Repository: MetaGLM/zhipuai-sdk-python-v4 Branch: main Commit: ccbec4c7b53c Files: 195 Total size: 404.2 KB Directory structure: gitextract_z9p34zne/ ├── .github/ │ ├── ISSUE_TEMPLATE/ │ │ ├── bug-report.yml │ │ └── feature-request.yml │ ├── PULL_REQUEST_TEMPLATE.md │ ├── actions/ │ │ └── poetry_setup/ │ │ └── action.yml │ └── workflows/ │ ├── _integration_test.yml │ ├── _release.yml │ ├── _test.yml │ ├── _test_release.yml │ └── lint-pr.yaml ├── .gitignore ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── LICENSE ├── Makefile ├── README.md ├── README_CN.md ├── Release-Note.md ├── poetry.toml ├── pyproject.toml ├── tests/ │ ├── conftest.py │ ├── integration_tests/ │ │ ├── batchinput.jsonl │ │ ├── demo.jsonl │ │ ├── file.xlsx │ │ ├── test.py │ │ ├── test_agents.py │ │ ├── test_assistant.py │ │ ├── test_audio.py │ │ ├── test_batches.py │ │ ├── test_charglm3.py │ │ ├── test_chat.py │ │ ├── test_code_geex.py │ │ ├── test_embedding.py │ │ ├── test_emohaa.py │ │ ├── test_file.py │ │ ├── test_file_parser.py │ │ ├── test_finetuning.py │ │ ├── test_images.py │ │ ├── test_knowledge.py │ │ ├── test_moderation.py │ │ ├── test_tools.py │ │ ├── test_transcriptions.py │ │ ├── test_videos.py │ │ ├── test_vlm_thinking.py │ │ └── test_web_search.py │ └── unit_tests/ │ ├── batchinput.jsonl │ ├── maybe/ │ │ └── test_maybe_transform.py │ ├── response_model/ │ │ ├── __init__.py │ │ └── test_response.py │ ├── sse_client/ │ │ ├── __init__.py │ │ └── test_stream.py │ ├── test_agents.py │ ├── test_audio.py │ ├── test_jwt.py │ ├── test_request_opt.py │ ├── test_response.py │ ├── test_sdk_import.py │ └── test_streaming.py └── zhipuai/ ├── __init__.py ├── __version__.py ├── _client.py ├── api_resource/ │ ├── __init__.py │ ├── agents/ │ │ ├── __init__.py │ │ └── agents.py │ ├── assistant/ │ │ ├── __init__.py │ │ └── assistant.py │ ├── audio/ │ │ ├── __init__.py │ │ ├── audio.py │ │ └── transcriptions.py │ ├── batches.py │ ├── chat/ │ │ ├── __init__.py │ │ ├── async_completions.py │ │ ├── chat.py │ │ └── completions.py │ ├── embeddings.py │ ├── file_parser/ │ │ ├── __init__.py │ │ └── file_parser.py │ ├── files.py │ ├── fine_tuning/ │ │ ├── __init__.py │ │ ├── fine_tuning.py │ │ ├── jobs/ │ │ │ ├── __init__.py │ │ │ └── jobs.py │ │ └── models/ │ │ ├── __init__.py │ │ └── fine_tuned_models.py │ ├── images.py │ ├── knowledge/ │ │ ├── __init__.py │ │ ├── document/ │ │ │ ├── __init__.py │ │ │ └── document.py │ │ └── knowledge.py │ ├── moderation/ │ │ ├── __init__.py │ │ └── moderations.py │ ├── tools/ │ │ ├── __init__.py │ │ └── tools.py │ ├── videos/ │ │ ├── __init__.py │ │ └── videos.py │ └── web_search/ │ ├── __init__.py │ └── web_search.py ├── core/ │ ├── __init__.py │ ├── _base_api.py │ ├── _base_compat.py │ ├── _base_models.py │ ├── _base_type.py │ ├── _constants.py │ ├── _errors.py │ ├── _files.py │ ├── _http_client.py │ ├── _jwt_token.py │ ├── _legacy_binary_response.py │ ├── _legacy_response.py │ ├── _request_opt.py │ ├── _response.py │ ├── _sse_client.py │ ├── _utils/ │ │ ├── __init__.py │ │ ├── _transform.py │ │ ├── _typing.py │ │ └── _utils.py │ ├── logs.py │ └── pagination.py └── types/ ├── __init__.py ├── agents/ │ ├── __init__.py │ ├── agents_completion.py │ ├── agents_completion_chunk.py │ └── chat_completions_create_param.py ├── assistant/ │ ├── __init__.py │ ├── assistant_completion.py │ ├── assistant_conversation_params.py │ ├── assistant_conversation_resp.py │ ├── assistant_create_params.py │ ├── assistant_support_resp.py │ └── message/ │ ├── __init__.py │ ├── message_content.py │ ├── text_content_block.py │ ├── tools/ │ │ ├── code_interpreter_delta_block.py │ │ ├── drawing_tool_delta_block.py │ │ ├── function_delta_block.py │ │ ├── retrieval_delta_black.py │ │ ├── tools_type.py │ │ └── web_browser_delta_block.py │ └── tools_delta_block.py ├── audio/ │ ├── __init__.py │ ├── audio_customization_param.py │ ├── audio_speech_chunk.py │ ├── audio_speech_params.py │ └── transcriptions_create_param.py ├── batch.py ├── batch_create_params.py ├── batch_error.py ├── batch_list_params.py ├── batch_request_counts.py ├── chat/ │ ├── __init__.py │ ├── async_chat_completion.py │ ├── chat_completion.py │ ├── chat_completion_chunk.py │ ├── chat_completions_create_param.py │ └── code_geex/ │ └── code_geex_params.py ├── embeddings.py ├── file_parser/ │ ├── __init__.py │ ├── file_parser_create_params.py │ └── file_parser_resp.py ├── files/ │ ├── __init__.py │ ├── file_create_params.py │ ├── file_deleted.py │ ├── file_object.py │ └── upload_detail.py ├── fine_tuning/ │ ├── __init__.py │ ├── fine_tuning_job.py │ ├── fine_tuning_job_event.py │ ├── job_create_params.py │ └── models/ │ ├── __init__.py │ └── fine_tuned_models.py ├── image.py ├── knowledge/ │ ├── __init__.py │ ├── document/ │ │ ├── __init__.py │ │ ├── document.py │ │ ├── document_edit_params.py │ │ ├── document_list_params.py │ │ └── document_list_resp.py │ ├── knowledge.py │ ├── knowledge_create_params.py │ ├── knowledge_list_params.py │ ├── knowledge_list_resp.py │ └── knowledge_used.py ├── moderation/ │ ├── __init__.py │ └── moderation_completion.py ├── sensitive_word_check/ │ ├── __init__.py │ └── sensitive_word_check.py ├── tools/ │ ├── __init__.py │ ├── tools_web_search_params.py │ ├── web_search.py │ └── web_search_chunk.py ├── video/ │ ├── __init__.py │ ├── video_create_params.py │ └── video_object.py └── web_search/ ├── __init__.py ├── web_search_create_params.py └── web_search_resp.py ================================================ FILE CONTENTS ================================================ ================================================ FILE: .github/ISSUE_TEMPLATE/bug-report.yml ================================================ name: 🐞 Bug Report description: File a bug report title: "[Bug]: " type: "Bug" body: - type: markdown attributes: value: | Thanks for stopping by to let us know something could be better! - type: textarea id: what-happened attributes: label: What happened? description: Also tell us what you expected to happen and how to reproduce the issue. placeholder: Tell us what you see! value: "A bug happened!" validations: required: true - type: textarea id: logs attributes: label: Relevant log output description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks. render: shell - type: checkboxes id: terms attributes: label: Code of Conduct description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/MetaGLM/zhipuai-sdk-python-v4/blob/main/CODE_OF_CONDUCT.md) options: - label: I agree to follow this project's Code of Conduct required: true ================================================ FILE: .github/ISSUE_TEMPLATE/feature-request.yml ================================================ name: 💡 Feature Request description: Suggest an idea for this repository title: "[Feat]: " type: "Feature" body: - type: markdown attributes: value: | Thanks for stopping by to let us know something could be better! - type: textarea id: problem attributes: label: Is your feature request related to a problem? Please describe. description: A clear and concise description of what the problem is. placeholder: Ex. I'm always frustrated when [...] - type: textarea id: describe attributes: label: Describe the solution you'd like description: A clear and concise description of what you want to happen. validations: required: true - type: textarea id: alternatives attributes: label: Describe alternatives you've considered description: A clear and concise description of any alternative solutions or features you've considered. - type: textarea id: context attributes: label: Additional context description: Add any other context or screenshots about the feature request here. - type: checkboxes