulatedBuffer = microphonePCMSampleVendorCommon.resampleAndAccumulate(buffer) {\n continuation?.yield(accumulatedBuffer)\n }\n }\n\n}\n#endif\n"
},
{
"path": "Sources/OpenAI/Private/Audio/MicrophonePCMSampleVendorAT.swift",
"content": "//\n// MicrophonePCMSampleVendorAT.swift\n// SwiftOpenAI\n//\n// Created from AIProxySwift\n// Original: https://github.com/lzell/AIProxySwift\n//\n\n#if canImport(AVFoundation)\n#if os(macOS) || os(iOS)\n\nimport AudioToolbox\n@preconcurrency import AVFoundation\nimport Foundation\nimport OSLog\n\nprivate let logger = Logger(subsystem: \"com.swiftopenai\", category: \"Audio\")\n\nnonisolated private let kVoiceProcessingInputSampleRate: Double = 44100\n\n/// This is an AudioToolbox-based implementation that vends PCM16 microphone samples at a\n/// sample rate that OpenAI's realtime models expect.\n///\n/// ## Requirements\n///\n/// - Assumes an `NSMicrophoneUsageDescription` description has been added to Target > Info\n/// - Assumes that microphone permissions have already been granted\n///\n/// ## Usage\n///\n/// ```\n/// let microphoneVendor = MicrophonePCMSampleVendorAT()\n/// let micStream = try microphoneVendor.start()\n/// Task {\n/// for await buffer in micStream {\n/// // Use buffer\n/// }\n/// }\n/// // ... some time later ...\n/// microphoneVendor.stop()\n/// ```\n@RealtimeActor\nclass MicrophonePCMSampleVendorAT: MicrophonePCMSampleVendor {\n\n public init() { }\n\n deinit {\n logger.debug(\"MicrophonePCMSampleVendorAT is being freed\")\n }\n\n public func start() throws -> AsyncStream {\n var desc = AudioComponentDescription(\n componentType: kAudioUnitType_Output,\n componentSubType: kAudioUnitSubType_VoiceProcessingIO,\n componentManufacturer: kAudioUnitManufacturer_Apple,\n componentFlags: 0,\n componentFlagsMask: 0)\n\n guard let component = AudioComponentFindNext(nil, &desc) else {\n throw MicrophonePCMSampleVendorError.couldNotConfigureAudioUnit(\n \"Could not find an audio component with VoiceProcessingIO\")\n }\n\n AudioComponentInstanceNew(component, &audioUnit)\n guard let audioUnit else {\n throw MicrophonePCMSampleVendorError.couldNotConfigureAudioUnit(\n \"Could not instantiate an audio component with VoiceProcessingIO\")\n }\n\n var one: UInt32 = 1\n var err = AudioUnitSetProperty(\n audioUnit,\n kAudioOutputUnitProperty_EnableIO,\n kAudioUnitScope_Input,\n 1,\n &one,\n UInt32(MemoryLayout.size(ofValue: one)))\n\n guard err == noErr else {\n throw MicrophonePCMSampleVendorError.couldNotConfigureAudioUnit(\n \"Could not enable the input scope of the microphone bus\")\n }\n\n var zero: UInt32 = 0\n err = AudioUnitSetProperty(\n audioUnit,\n kAudioOutputUnitProperty_EnableIO,\n kAudioUnitScope_Output,\n 0,\n &zero,\n UInt32(MemoryLayout.size(ofValue: one)))\n\n guard err == noErr else {\n throw MicrophonePCMSampleVendorError.couldNotConfigureAudioUnit(\n \"Could not disable the output scope of the speaker bus\")\n }\n\n var hardwareASBD = AudioStreamBasicDescription()\n var size = UInt32(MemoryLayout.size)\n let _ = AudioUnitGetProperty(\n audioUnit,\n kAudioUnitProperty_StreamFormat,\n kAudioUnitScope_Input,\n 1,\n &hardwareASBD,\n &size)\n logger.debug(\"Hardware mic is natively at \\(hardwareASBD.mSampleRate) sample rate\")\n\n var ioFormat = AudioStreamBasicDescription(\n mSampleRate: kVoiceProcessingInputSampleRate,\n mFormatID: kAudioFormatLinearPCM,\n mFormatFlags: kAudioFormatFlagIsSignedInteger | kAudioFormatFlagIsPacked,\n mBytesPerPacket: 2,\n mFramesPerPacket: 1,\n mBytesPerFrame: 2,\n mChannelsPerFrame: 1,\n mBitsPerChannel: 16,\n mReserved: 0)\n\n err = AudioUnitSetProperty(\n audioUnit,\n kAudioUnitProperty_StreamFormat,\n kAudioUnitScope_Output,\n 1,\n &ioFormat,\n UInt32(MemoryLayout.size))\n guard err == noErr else {\n throw MicrophonePCMSampleVendorError.couldNotConfigureAudioUnit(\n \"Could not set ASBD on the output scope of the mic bus\")\n }\n\n #if os(macOS)\n if let deviceID = AudioUtils.getDefaultAudioInputDevice() {\n // Try to get 50ms updates.\n // 50ms is half the granularity of our target accumulator (we accumulate into 100ms payloads that we send up to OpenAI)\n var bufferSize = UInt32(kVoiceProcessingInputSampleRate / 20)\n var propertyAddress = AudioObjectPropertyAddress(\n mSelector: kAudioDevicePropertyBufferFrameSize,\n mScope: kAudioDevicePropertyScopeInput,\n mElement: kAudioObjectPropertyElementMain)\n\n let size = UInt32(MemoryLayout.size(ofValue: bufferSize))\n let status = AudioObjectSetPropertyData(\n deviceID,\n &propertyAddress,\n 0,\n nil,\n size,\n &bufferSize)\n\n if status != noErr {\n logger.debug(\"Could not set desired buffer size\")\n }\n }\n #endif\n\n var inputCallbackStruct = AURenderCallbackStruct(\n inputProc: audioRenderCallback,\n inputProcRefCon: Unmanaged.passUnretained(self).toOpaque())\n err = AudioUnitSetProperty(\n audioUnit,\n kAudioOutputUnitProperty_SetInputCallback,\n kAudioUnitScope_Global,\n 1,\n &inputCallbackStruct,\n UInt32(MemoryLayout.size))\n\n guard err == noErr else {\n throw MicrophonePCMSampleVendorError.couldNotConfigureAudioUnit(\n \"Could not set the render callback on the voice processing audio unit\")\n }\n\n guard err == noErr else {\n throw MicrophonePCMSampleVendorError.couldNotConfigureAudioUnit(\n \"Could not configure auto gain control\")\n }\n\n err = AudioUnitInitialize(audioUnit)\n guard err == noErr else {\n throw MicrophonePCMSampleVendorError.couldNotConfigureAudioUnit(\n \"Could not initialize the audio unit\")\n }\n\n err = AudioOutputUnitStart(audioUnit)\n guard err == noErr else {\n throw MicrophonePCMSampleVendorError.couldNotConfigureAudioUnit(\n \"Could not start the audio unit\")\n }\n\n return AsyncStream { [weak self] continuation in\n self?.continuation = continuation\n }\n }\n\n public func stop() {\n continuation?.finish()\n continuation = nil\n\n // Capture the audio unit reference\n if let au = audioUnit {\n // Clear the property immediately on RealtimeActor\n audioUnit = nil\n\n // Dispatch the actual AudioToolbox cleanup to a background queue\n // to avoid priority inversion with the audio render thread.\n // Note: AudioUnit is a C pointer type (non-Sendable), but the AudioToolbox\n // cleanup APIs are thread-safe and we've already cleared our reference.