id: terms attributes: label: Code of Conduct description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/MetaGLM/zhipuai-sdk-python-v4/blob/main/CODE_OF_CONDUCT.md) options: - label: I agree to follow this project's Code of Conduct required: true ================================================ FILE: .github/PULL_REQUEST_TEMPLATE.md ================================================ # Description Thank you for opening a Pull Request! Before submitting your PR, there are a few things you can do to make sure it goes smoothly: - [ ] Follow the [`CONTRIBUTING` Guide](https://github.com/MetaGLM/zhipuai-sdk-python-v4/blob/main/CONTRIBUTING.md). - [ ] Make your Pull Request title in the specification. - [ ] Ensure the tests pass (Run `mvn clean test` from the repository root) - [ ] Appropriate docs were updated (if necessary) Fixes # ================================================ FILE: .github/actions/poetry_setup/action.yml ================================================ # An action for setting up poetry install with caching. # Using a custom action since the default action does not # take poetry install groups into account. # Action code from: # https://github.com/actions/setup-python/issues/505#issuecomment-1273013236 name: poetry-install-with-caching description: Poetry install with support for caching of dependency groups. inputs: python-version: description: Python version, supporting MAJOR.MINOR only required: true poetry-version: description: Poetry version required: true cache-key: description: Cache key to use for manual handling of caching required: true working-directory: description: Directory whose poetry.lock file should be cached required: true runs: using: composite steps: - uses: actions/setup-python@v5 name: Setup python ${{ inputs.python-version }} id: setup-python with: python-version: ${{ inputs.python-version }} # - uses: actions/cache@v4 # id: cache-bin-poetry # name: Cache Poetry binary - Python ${{ inputs.python-version }} # env: # SEGMENT_DOWNLOAD_TIMEOUT_MIN: "1" # with: # path: | # /opt/pipx/venvs/poetry # # This step caches the poetry installation, so make sure it's keyed on the poetry version as well. # key: bin-poetry-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-${{ inputs.poetry-version }} - name: Refresh shell hashtable and fixup softlinks if: steps.cache-bin-poetry.outputs.cache-hit == 'true' shell: bash env: POETRY_VERSION: ${{ inputs.poetry-version }} PYTHON_VERSION: ${{ inputs.python-version }} run: | set -eux # Refresh the shell hashtable, to ensure correct `which` output. hash -r # `actions/cache@v3` doesn't always seem able to correctly unpack softlinks. # Delete and recreate the softlinks pipx expects to have. rm /opt/pipx/venvs/poetry/bin/python cd /opt/pipx/venvs/poetry/bin ln -s "$(which "python$PYTHON_VERSION")" python chmod +x python cd /opt/pipx_bin/ ln -s /opt/pipx/venvs/poetry/bin/poetry poetry chmod +x poetry # Ensure everything got set up correctly. /opt/pipx/venvs/poetry/bin/python --version /opt/pipx_bin/poetry --version - name: Install poetry via pip if: steps.cache-bin-poetry.outputs.cache-hit != 'true' shell: bash env: POETRY_VERSION: ${{ inputs.poetry-version }} run: | python -m pip install --upgrade pip python -m pip install "poetry==$POETRY_VERSION" poetry --version - name: Restore pip and poetry cached dependencies uses: actions/cache@v4 env: SEGMENT_DOWNLOAD_TIMEOUT_MIN: "4" WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }} with: path: | ~/.cache/pip ~/.cache/pypoetry/virtualenvs ~/.cache/pypoetry/cache ~/.cache/pypoetry/artifacts ${{ env.WORKDIR }}/.venv key: py-deps-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-poetry-${{ inputs.poetry-version }}-${{ inputs.cache-key }}-${{ hashFiles(format('{0}/**/poetry.lock', env.WORKDIR)) }} ================================================ FILE: .github/workflows/_integration_test.yml ================================================ name: integration_test on: workflow_dispatch: inputs: working-directory: required: true type: string default: '.' description: "From which folder this pipeline executes" env: POETRY_VERSION: "1.8.2" jobs: build: if: github.ref == 'refs/heads/main' runs-on: ubuntu-latest environment: Scheduled testing publish outputs: pkg-name: ${{ steps.check-version.outputs.pkg-name }} version: ${{ steps.check-version.outputs.version }} strategy: matrix: python-version: - "3.8" - "3.9" - "3.10" - "3.11" - "3.12" name: "make integration_test #${{ matrix.python-version }}" steps: - uses: actions/checkout@v4 - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }} uses: "./.github/actions/poetry_setup" with: python-version: ${{ matrix.python-version }} poetry-version: ${{ env.POETRY_VERSION }} working-directory: ${{ inputs.working-directory }} cache-key: core - name: Import test dependencies run: poetry install --with test working-directory: ${{ inputs.working-directory }} - name: Run integration tests shell: bash env: ZHIPUAI_API_KEY: ${{ secrets.ZHIPUAI_API_KEY }} ZHIPUAI_BASE_URL: ${{ secrets.ZHIPUAI_BASE_URL }} run: | make integration_tests - name: Ensure the tests did not create any additional files shell: bash run: | set -eu STATUS="$(git status)" echo "$STATUS" # grep will exit non-zero if the target message isn't found, # and `set -e` above will cause the step to fail. echo "$STATUS" | grep 'nothing to commit, working tree clean' ================================================ FILE: .github/workflows/_release.yml ================================================ name: release run-name: Release ${{ inputs.working-directory }} by @${{ github.actor }} on: workflow_call: inputs: working-directory: required: true type: string description: "From which folder this pipeline executes" workflow_dispatch: inputs: working-directory: required: true type: string default: '.' description: "From which folder this pipeline executes" env: PYTHON_VERSION: "3.9" POETRY_VERSION: "1.8.2" jobs: build: if: github.ref == 'refs/heads/main' environment: Scheduled testing publish runs-on: ubuntu-latest outputs: pkg-name: ${{ steps.check-version.outputs.pkg-name }} version: ${{ steps.check-version.outputs.version }} steps: - uses: actions/checkout@v4 - name: Set up Python + Poetry ${{ env.POETRY_VERSION }} uses: "./.github/actions/poetry_setup" with: python-version: ${{ env.PYTHON_VERSION }} poetry-version: ${{ env.POETRY_VERSION }} working-directory: ${{ inputs.working-directory }} cache-key: release # We want to keep this build stage *separate* from the release stage, # so that there's no sharing of permissions between them. # The release stage has trusted publishing and GitHub repo contents write access, # and we want to keep the scope of that access limited just to the release job. # Otherwise, a malicious `build` step (e.g. via a compromised dependency) # could get access to our GitHub or PyPI credentials. # # Per the trusted publishing GitHub Action: # > It is strongly advised to separate jobs for building [...] # > from the publish job. # https://github.com/pypa/gh-action-pypi-publish#non-goals - name: Build project for distribution run: poetry build working-directory: ${{ inputs.working-directory }} - name: Upload build uses: actions/upload-artifact@v4 with: name: dist path: ${{ inputs.working-directory }}/dist/ - name: Check Version id: check-version shell: bash working-directory: ${{ inputs.working-directory }} run: | echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT echo version="$(poetry version --short)" >> $GITHUB_OUTPUT test-pypi-publish: needs: - build uses: ./.github/workflows/_test_release.yml with: working-directory: ${{ inputs.working-directory }} secrets: inherit pre-release-checks: needs: - build - test-pypi-publish environment: Scheduled testing publish runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 # We explicitly *don't* set up caching here. This ensures our tests are # maximally sensitive to catching breakage. # # For example, here's a way that caching can cause a falsely-passing test: # - Make the langchain package manifest no longer list a dependency package # as a requirement. This means it won't be installed by `pip install`, # and attempting to use it would cause a crash. # - That dependency used to be required, so it may have been cached. # When restoring the venv packages from cache, that dependency gets included. # - Tests pass, because the dependency is present even though it wasn't specified. # - The package is published, and it breaks on the missing dependency when # used in the real world. - name: Set up Python + Poetry ${{ env.POETRY_VERSION }} uses: "./.github/actions/poetry_setup" with: python-version: ${{ env.PYTHON_VERSION }} poetry-version: ${{ env.POETRY_VERSION }} working-directory: ${{ inputs.working-directory }} - name: Import published package shell: bash working-directory: ${{ inputs.working-directory }} env: PKG_NAME: ${{ needs.build.outputs.pkg-name }} VERSION: ${{ needs.build.outputs.version }} # Here we use: # - The default regular PyPI index as the *primary* index, meaning # that it takes priority (https://pypi.org/simple) # - The test PyPI index as an extra index, so that any dependencies that # are not found on test PyPI can be resolved and installed anyway. # (https://test.pypi.org/simple). This will include the PKG_NAME==VERSION # package because VERSION will not have been uploaded to regular PyPI yet. # - attempt install again after 5 seconds if it fails because there is # sometimes a delay in availability on test pypi run: | poetry run pip install \ --extra-index-url https://test.pypi.org/simple/ \ "$PKG_NAME==$VERSION" || \ ( \ sleep 5 && \ poetry run pip install \ --extra-index-url https://test.pypi.org/simple/ \ "$PKG_NAME==$VERSION" \ ) # Replace all dashes in the package name with underscores, # since that's how Python imports packages with dashes in the name. IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g)" poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))" - name: Import test dependencies run: poetry install --with test working-directory: ${{ inputs.working-directory }} # Overwrite the local version of the package with the test PyPI version. - name: Import published package (again) working-directory: ${{ inputs.working-directory }} shell: bash env: PKG_NAME: ${{ needs.build.outputs.pkg-name }} VERSION: ${{ needs.build.outputs.version }} run: | poetry run pip install \ --extra-index-url https://test.pypi.org/simple/ \ "$PKG_NAME==$VERSION" # - name: Run unit tests # run: make tests # env: # ZHIPUAI_API_KEY: ${{ secrets.ZHIPUAI_API_KEY }} # ZHIPUAI_BASE_URL: ${{ secrets.ZHIPUAI_BASE_URL }} # working-directory: ${{ inputs.working-directory }} # - name: Run integration tests # env: # ZHIPUAI_API_KEY: ${{ secrets.ZHIPUAI_API_KEY }} # ZHIPUAI_BASE_URL: ${{ secrets.ZHIPUAI_BASE_URL }} # run: make integration_tests # working-directory: ${{ inputs.working-directory }} publish: needs: - build - test-pypi-publish - pre-release-checks environment: Scheduled testing publish runs-on: ubuntu-latest defaults: run: working-directory: ${{ inputs.working-directory }} steps: - uses: actions/checkout@v4 - name: Set up Python + Poetry ${{ env.POETRY_VERSION }} uses: "./.github/actions/poetry_setup" with: python-version: ${{ env.PYTHON_VERSION }} poetry-version: ${{ env.POETRY_VERSION }} working-directory: ${{ inputs.working-directory }} cache-key: release - uses: actions/download-artifact@v4 with: name: dist path: ${{ inputs.working-directory }}/dist/ - name: Publish package distributions to PyPI uses: pypa/gh-action-pypi-publish@release/v1 with: packages-dir: ${{ inputs.working-directory }}/dist/ verbose: true print-hash: true user: __token__ password: ${{ secrets.PYPI_API_TOKEN }} # We overwrite any existing distributions with the same name and version. # This is *only for CI use* and is *extremely dangerous* otherwise! # https://github.com/pypa/gh-action-pypi-publish#tolerating-release-package-file-duplicates skip-existing: true mark-release: needs: - build - test-pypi-publish - pre-release-checks - publish environment: Scheduled testing publish runs-on: ubuntu-latest permissions: # This permission is needed by `ncipollo/release-action` to # create the GitHub release. contents: write id-token: none defaults: run: working-directory: ${{ inputs.working-directory }} steps: - uses: actions/checkout@v4 - name: Set up Python + Poetry ${{ env.POETRY_VERSION }} uses: "./.github/actions/poetry_setup" with: python-version: ${{ env.PYTHON_VERSION }} poetry-version: ${{ env.POETRY_VERSION }} working-directory: ${{ inputs.working-directory }} cache-key: release - uses: actions/download-artifact@v4 with: name: dist path: ${{ inputs.working-directory }}/dist/ - name: Create Release uses: ncipollo/release-action@v1 if: ${{ inputs.working-directory == '.' }} with: artifacts: "dist/*" token: ${{ secrets.GITHUB_TOKEN }} draft: false generateReleaseNotes: true tag: v${{ needs.build.outputs.version }} commit: main ================================================ FILE: .github/workflows/_test.yml ================================================ name: test on: workflow_dispatch: inputs: working-directory: required: true type: string default: '.' description: "From which folder this pipeline executes" pull_request: branches: - main push: branches: - 'action*' env: POETRY_VERSION: "1.8.2" jobs: build: defaults: run: working-directory: ${{ inputs.working-directory || '.' }} runs-on: ubuntu-latest strategy: matrix: python-version: - "3.8" - "3.9" - "3.10" - "3.11" - "3.12" name: "make test #${{ matrix.python-version }}" steps: - uses: actions/checkout@v4 - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }} uses: "./.github/actions/poetry_setup" with: python-version: ${{ matrix.python-version }} poetry-version: ${{ env.POETRY_VERSION }} working-directory: ${{ inputs.working-directory || '.' }} cache-key: core - name: Import test dependencies run: poetry install --with test working-directory: ${{ inputs.working-directory || '.' }} - name: Run core tests shell: bash run: | make test - name: Ensure the tests did not create any additional files shell: bash run: | set -eu STATUS="$(git status)" echo "$STATUS" # grep will exit non-zero if the target message isn't found, # and `set -e` above will cause the step to fail. echo "$STATUS" | grep 'nothing to commit, working tree clean' ================================================ FILE: .github/workflows/_test_release.yml ================================================ name: test-release on: workflow_call: inputs: working-directory: required: true type: string description: "From which folder this pipeline executes" env: POETRY_VERSION: "1.8.2" PYTHON_VERSION: "3.9" jobs: build: if: github.ref == 'refs/heads/main' runs-on: ubuntu-latest outputs: pkg-name: ${{ steps.check-version.outputs.pkg-name }} version: ${{ steps.check-version.outputs.version }} steps: - uses: actions/checkout@v4 - name: Set up Python + Poetry ${{ env.POETRY_VERSION }} uses: "./.github/actions/poetry_setup" with: python-version: ${{ env.PYTHON_VERSION }} poetry-version: ${{ env.POETRY_VERSION }} working-directory: ${{ inputs.working-directory }} cache-key: release # We want to keep this build stage *separate* from the release stage, # so that there's no sharing of permissions between them. # The release stage has trusted publishing and GitHub repo contents write access, # and we want to keep the scope of that access limited just to the release job. # Otherwise, a malicious `build` step (e.g. via a compromised dependency) # could get access to our GitHub or PyPI credentials. # # Per the trusted publishing GitHub Action: # > It is strongly advised to separate jobs for building [...] # > from the publish job. # https://github.com/pypa/gh-action-pypi-publish#non-goals - name: Build project for distribution run: poetry build working-directory: ${{ inputs.working-directory }} - name: Upload build uses: actions/upload-artifact@v4 with: name: test-dist path: ${{ inputs.working-directory }}/dist/ - name: Check Version id: check-version shell: bash working-directory: ${{ inputs.working-directory }} run: | echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT echo version="$(poetry version --short)" >> $GITHUB_OUTPUT publish: needs: - build runs-on: ubuntu-latest environment: Scheduled testing publish # permissions: # id-token: none # This is required for requesting the JWT steps: - uses: actions/checkout@v4 - uses: actions/download-artifact@v4 with: name: test-dist path: ${{ inputs.working-directory }}/dist/ - name: Publish to test PyPI uses: pypa/gh-action-pypi-publish@release/v1 with: user: __token__ password: ${{ secrets.TEST_PYPI_API_TOKEN }} packages-dir: ${{ inputs.working-directory }}/dist/ verbose: true print-hash: true repository-url: https://test.pypi.org/legacy/ # We overwrite any existing distributions with the same name and version. # This is *only for CI use* and is *extremely dangerous* otherwise! # https://github.com/pypa/gh-action-pypi-publish#tolerating-release-package-file-duplicates skip-existing: true ================================================ FILE: .github/workflows/lint-pr.yaml ================================================ name: "Lint PR" on: pull_request_target: types: - opened - edited - reopened jobs: lint-pr: name: Validate PR title runs-on: ubuntu-latest permissions: pull-requests: read steps: - uses: amannn/action-semantic-pull-request@v5 env: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} ================================================ FILE: .gitignore ================================================ .vscode .idea *.pyc __pycache__/ .pytest_cache/ .DS_Store/ *.swp *~ build/ dist/ eggs/ .eggs/ *.egg-info/ test/ examples/ .pypirc /poetry.lock logs /tests/integration_tests/batchoutput.jsonl /tests/integration_tests/content_batchoutput.jsonl /tests/integration_tests/write_to_file_batchoutput.jsonl ================================================ FILE: CODE_OF_CONDUCT.md ================================================ # Code of Conduct ## Our Pledge In the interest of fostering an open and welcoming environment, we as contributors and maintainers pledge to making participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation. ## Our Standards Examples of behavior that contributes to creating a positive environment include: * Using welcoming and inclusive language * Being respectful of differing viewpoints and experiences * Gracefully accepting constructive criticism * Focusing on what is best for the community * Showing empathy towards other community members Examples of unacceptable behavior by participants include: * The use of sexualized language or imagery and unwelcome sexual attention or advances * Trolling, insulting/derogatory comments, and personal or political attacks * Public or private harassment * Publishing others' private information, such as a physical or electronic address, without explicit permission * Other conduct which could reasonably be considered inappropriate in a professional setting ## Our Responsibilities Project maintainers are responsible for clarifying the standards of acceptable behavior and are expected to take appropriate and fair corrective action in response to any instances of unacceptable behavior. Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, or to ban temporarily or permanently any contributor for other behaviors that they deem inappropriate, threatening, offensive, or harmful. ## Scope This Code of Conduct applies both within project spaces and in public spaces when an individual is representing the project or its community. Examples of representing a project or community include using an official project e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event. Representation of a project may be further defined and clarified by project maintainers. This Code of Conduct also applies outside the project spaces when the Project Steward has a reasonable belief that an individual's behavior may have a negative impact on the project or its community. ## Conflict Resolution We do not believe that all conflict is bad; healthy debate and disagreement often yield positive results. However, it is never okay to be disrespectful or to engage in behavior that violates the project’s code of conduct. If you see someone violating the code of conduct, you are encouraged to address the behavior directly with those involved. Many issues can be resolved quickly and easily, and this gives people more control over the outcome of their dispute. If you are unable to resolve the matter for any reason, or if the behavior is threatening or harassing, report it. We are dedicated to providing an environment where participants feel welcome and safe. Reports should be directed to *Weijun Zheng (weijun.zheng@aminer.cn)*, the Project Steward(s) for *zhipuai-sdk-python-v4*. It is the Project Steward’s duty to receive and address reported violations of the code of conduct. They will then work with a committee consisting of representatives from the Open Source Programs Office and the Z.ai Open Source Strategy team. We will investigate every complaint, but you may not receive a direct response. We will use our discretion in determining when and how to follow up on reported incidents, which may range from not taking action to permanent expulsion from the project and project-sponsored spaces. We will notify the accused of the report and provide them an opportunity to discuss it before any action is taken. The identity of the reporter will be omitted from the details of the report supplied to the accused. In potentially harmful situations, such as ongoing harassment or threats to anyone's safety, we may take action without notice. ## Attribution This Code of Conduct is adapted from the Contributor Covenant, version 1.4, available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html ================================================ FILE: CONTRIBUTING.md ================================================ # How to contribute We'd love to accept your patches and contributions to this project. ## Contribution process ### Code reviews All submissions, including submissions by project members, require review. We use GitHub pull requests for this purpose. Consult [GitHub Help](https://help.github.com/articles/about-pull-requests/) for more information on using pull requests. ### Contributor Guide You may follow these steps to contribute: 1. **Fork the official repository.** This will create a copy of the official repository in your own account. 2. **Sync the branches.** This will ensure that your copy of the repository is up-to-date with the latest changes from the official repository. 3. **Work on your forked repository's feature branch.** This is where you will make your changes to the code. 4. **Commit your updates on your forked repository's feature branch.** This will save your changes to your copy of the repository. 5. **Submit a pull request to the official repository's main branch.** This will request that your changes be merged into the official repository. 