\n DispatchQueue.global(qos: .utility).async {\n AudioOutputUnitStop(au)\n AudioUnitUninitialize(au)\n AudioComponentInstanceDispose(au)\n }\n }\n\n microphonePCMSampleVendorCommon.audioConverter = nil\n }\n\n fileprivate func didReceiveRenderCallback(\n _ ioActionFlags: UnsafeMutablePointer,\n _ inTimeStamp: UnsafePointer,\n _ inBusNumber: UInt32,\n _ inNumberFrames: UInt32)\n {\n guard let audioUnit else {\n logger.error(\"There is no audioUnit attached to the sample vendor. Render callback should not be called\")\n return\n }\n var bufferList = AudioBufferList(\n mNumberBuffers: 1,\n mBuffers: AudioBuffer(\n mNumberChannels: 1,\n mDataByteSize: inNumberFrames * 2,\n mData: UnsafeMutableRawPointer.allocate(\n byteCount: Int(inNumberFrames) * 2,\n alignment: MemoryLayout.alignment)))\n\n let status = AudioUnitRender(\n audioUnit,\n ioActionFlags,\n inTimeStamp,\n inBusNumber,\n inNumberFrames,\n &bufferList)\n\n guard status == noErr else {\n logger.error(\"Could not render voice processed audio data to bufferList\")\n return\n }\n\n guard\n let audioFormat = AVAudioFormat(\n commonFormat: .pcmFormatInt16,\n sampleRate: kVoiceProcessingInputSampleRate,\n channels: 1,\n interleaved: true)\n else {\n logger.error(\"Could not create audio format inside render callback.\")\n return\n }\n\n if\n let sampleBuffer = AVAudioPCMBuffer(pcmFormat: audioFormat, bufferListNoCopy: &bufferList),\n let accumulatedBuffer = microphonePCMSampleVendorCommon.resampleAndAccumulate(sampleBuffer)\n {\n // If the buffer has accumulated to a sufficient level, give it back to the caller\n Task { @RealtimeActor in\n self.continuation?.yield(accumulatedBuffer)\n }\n }\n }\n\n private var audioUnit: AudioUnit?\n private let microphonePCMSampleVendorCommon = MicrophonePCMSampleVendorCommon()\n private var continuation: AsyncStream.Continuation?\n\n}\n\n/// This @RealtimeActor annotation is a lie.\n@RealtimeActor private let audioRenderCallback: AURenderCallback = {\n inRefCon,\n ioActionFlags,\n inTimeStamp,\n inBusNumber,\n inNumberFrames,\n _ in\n let microphonePCMSampleVendor = Unmanaged\n .fromOpaque(inRefCon)\n .takeUnretainedValue()\n microphonePCMSampleVendor.didReceiveRenderCallback(\n ioActionFlags,\n inTimeStamp,\n inBusNumber,\n inNumberFrames)\n return noErr\n}\n#endif\n#endif\n"
},
{
"path": "Sources/OpenAI/Private/Audio/MicrophonePCMSampleVendorCommon.swift",
"content": "//\n// MicrophonePCMSampleVendorCommon.swift\n// SwiftOpenAI\n//\n// Created from AIProxySwift\n// Original: https://github.com/lzell/AIProxySwift\n//\n\n#if canImport(AVFoundation)\n@preconcurrency import AVFoundation\nimport OSLog\n\nprivate let logger = Logger(subsystem: \"com.swiftopenai\", category: \"Audio\")\n\n// MARK: - MicrophonePCMSampleVendorCommon\n\n/// This protocol is used as a mixin.\n/// Please see MicrophonePCMSampleVendor.swift for the protocol that defines a user interface.\nnonisolated final class MicrophonePCMSampleVendorCommon {\n var bufferAccumulator: AVAudioPCMBuffer?\n var audioConverter: AVAudioConverter?\n\n func resampleAndAccumulate(_ pcm16Buffer: AVAudioPCMBuffer) -> AVAudioPCMBuffer? {\n if\n let resampledBuffer = convertPCM16BufferToExpectedSampleRate(pcm16Buffer),\n let accumulatedBuffer = accummulateAndVendIfFull(resampledBuffer)\n {\n return accumulatedBuffer\n }\n return nil\n }\n\n private func convertPCM16BufferToExpectedSampleRate(_ pcm16Buffer: AVAudioPCMBuffer) -> AVAudioPCMBuffer? {\n guard\n let audioFormat = AVAudioFormat(\n commonFormat: .pcmFormatInt16,\n sampleRate: 24000.0,\n channels: 1,\n interleaved: false)\n else {\n logger.error(\"Could not create target audio format\")\n return nil\n }\n\n if audioConverter == nil {\n audioConverter = AVAudioConverter(from: pcm16Buffer.format, to: audioFormat)\n }\n\n guard let converter = audioConverter else {\n logger.error(\"There is no audio converter to use for PCM16 resampling\")\n return nil\n }\n\n guard\n let outputBuffer = AVAudioPCMBuffer(\n pcmFormat: audioFormat,\n frameCapacity: AVAudioFrameCount(audioFormat.sampleRate * 2.0))\n else {\n logger.error(\"Could not create output buffer for PCM16 resampling\")\n return nil\n }\n\n // See the docstring on AVAudioConverterInputBlock in AVAudioConverter.h\n //\n // The block will keep getting invoked until either the frame capacity is\n // reached or outStatus.pointee is set to `.noDataNow` or `.endStream`.\n var error: NSError?\n nonisolated(unsafe) var ptr: UInt32 = 0\n let targetFrameLength = pcm16Buffer.frameLength\n let _ = converter.convert(to: outputBuffer, error: &error) { numberOfFrames, outStatus in\n guard\n ptr < targetFrameLength,\n let workingCopy = advancedPCMBuffer_noCopy(pcm16Buffer, offset: ptr)\n else {\n outStatus.pointee = .noDataNow\n return nil\n }\n let amountToFill = min(numberOfFrames, targetFrameLength - ptr)\n outStatus.pointee = .haveData\n ptr += amountToFill\n workingCopy.frameLength = amountToFill\n return workingCopy\n }\n\n if let error {\n logger.error(\"Error converting to expected sample rate: \\(error.localizedDescription)\")\n return nil\n }\n\n return outputBuffer\n }\n\n /// The incoming buffer here must be guaranteed at 24kHz in PCM16Int format.\n private func accummulateAndVendIfFull(_ buf: AVAudioPCMBuffer) -> AVAudioPCMBuffer? {\n var returnBuffer: AVAudioPCMBuffer? = nil\n let targetAccumulatorLength = 2400\n if bufferAccumulator == nil {\n bufferAccumulator = AVAudioPCMBuffer(pcmFormat: buf.format, frameCapacity: AVAudioFrameCount(targetAccumulatorLength * 2))\n }\n guard let accumulator = bufferAccumulator else { return nil }\n\n let copyFrames = min(buf.frameLength, accumulator.frameCapacity - accumulator.frameLength)\n let dst = accumulator.int16ChannelData![0].advanced(by: Int(accumulator.frameLength))\n let src = buf.int16ChannelData![0]\n\n dst.update(from: src, count: Int(copyFrames))\n accumulator.frameLength += copyFrames\n if accumulator.frameLength >= targetAccumulatorLength {\n returnBuffer = accumulator\n bufferAccumulator = nil\n }\n return returnBuffer\n }\n}\n\nnonisolated private func advancedPCMBuffer_noCopy(_ originalBuffer: AVAudioPCMBuffer, offset: UInt32) -> AVAudioPCMBuffer? {\n let audioBufferList = originalBuffer.mutableAudioBufferList\n guard\n audioBufferList.pointee.mNumberBuffers == 1,\n audioBufferList.pointee.mBuffers.mNumberChannels == 1\n else {\n logger.error(\"Broken programmer assumption. Audio conversion depends on single channel PCM16 as input\")\n return nil\n }\n guard let audioBufferData = audioBufferList.pointee.mBuffers.mData else {\n logger.error(\"Could not get audio buffer data from the original PCM16 buffer\")\n return nil\n }\n // advanced(by:) is O(1)\n audioBufferList.pointee.mBuffers.mData = audioBufferData.advanced(\n by: Int(offset) * MemoryLayout.size)\n return AVAudioPCMBuffer(\n pcmFormat: originalBuffer.format,\n bufferListNoCopy: audioBufferList)\n}\n#endif\n"
},
{
"path": "Sources/OpenAI/Private/Audio/MicrophonePCMSampleVendorError.swift",
"content": "//\n// MicrophonePCMSampleVendorError.swift\n// SwiftOpenAI\n//\n// Created from AIProxySwift\n// Original: https://github.com/lzell/AIProxySwift\n//\n\nimport Foundation\n\npublic enum MicrophonePCMSampleVendorError: LocalizedError, Sendable {\n case couldNotConfigureAudioUnit(String)\n\n public var errorDescription: String? {\n switch self {\n case .couldNotConfigureAudioUnit(let message):\n message\n }\n }\n}\n"
},
{
"path": "Sources/OpenAI/Private/Networking/AsyncHTTPClientAdapter.swift",
"content": "//\n// AsyncHTTPClientAdapter.swift\n// SwiftOpenAI\n//\n// Created by Joe Fabisevich on 5/18/25.\n//\n\n#if os(Linux)\nimport AsyncHTTPClient\nimport Foundation\nimport NIOCore\nimport NIOFoundationCompat\nimport NIOHTTP1\n\n/// Adapter that implements HTTPClient protocol using AsyncHTTPClient\npublic class AsyncHTTPClientAdapter: HTTPClient {\n /// Initializes a new AsyncHTTPClientAdapter with the provided AsyncHTTPClient\n /// - Parameter client: The AsyncHTTPClient instance to use\n public init(client: AsyncHTTPClient.HTTPClient) {\n self.client = client\n }\n\n deinit {\n shutdown()\n }\n\n /// Creates a new AsyncHTTPClientAdapter with a default configuration\n /// - Returns: A new AsyncHTTPClientAdapter instance\n public static func createDefault() -> AsyncHTTPClientAdapter {\n let httpClient = AsyncHTTPClient.HTTPClient(\n eventLoopGroupProvider: .singleton,\n configuration: AsyncHTTPClient.HTTPClient.Configuration(\n certificateVerification: .fullVerification,\n timeout: .init(\n connect: .seconds(30),\n read: .seconds(30)),\n backgroundActivityLogger: nil))\n return AsyncHTTPClientAdapter(client: httpClient)\n }\n\n /// Fetches data for a given HTTP request\n /// - Parameter request: The HTTP request to perform\n /// - Returns: A tuple containing the data and HTTP response\n public func data(for request: HTTPRequest) async throws -> (Data, HTTPResponse) {\n let asyncHTTPClientRequest = try createAsyncHTTPClientRequest(from: request)\n\n let response = try await client.execute(asyncHTTPClientRequest, deadline: .now() + .seconds(60))\n let body = try await response.body.collect(upTo: 100 * 1024 * 1024) // 100 MB max\n\n let data = Data(buffer: body)\n let httpResponse = HTTPResponse(\n statusCode: Int(response.status.code),\n headers: convertHeaders(response.headers))\n\n return (data, httpResponse)\n }\n\n /// Fetches a byte stream for a given HTTP request\n /// - Parameter request: The HTTP request to perform\n /// - Returns: A tuple containing the byte stream and HTTP response\n public func bytes(for request: HTTPRequest) async throws -> (HTTPByteStream, HTTPResponse) {\n let asyncHTTPClientRequest = try createAsyncHTTPClientRequest(from: request)\n\n let response = try await client.execute(asyncHTTPClientRequest, deadline: .now() + .seconds(60))\n let httpResponse = HTTPResponse(\n statusCode: Int(response.status.code),\n headers: convertHeaders(response.headers))\n\n let stream = AsyncThrowingStream { continuation in\n Task {\n do {\n for try await byteBuffer in response.body {\n if let string = byteBuffer.getString(at: 0, length: byteBuffer.readableBytes) {\n let lines = string.split(separator: \"\\n\", omittingEmptySubsequences: false)\n for line in lines {\n continuation.yield(String(line))\n }\n }\n }\n continuation.finish()\n } catch {\n continuation.finish(throwing: error)\n }\n }\n }\n\n return (.lines(stream), httpResponse)\n }\n\n /// Properly shutdown the HTTP client\n public func shutdown() {\n try? client.shutdown().wait()\n }\n\n /// The underlying AsyncHTTPClient instance\n private let client: AsyncHTTPClient.HTTPClient\n\n /// Converts our HTTPRequest to AsyncHTTPClient's Request\n /// - Parameter request: Our HTTPRequest\n /// - Returns: AsyncHTTPClient Request\n private func createAsyncHTTPClientRequest(from request: HTTPRequest) throws -> HTTPClientRequest {\n var asyncHTTPClientRequest = HTTPClientRequest(url: request.url.absoluteString)\n asyncHTTPClientRequest.method = NIOHTTP1.HTTPMethod(rawValue: request.method.rawValue)\n\n // Add headers\n for (key, value) in request.headers {\n asyncHTTPClientRequest.headers.add(name: key, value: value)\n }\n\n // Add body if present\n if let body = request.body {\n asyncHTTPClientRequest.body = .bytes(body)\n }\n\n return asyncHTTPClientRequest\n }\n\n /// Converts NIOHTTP1 headers to a dictionary\n /// - Parameter headers: NIOHTTP1 HTTPHeaders\n /// - Returns: Dictionary of header name-value pairs\n private func convertHeaders(_ headers: HTTPHeaders) -> [String: String] {\n var result = [String: String]()\n for header in headers {\n result[header.name] = header.value\n }\n return result\n }\n}\n#endif\n"
},
{
"path": "Sources/OpenAI/Private/Networking/Endpoint.swift",
"content": "//\n// Endpoint.swift\n//\n//\n// Created by James Rochabrun on 10/11/23.\n//\n\nimport Foundation\n#if os(Linux)\nimport FoundationNetworking\n#endif\n\n// MARK: - HTTPMethod\n\npublic enum HTTPMethod: String {\n case post = \"POST\"\n case get = \"GET\"\n case delete = \"DELETE\"\n}\n\n// MARK: - Endpoint\n\nprotocol Endpoint {\n func path(\n in openAIEnvironment: OpenAIEnvironment)\n -> String\n}\n\n// MARK: Endpoint+Requests\n\nextension Endpoint {\n func request(\n apiKey: Authorization,\n openAIEnvironment: OpenAIEnvironment,\n organizationID: String?,\n method: HTTPMethod,\n params: Encodable? = nil,\n queryItems: [URLQueryItem] = [],\n betaHeaderField: String? = nil,\n extraHeaders: [String: String]? = nil)\n throws -> URLRequest\n {\n let finalPath = path(in: openAIEnvironment)\n let components = urlComponents(base: openAIEnvironment.baseURL, path: finalPath, queryItems: queryItems)\n guard let url = components.url else {\n throw URLError(.badURL)\n }\n var request = URLRequest(url: url)\n request.addValue(\"application/json\", forHTTPHeaderField: \"Content-Type\")\n request.addValue(apiKey.value, forHTTPHeaderField: apiKey.headerField)\n if let organizationID {\n request.addValue(organizationID, forHTTPHeaderField: \"OpenAI-Organization\")\n }\n if let betaHeaderField {\n request.addValue(betaHeaderField, forHTTPHeaderField: \"OpenAI-Beta\")\n }\n if let extraHeaders {\n for header in extraHeaders {\n request.addValue(header.value, forHTTPHeaderField: header.key)\n }\n }\n request.httpMethod = method.rawValue\n if let params {\n request.httpBody = try JSONEncoder().encode(params)\n }\n return request\n }\n\n func multiPartRequest(\n apiKey: Authorization,\n openAIEnvironment: OpenAIEnvironment,\n organizationID: String?,\n method: HTTPMethod,\n params: MultipartFormDataParameters,\n queryItems: [URLQueryItem] = [])\n throws -> URLRequest\n {\n let finalPath = path(in: openAIEnvironment)\n let components = urlComponents(base: openAIEnvironment.baseURL, path: finalPath, queryItems: queryItems)\n guard let url = components.url else {\n throw URLError(.badURL)\n }\n var