6. **Resolve any linting errors.** This will ensure that your changes are formatted correctly. Here are some additional things to keep in mind during the process: - **Test your changes.** Before you submit a pull request, make sure that your changes work as expected. - **Be patient.** It may take some time for your pull request to be reviewed and merged. Have Fun! --- ================================================ FILE: LICENSE ================================================ MIT License Copyright (c) Zhipu, Inc. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. ================================================ FILE: Makefile ================================================ .PHONY: all format lint test tests test_watch integration_tests docker_tests help extended_tests # Default target executed when no arguments are given to make. all: help ###################### # TESTING AND COVERAGE ###################### # Define a variable for the test file path. TEST_FILE ?= tests/unit_tests/ test tests: poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE) integration_tests: poetry run pytest tests/integration_tests ###################### # LINTING AND FORMATTING ###################### # Define a variable for Python and notebook files. PYTHON_FILES=. MYPY_CACHE=.mypy_cache lint format: PYTHON_FILES=. lint_diff format_diff: PYTHON_FILES=$(shell git diff --relative=libs/langchain --name-only --diff-filter=d master | grep -E '\.py$$|\.ipynb$$') lint_package: PYTHON_FILES=zhipuai lint_tests: PYTHON_FILES=tests lint_tests: MYPY_CACHE=.mypy_cache_test lint lint_diff lint_package lint_tests: ./scripts/check_pydantic.sh . ./scripts/lint_imports.sh poetry run ruff . [ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) --diff [ "$(PYTHON_FILES)" = "" ] || poetry run ruff --select I $(PYTHON_FILES) [ "$(PYTHON_FILES)" = "" ] || mkdir -p $(MYPY_CACHE) && poetry run mypy $(PYTHON_FILES) --cache-dir $(MYPY_CACHE) format format_diff: [ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) [ "$(PYTHON_FILES)" = "" ] || poetry run ruff --select I --fix $(PYTHON_FILES) ###################### # HELP ###################### help: @echo '-- LINTING --' @echo 'format - run code formatters' @echo 'lint - run linters' @echo '-- TESTS --' @echo 'test - run unit tests' @echo 'tests - run unit tests (alias for "make test")' @echo 'test TEST_FILE= - run all tests in file' ================================================ FILE: README.md ================================================ **The [New Python SDK](https://github.com/zai-org/z-ai-sdk-python) for Z.AI and ZhipuAI has released: [z-ai-sdk-python](https://github.com/zai-org/z-ai-sdk-python)!** It is recommended to use this SDK for better, faster, and long-term support. # ZhipuAI Open Platform Python SDK [![PyPI version](https://img.shields.io/pypi/v/zhipuai.svg)](https://pypi.org/project/zhipuai/) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Python](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/) [中文文档](README_CN.md) | English The official Python SDK for ZhipuAI's large model open interface, making it easier for developers to call ZhipuAI's open APIs. ## ✨ Features - **Type Safety**: Complete type annotations for all interfaces - **Easy Integration**: Simple initialization and intuitive method calls - **High Performance**: Built-in connection pooling and request optimization - **Secure**: Automatic token caching and secure API key management - **Lightweight**: Minimal dependencies with efficient resource usage - **Streaming Support**: Real-time streaming responses for chat completions ## 📦 Installation ### Requirements - **Python**: 3.9+ - **Package Manager**: pip ### Install via pip ```bash pip install zhipuai ``` ### Core Dependencies | Package | Version | Purpose | |---------|---------|----------| | `httpx` | `>=0.23.0` | HTTP client for API requests | | `pydantic` | `>=1.9.0,<3.0.0` | Data validation and serialization | | `typing-extensions` | `>=4.0.0` | Enhanced type hints support | ## 🚀 Quick Start ### Basic Usage ```python from zhipuai import ZhipuAI # Initialize client client = ZhipuAI(api_key="your-api-key") # Create chat completion response = client.chat.completions.create( model="glm-4", messages=[ {"role": "user", "content": "Hello, ZhipuAI!"} ] ) print(response.choices[0].message.content) ``` ### Client Configuration #### Environment Variables ```bash export ZHIPUAI_API_KEY="your-api-key" export ZHIPUAI_BASE_URL="https://open.bigmodel.cn/api/paas/v4/" # Optional ``` #### Code Configuration ```python from zhipuai import ZhipuAI client = ZhipuAI( api_key="your-api-key", base_url="https://open.bigmodel.cn/api/paas/v4/" # Optional ) ``` ### Advanced Configuration Customize client behavior with additional parameters: ```python from zhipuai import ZhipuAI import httpx client = ZhipuAI( api_key="your-api-key", timeout=httpx.Timeout(timeout=300.0, connect=8.0), # Request timeout max_retries=3, # Retry attempts base_url="https://open.bigmodel.cn/api/paas/v4/" # Custom API endpoint ) ``` ## 📖 Usage Examples ### Basic Chat ```python from zhipuai import ZhipuAI client = ZhipuAI(api_key="your-api-key") # Uses environment variable ZHIPUAI_API_KEY response = client.chat.completions.create( model="glm-4", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is artificial intelligence?"} ], tools=[ { "type": "web_search", "web_search": { "search_query": "Search the Zhipu", "search_result": True, } } ], extra_body={"temperature": 0.5, "max_tokens": 50} ) print(response) ``` ### Streaming Chat ```python from zhipuai import ZhipuAI client = ZhipuAI(api_key="your-api-key") response = client.chat.completions.create( model="glm-4", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Tell me a story about AI."} ], stream=True ) for chunk in response: if chunk.choices[0].delta.content: print(chunk.choices[0].delta) ``` ### Multimodal Chat ```python import base64 from zhipuai import ZhipuAI def encode_image(image_path): """Encode image to base64 format""" with open(image_path, "rb") as image_file: return base64.b64encode(image_file.read()).decode('utf-8') client = ZhipuAI(api_key="your-api-key") base64_image = encode_image("path/to/your/image.jpg") response = client.chat.completions.create( model="glm-4v", extra_body={"temperature": 0.5, "max_tokens": 50}, messages=[ { "role": "user", "content": [ { "type": "text", "text": "What's in this image?" }, { "type": "image_url", "image_url": { "url": f"data:image/jpeg;base64,{base64_image}" } } ] } ] ) print(response) ``` ### Character Role-Playing ```python from zhipuai import ZhipuAI client = ZhipuAI(api_key="your-api-key") response = client.chat.completions.create( model="charglm-3", messages=[ { "role": "user", "content": "Hello, how are you doing lately?" } ], meta={ "user_info": "I am a film director who specializes in music-themed movies.", "bot_info": "You are a popular domestic female singer and actress with outstanding musical talent.", "bot_name": "Xiaoya", "user_name": "Director" } ) print(response) ``` ### Assistant Conversation ```python from zhipuai import ZhipuAI client = ZhipuAI(api_key="your-api-key") response = client.assistant.conversation( assistant_id="your_assistant_id", # You can use 65940acff94777010aa6b796 for testing model="glm-4-assistant", messages=[ { "role": "user", "content": [{ "type": "text", "text": "Help me search for the latest ZhipuAI product information" }] } ], stream=True, attachments=None, metadata=None, request_id="request_1790291013237211136", user_id="12345678" ) for chunk in response: print(chunk) ``` ### Video Generation ```python from zhipuai import ZhipuAI client = ZhipuAI(api_key="your-api-key") response = client.videos.generations( model="cogvideox-2", prompt="A beautiful sunset beach scene", quality="quality", # Output mode: use "quality" for higher quality, "speed" for faster generation with_audio=True, # Generate video with background audio size="1920x1080", # Video resolution (up to 4K, e.g. "3840x2160") fps=30, # Frames per second (choose 30 fps or 60 fps) user_id="user_12345" ) # Generation may take some time result = client.videos.retrieve_videos_result(id=response.id) print(result) ``` ## 🚨 Error Handling The SDK provides comprehensive error handling: ```python from zhipuai import ZhipuAI import zhipuai client = ZhipuAI() try: response = client.chat.completions.create( model="glm-4", messages=[ {"role": "user", "content": "Hello, ZhipuAI!"