request = URLRequest(url: url)\n request.httpMethod = method.rawValue\n let boundary = UUID().uuidString\n request.addValue(apiKey.value, forHTTPHeaderField: apiKey.headerField)\n if let organizationID {\n request.addValue(organizationID, forHTTPHeaderField: \"OpenAI-Organization\")\n }\n request.addValue(\"multipart/form-data; boundary=\\(boundary)\", forHTTPHeaderField: \"Content-Type\")\n request.httpBody = params.encode(boundary: boundary)\n return request\n }\n\n private func urlComponents(\n base: String,\n path: String,\n queryItems: [URLQueryItem])\n -> URLComponents\n {\n guard var components = URLComponents(string: base) else {\n fatalError(\"Invalid base URL: \\(base)\")\n }\n components.path = path\n if !queryItems.isEmpty {\n components.queryItems = queryItems\n }\n return components\n }\n}\n"
},
{
"path": "Sources/OpenAI/Private/Networking/HTTPClient.swift",
"content": "import Foundation\n\n#if canImport(FoundationNetworking)\nimport FoundationNetworking\n#endif\n\n// MARK: - HTTPClient\n\n/// Protocol that abstracts HTTP client functionality\npublic protocol HTTPClient {\n /// Fetches data for a given HTTP request\n /// - Parameter request: The HTTP request to perform\n /// - Returns: A tuple containing the data and HTTP response\n func data(for request: HTTPRequest) async throws -> (Data, HTTPResponse)\n\n /// Fetches a byte stream for a given HTTP request\n /// - Parameter request: The HTTP request to perform\n /// - Returns: A tuple containing the byte stream and HTTP response\n func bytes(for request: HTTPRequest) async throws -> (HTTPByteStream, HTTPResponse)\n}\n\n// MARK: - HTTPRequest\n\n/// Represents an HTTP request with platform-agnostic properties\npublic struct HTTPRequest {\n public init(url: URL, method: HTTPMethod, headers: [String: String], body: Data? = nil) {\n self.url = url\n self.method = method\n self.headers = headers\n self.body = body\n }\n\n /// Initializes an HTTPRequest from a URLRequest\n /// - Parameter urlRequest: The URLRequest to convert\n public init(from urlRequest: URLRequest) throws {\n guard let url = urlRequest.url else {\n throw URLError(.badURL)\n }\n\n guard\n let httpMethodString = urlRequest.httpMethod,\n let httpMethod = HTTPMethod(rawValue: httpMethodString)\n else {\n throw URLError(.unsupportedURL)\n }\n\n var headers = [String: String]()\n if let allHTTPHeaderFields = urlRequest.allHTTPHeaderFields {\n headers = allHTTPHeaderFields\n }\n\n self.url = url\n method = httpMethod\n self.headers = headers\n body = urlRequest.httpBody\n }\n\n /// The URL for the request\n var url: URL\n /// The HTTP method for the request\n var method: HTTPMethod\n /// The HTTP headers for the request\n var headers: [String: String]\n /// The body of the request, if any\n var body: Data?\n}\n\n// MARK: - HTTPResponse\n\n/// Represents an HTTP response with platform-agnostic properties\npublic struct HTTPResponse {\n /// The HTTP status code of the response\n var statusCode: Int\n /// The HTTP headers in the response\n var headers: [String: String]\n\n public init(statusCode: Int, headers: [String: String]) {\n self.statusCode = statusCode\n self.headers = headers\n }\n}\n\n// MARK: - HTTPByteStream\n\n/// Represents a stream of bytes or lines from an HTTP response\npublic enum HTTPByteStream {\n /// A stream of bytes\n case bytes(AsyncThrowingStream