} ] ) print(response.choices[0].message.content) except zhipuai.APIStatusError as err: print(f"API Status Error: {err}") except zhipuai.APITimeoutError as err: print(f"Request Timeout: {err}") except Exception as err: print(f"Other Error: {err}") ``` ### Error Codes | Status Code | Error Type | Description | |-------------|------------|-------------| | 400 | `APIRequestFailedError` | Invalid request parameters | | 401 | `APIAuthenticationError` | Authentication failed | | 429 | `APIReachLimitError` | Rate limit exceeded | | 500 | `APIInternalError` | Internal server error | | 503 | `APIServerFlowExceedError` | Server overloaded | | N/A | `APIStatusError` | General API error | ## 📈 Version Updates For detailed version history and update information, please see [Release-Note.md](Release-Note.md). ## 📄 License This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details. ## 🤝 Contributing Contributions are welcome! Please feel free to submit a Pull Request. ## 📞 Support For questions and technical support, please visit [ZhipuAI Open Platform](https://open.bigmodel.cn/) or check our documentation. ================================================ FILE: README_CN.md ================================================ Z.AI 和 智谱AI 的 [全新 Python SDK](https://github.com/zai-org/z-ai-sdk-python) 已经发布：[z-ai-sdk-python](https://github.com/zai-org/z-ai-sdk-python)！推荐使用此 SDK，以获得更好、更快的长期支持。 # 智谱AI开放平台 Python SDK [![PyPI version](https://img.shields.io/pypi/v/zhipuai.svg)](https://pypi.org/project/zhipuai/) [![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) [![Python](https://img.shields.io/badge/python-3.9%2B-blue.svg)](https://www.python.org/) [English Readme](README.md) [智谱AI开放平台](https://open.bigmodel.cn/dev/api)官方 Python SDK，帮助开发者快速集成智谱AI强大的人工智能能力到Python应用中。 ## ✨ 特性 - 🚀 **类型安全**: 所有接口完全类型封装，无需查阅API文档即可完成接入 - 🔧 **简单易用**: 简洁直观的API设计，快速上手 - ⚡ **高性能**: 基于现代Python库构建，性能优异 - 🛡️ **安全可靠**: 内置身份验证和令牌管理 - 📦 **轻量级**: 最小化依赖，易于项目集成 - 🔄 **流式支持**: 支持SSE流式响应和异步调用 ## 📦 安装 ### 环境要求 - Python 3.9 或更高版本 - pip 包管理器 ### 使用 pip 安装 ```sh pip install zhipuai ``` ### 📋 核心依赖 本SDK使用以下核心依赖库： | 依赖库 | 用途 | |--------|------| | httpx | HTTP客户端库 | | pydantic | 数据验证和序列化 | | typing-extensions | 类型注解扩展 | ## 🚀 快速开始 ### 基本用法 1. **使用API密钥创建客户端** 2. **调用相应的API方法** 完整示例请参考开放平台[接口文档](https://open.bigmodel.cn/dev/api)以及[使用指南](https://open.bigmodel.cn/dev/howuse/)，记得替换为您自己的API密钥。 ### 客户端配置 SDK支持多种方式配置API密钥： **环境变量配置：** ```bash export ZHIPUAI_API_KEY="your_api_key_here" export ZHIPUAI_BASE_URL="https://open.bigmodel.cn/api/paas/v4/" # 可选 ``` **代码配置：** ```python from zhipuai import ZhipuAI client = ZhipuAI( api_key="your_api_key_here", # 填写您的 APIKey ) ``` **高级配置：** SDK提供了灵活的客户端配置选项： ```python import httpx from zhipuai import ZhipuAI client = ZhipuAI( api_key="your_api_key_here", timeout=httpx.Timeout(timeout=300.0, connect=8.0), # 超时配置 max_retries=3, # 重试次数 base_url="https://open.bigmodel.cn/api/paas/v4/" # Custom API endpoint ) ``` **配置选项：** - `timeout`: 控制接口连接和读取超时时间 - `max_retries`: 控制重试次数，默认为3次 - `base_url`: 自定义API基础URL ## 💡 使用示例 ### 基础对话 ```python from zhipuai import ZhipuAI client = ZhipuAI(api_key="your-api-key") # 请填写您自己的APIKey response = client.chat.completions.create( model="glm-4", # 填写需要调用的模型名称 messages=[ {"role": "user", "content": "你好，请介绍一下智谱AI"} ], tools=[ { "type": "web_search", "web_search": { "search_query": "Search the Zhipu", "search_result": True, } } ], extra_body={"temperature": 0.5, "max_tokens": 50} ) print(response.choices[0].message.content) ``` ### 流式对话 ```python from zhipuai import ZhipuAI client = ZhipuAI(api_key="your-api-key") # 请填写您自己的APIKey response = client.chat.completions.create( model="glm-4", # 填写需要调用的模型名称 messages=[ {"role": "system", "content": "你是一个人工智能助手，你叫ChatGLM"}, {"role": "user", "content": "你好！你叫什么名字"}, ], stream=True, ) for chunk in response: if chunk.choices[0].delta.content: print(chunk.choices[0].delta) ``` ### 多模态对话 ```python import base64 from zhipuai import ZhipuAI def encode_image(image_path): """将图片编码为base64格式""" with open(image_path, "rb") as image_file: return base64.b64encode(image_file.read()).decode('utf-8') client = ZhipuAI() # 请填写您自己的APIKey base64_image = encode_image("path/to/your/image.jpg") response = client.chat.completions.create( model="glm-4v", # 视觉模型 messages=[ { "role": "user", "content": [ { "type": "text", "text": "请描述这张图片的内容" }, { "type": "image_url", "image_url": { "url": f"data:image/jpeg;base64,{base64_image}" } } ] } ], extra_body={"temperature": 0.5, "max_tokens": 50} ) print(response.choices[0].message.content) ``` ### 角色扮演 ```python from zhipuai import ZhipuAI client = ZhipuAI() # 请填写您自己的APIKey response = client.chat.completions.create( model="charglm-3", # 角色扮演模型 messages=[ { "role": "user", "content": "你好，最近在忙什么呢？" } ], meta={ "user_info": "我是一位电影导演，擅长拍摄音乐题材的电影。", "bot_info": "你是一位当红的国内女歌手及演员，拥有出众的音乐才华。", "bot_name": "小雅", "user_name": "导演" }, ) print(response.choices[0].message.content) ``` ### 智能体对话 ```python from zhipuai import ZhipuAI client = ZhipuAI() # 请填写您自己的APIKey response = client.assistant.conversation( assistant_id="your_assistant_id", # 智能体ID，可用 65940acff94777010aa6b796 进行测试 model="glm-4-assistant", messages=[ { "role": "user", "content": [{ "type": "text", "text": "帮我搜索智谱AI的最新产品信息" }] } ], stream=True, attachments=None, metadata=None, request_id="request_1790291013237211136", user_id="12345678" ) for chunk in response: print(chunk) ``` ### 视频生成 ```python from zhipuai import ZhipuAI client = ZhipuAI(api_key="your-api-key") response = client.videos.generations( model="cogvideox-2", prompt="一个美丽的日落海滩场景", # 生成内容的提示词 quality="quality", # 输出模式：'quality' 表示质量优先，'speed' 表示速度优先 with_audio=True, # 生成带背景音频的视频 size="1920x1080", # 视频分辨率（最高支持 4K，例如 "3840x2160"） fps=30, # 帧率（可选 30 或 60） user_id="user_12345" ) # 生成过程可能需要一些时间 result = client.videos.retrieve_videos_result(id=response.id) print(result) ``` ## 🚨 异常处理 SDK提供了完善的异常处理机制： ```python from zhipuai import ZhipuAI import zhipuai client = ZhipuAI() # 请填写您自己的APIKey try: response = client.chat.completions.create( model="glm-4", messages=[ {"role": "user", "content": "你好，智谱AI！"} ] ) print(response.choices[0].message.content) except zhipuai.APIStatusError as err: print(f"API状态错误: {err}") except zhipuai.APITimeoutError as err: print(f"请求超时: {err}") except Exception as err: print(f"其他错误: {err}") ``` ### 错误码说明 | 状态码 | 错误类型 | 说明 | |--------|----------|------| | 400 | `APIRequestFailedError` | 请求参数错误 | | 401 | `APIAuthenticationError` | 身份验证失败 | | 429 | `APIReachLimitError` | 请求频率超限 | | 500 | `APIInternalError` | 服务器内部错误 | | 503 | `APIServerFlowExceedError` | 服务器流量超限 | | N/A | `APIStatusError` | 通用API错误 | ## 📈 版本更新 详细的版本更新记录和历史信息，请查看 [Release-Note.md](Release-Note.md)。 ## 📄 许可证 本项目基于 MIT 许可证开源 - 详情请查看 [LICENSE](LICENSE) 文件。 ## 🤝 贡献 欢迎贡献代码！请随时提交 Pull Request。 ## 📞 支持 如有问题和技术支持，请访问 [智谱AI开放平台](https://open.bigmodel.cn/) 或查看我们的文档。 ================================================ FILE: Release-Note.md ================================================ ## Release Notes ### 2024-08-12 **New Features:** - Modified video prompt to be optional, added file deletion functionality - Added Assistant business logic - Fixed embedding 3 dimensions ### 2024-07-25 **Bug Fixes:** - Fixed cogvideo related issues ### 2024-07-12 **New Features:** - Added advanced search tool Web search business logic - Specified Python versions support (3.8, 3.9, 3.10, 3.11, 3.12) - Integrated cogvideo business functionality ### 2024-05-20 **Improvements:** - Fixed some `python3.12` dependency issues - Added pagination processing code, rewrote instantiation rules for some response classes - Added type conversion validation - Added batch task related APIs - Added file stream response wrapper ### 2024-04-29 **Improvements:** - Fixed some `python3.7` code compatibility issues - Added interface failure retry mechanism, controlled by `retry` parameter with default of 3 retries - Adjusted interface timeout strategy, controlled by `Timeout` for interface `connect` and `read` timeout, default `timeout=300.0, connect=8.0` - Added support for super-humanoid large model parameters in conversation module, `model="charglm-3"`, `meta` parameter support ### 2024-04-23 **Improvements:** - Fixed some compatibility issues with `pydantic<3,>=1.9.0` - Message processing business request and response parameters can be extended through configuration - Compatible with some parameters `top_p:1`, `temperature:0` (do_sample rewritten to false, parameters top_p temperature do not take effect) - Image understanding part, image_url parameter base64 content containing `data:image/jpeg;base64` compatibility - Removed JWT authentication logic --- ## Migration Guide For users upgrading from older versions, please note the following breaking changes: ### From v3.x to v4.x - API key configuration has been simplified - Some method signatures have changed for better type safety - Error handling has been improved with more specific exception types ## Support For questions about specific versions or upgrade assistance, please visit our [documentation](https://open.bigmodel.cn/) or contact our support team. --- ## 版本更新 ### 2024-08-12 **新功能：** - ✅ 视频提示词设为可选，新增文件删除功能 - ✅ 智能助手业务逻辑 - 🔧 修复 embedding 3 维度问题 ### 2024-07-25 **问题修复：** - 🔧 修复 cogvideo 相关问题 ### 2024-07-12 **新功能：** - ✅ 高级搜索工具 Web search 业务逻辑 - ✅ 指定 Python 版本支持 (3.8, 3.9, 3.10, 3.11, 3.12) - ✅ 集成 cogvideo 业务功能 ### 2024-05-20 **改进优化：** - 🔧 修复部分 `python3.12` 依赖问题 - ✅ 新增分页处理代码，重写部分响应类实例化规则 - ✅ 新增类型转换校验 - ✅ 批处理任务相关 API - ✅ 文件流响应包装器 ### 2024-04-29 **改进优化：** - 🔧 修复部分 `python3.7` 代码兼容性问题 - ✅ 接口失败重试机制，通过 `retry` 参数控制重试次数，默认 3 次 - ⏱️ 调整接口超时策略，通过 `Timeout` 控制接口 `connect` 和 `read` 超时时间，默认 `timeout=300.0, connect=8.0` - ✅ 对话模块新增超拟人大模型参数支持，`model="charglm-3"`，`meta` 参数支持 ### 2024-04-23 **改进优化：** - 🔧 修复部分 `pydantic<3,>=1.9.0` 兼容性问题 - ✅ 报文处理的业务请求参数和响应参数可通过配置扩充 - ✅ 兼容部分参数 `top_p:1`，`temperature:0`（do_sample 重写为 false，参数 top_p temperature 不生效） - ✅ 图像理解部分，image_url 参数 base64 内容包含 `data:image/jpeg;base64` 兼容性 - 🔄 删除 JWT 认证逻辑 --- ## 迁移指南 对于从旧版本升级的用户，请注意以下重大变更： ### 从 v3.x 到 v4.x - API 密钥配置已简化 - 部分方法签名已更改以提供更好的类型安全性 - 错误处理已改进，提供更具体的异常类型 ## 技术支持 如有特定版本问题或升级协助需求，请访问我们的[文档](https://open.bigmodel.cn/)或联系我们的支持团队。 ================================================ FILE: poetry.toml ================================================ [virtualenvs] in-project = true [installer] modern-installation = false ================================================ FILE: pyproject.toml ================================================ [tool.poetry] name = "zhipuai" version = "2.1.5.20250825" description = "A SDK library for accessing big model apis from ZhipuAI" authors = ["Zhipu AI"] readme = "README.md" [tool.poetry.dependencies] python = ">=3.8,<4.0.0,!=3.9.7 " httpx = ">=0.23.0" pydantic = ">=1.9.0,<3.0" pydantic-core = ">=2.14.6" cachetools = ">=4.2.2" pyjwt = "~=2.8.0" [tool.poetry.group.test.dependencies] # The only dependencies that should be added are # dependencies used for running tests (e.g., pytest, freezegun, response). # Any dependencies that do not meet that criteria will be removed. pytest = "^7.3.0" pytest-cov = "^4.0.0" pytest-dotenv = "^0.5.2" duckdb-engine = "^0.9.2" pytest-watcher = "^0.2.6" freezegun = "^1.2.2" responses = "^0.22.0" pytest-asyncio = { version = "^0.23.2", python = "^3.8" } lark = "^1.1.5" pytest-mock = "^3.10.0" pytest-socket = { version = "^0.6.0", python = ">=3.8.1,<3.9.7 || >3.9.7,<4.0" } syrupy = { version = "^4.0.2", python = ">=3.8.1,<3.9.7 || >3.9.7,<4.0" } requests-mock = "^1.11.0" respx = "0.21.1" [tool.poetry.group.lint] optional = true [tool.poetry.group.lint.dependencies] ruff = "^0.1.5" [tool.poetry.extras] cli = ["typer"] # An extra used to be able to add extended testing. # Please use new-line on formatting to make it easier to add new packages without # merge-conflicts extended_testing = [ "langchain", ] [tool.ruff.lint] select = [ "E", # pycodestyle "F", # pyflakes "I", # isort "T201", # print ] [tool.ruff] line-length = 88 [tool.ruff.format] quote-style = "single" indent-style = "tab" docstring-code-format = true [tool.coverage.run] omit = [ "tests/*", ] [build-system] requires = ["poetry-core>=1.0.0", "poetry-plugin-pypi-mirror==0.4.2"] build-backend = "poetry.core.masonry.api" [tool.pytest.ini_options] # --strict-markers will raise errors on unknown marks. # https://docs.pytest.org/en/7.1.x/how-to/mark.html#raising-errors-on-unknown-marks # # https://docs.pytest.org/en/7.1.x/reference/reference.html # --strict-config any warnings encountered while parsing the `pytest` # section of the configuration file raise errors. # # https://github.com/tophat/syrupy # --snapshot-warn-unused Prints a warning on unused snapshots rather than fail the test suite. addopts = "--strict-markers --strict-config --durations=5 --snapshot-warn-unused -svv" # Registering custom markers. # https://docs.pytest.org/en/7.1.x/example/markers.html#registering-markers markers = [ "requires: mark tests as requiring a specific library", "scheduled: mark tests to run in scheduled testing", "compile: mark placeholder test used to compile integration tests without running them" ] asyncio_mode = "auto" # https://python-poetry.org/docs/repositories/ #[[tool.poetry.source]] #name = "tsinghua" #url = "https://pypi.tuna.tsinghua.edu.cn/simple/" #priority = "default" ================================================ FILE: tests/conftest.py ================================================ """Configuration for unit tests.""" from importlib import util from pathlib import Path from typing import Dict, Sequence import pytest from pytest import Config, Function, Parser from zhipuai.core.logs import ( get_config_dict, get_log_file, get_timestamp_ms, ) def pytest_addoption(parser: Parser) -> None: """Add custom command line options to pytest.""" parser.addoption( '--only-extended', action='store_true', help='Only run extended tests. Does not allow skipping any extended tests.', ) parser.addoption( '--only-core', action='store_true', help='Only run core tests. Never runs any extended tests.', ) def pytest_collection_modifyitems(config: Config, items: Sequence[Function]) -> None: """Add implementations for handling custom markers. At the moment, this adds support for a custom `requires` marker. The `requires` marker is used to denote tests that require one or more packages to be installed to run. If the package is not installed, the test is skipped. The `requires` marker syntax is: .. code-block:: python @pytest.mark.requires('package1', 'package2') def test_something(): ... """ # Mapping from the name of a package to whether it is installed or not. # Used to avoid repeated calls to `util.find_spec` required_pkgs_info: Dict[str, bool] = {} only_extended = config.getoption('--only-extended') or False only_core = config.getoption('--only-core') or False if only_extended and only_core: raise ValueError('Cannot specify both `--only-extended` and `--only-core`.') for item in items: requires_marker = item.get_closest_marker('requires') if requires_marker is not None: if only_core: item.add_marker(pytest.mark.skip(reason='Skipping not a core test.')) continue # Iterate through the list of required packages required_pkgs = requires_marker.args for pkg in required_pkgs: # If we haven't yet checked whether the pkg is installed # let's check it and store the result. if pkg not in required_pkgs_info: try: installed = util.find_spec(pkg) is not None except Exception: installed = False required_pkgs_info[pkg] = installed if not required_pkgs_info[pkg]: if only_extended: pytest.fail( f'Package `{pkg}` is not installed but is required for ' f'extended tests. Please install the given package and ' f'try again.', ) else: # If the package is not installed, we immediately break # and mark the test as skipped. item.add_marker(pytest.mark.skip(reason=f'Requires pkg: `{pkg}`')) break else: if only_extended: item.add_marker(pytest.mark.skip(reason='Skipping not an extended test.')) @pytest.fixture def logging_conf() -> dict: return get_config_dict( 'info', get_log_file(log_path='logs', sub_dir=f'local_{get_timestamp_ms()}'), 1024 * 1024, 1024 * 1024 * 1024, ) @pytest.fixture def test_file_path(request) -> Path: from pathlib import Path # 当前执行目录 # 获取当前测试文件的路径 test_file_path = Path(str(request.fspath)).parent print('test_file_path:', test_file_path) return test_file_path ================================================ FILE: tests/integration_tests/batchinput.jsonl ================================================ {"custom_id": "request-1", "method": "POST", "url": "/v4/chat/completions", "body": {"model": "glm-4", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}} {"custom_id": "request-2", "method": "POST", "url": "/v4/chat/completions", "body": {"model": "glm-4", "messages": [{"role": "system", "content": "You are an unhelpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}} ================================================ FILE: tests/integration_tests/demo.jsonl ================================================ {"messages": [{"role": "system", "content": "你是一位乐于助人，知识渊博的全能AI助手。"},{"role": "user", "content": "请介绍一下AlphaGo的基本原理。"}, {"role": "assistant", "content": "AlphaGo利用深度神经网络与树搜索算法相结合,通过对弈数据进行训练,逐步提升游戏水平,能够对围棋局面进行判断并选择最佳落子位置。"}]} {"messages": [{"role": "system", "content": "你是一位乐于助人，知识渊博的全能AI助手。"},{"role": "user", "content": "请列举一些健康饮食的重要原则。"}, {"role": "assistant", "content": "健康饮食的重要原则包括:膳食应营养均衡,合理摄入各种营养素;多吃新鲜蔬果,适量饮水;少吃糖、油、盐,忌吃过量快餐;养成规律生活作息习惯,适量运动。"}]} {"messages": [{"role": "system", "content": "你是一位乐于助人，知识渊博的全能AI助手。"},{"role": "user", "content": "请给出一些改善睡眠质量的建议。"}, {"role": "assistant", "content": "改善睡眠质量的建议包括:保证睡眠时间,避免睡眠不足;睡前放松身心,远离刺激;养成规律作息时间,不要频繁熬夜;适量运动,但不要运动过度;睡前可以喝一杯热牛奶等温和饮料。"}]} ================================================ FILE: tests/integration_tests/test.py ================================================ import time from zhipuai import ZhipuAI client = ZhipuAI() # 填写您自己的APIKey response = client.videos.generations( model='cogvideo', prompt='一个年轻的艺术家在一片彩虹上用调色板作画。', # prompt="一只卡通狐狸在森林里跳着欢快的爵士舞。" # prompt="这是一部汽车广告片，描述了一位30岁的汽车赛车手戴着红色头盔的赛车冒险。背景是蔚蓝的天空和苛刻的沙漠环境，电影风格使用35毫米胶片拍摄，色彩鲜艳夺目。" ) print(response) task_id = response.id task_status = response.task_status get_cnt = 0 while task_status == 'PROCESSING' and get_cnt <= 40: result_response = client.videos.retrieve_videos_result(id=task_id) print(result_response) task_status = result_response.task_status time.sleep(2) get_cnt += 1 ================================================ FILE: tests/integration_tests/test_agents.py ================================================ import logging import logging.config import time import zhipuai from zhipuai import ZhipuAI def test_completions_sync(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.agents.invoke( request_id=request_id, agent_id='general_translation', messages=[{'role': 'user', 'content': 'tell me a joke'}], user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_completions_stream(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.agents.invoke( request_id=request_id, agent_id='general_translation', messages=[{'role': 'user', 'content': 'tell me a joke'}], user_id='12345678', stream=True, ) for item in response: print(item) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_correction(): client = ZhipuAI() # 请替换为实际API密钥 response = client.agents.invoke( agent_id="intelligent_education_correction_agent", messages=[ { "role": "user", "content": [ { "type": "image_url", "image_url": "https://b0.bdstatic.com/e24937f1f6b9c0ff6895e1012c981515.jpg" } ] } ] ) print(response) def test_correction_result(image_id,uuids,trace_id): client = ZhipuAI() response = client.agents.async_result( agent_id="intelligent_education_correction_polling", custom_variables={ "images": [ { "image_id": image_id, "uuids": uuids } ], "trace_id": trace_id } ) print(response) def main(): test_completions_sync() test_completions_stream() # test_correction() # test_correction_result(image_id,uuids,trace_id) if __name__ == "__main__": main() ================================================ FILE: tests/integration_tests/test_assistant.py ================================================ import logging import logging.config import zhipuai from zhipuai import ZhipuAI def test_assistant(logging_conf) -> None: logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: generate = client.assistant.conversation( assistant_id='659e54b1b8006379b4b2abd6', messages=[ { 'role': 'user', 'content': [{'type': 'text', 'text': '帮我搜索下智谱的cogvideox发布时间'}], } ], stream=True, attachments=None, metadata=None, request_id='request_1790291013237211136', user_id='12345678', ) for assistant in generate: print(assistant) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_assistant_query_support(logging_conf) -> None: logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.assistant.query_support( assistant_id_list=[], request_id='request_1790291013237211136', user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_assistant_query_conversation_usage(logging_conf) -> None: logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.assistant.query_conversation_usage( assistant_id='659e54b1b8006379b4b2abd6', request_id='request_1790291013237211136', user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_translate_api(logging_conf) -> None: logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: translate_response = client.assistant.conversation( assistant_id='9996ijk789lmn012o345p999', messages=[{'role': 'user', 'content': [{'type': 'text', 'text': '你好呀'}]}], stream=True, attachments=None, metadata=None, request_id='request_1790291013237211136', user_id='12345678', extra_parameters={'translate': {'from': 'zh', 'to': 'en'}}, ) for chunk in translate_response: print(chunk.choices[0].delta) # print(translate_response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_audio.py ================================================ import base64 import json import logging import logging.config from pathlib import Path import zhipuai from zhipuai import ZhipuAI def test_audio_speech(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: speech_file_path = Path(__file__).parent / 'speech.wav' response = client.audio.speech( model='cogtts', input='你好呀,欢迎来到智谱开放平台', voice='tongtong', stream=False, response_format='wav', ) response.stream_to_file(speech_file_path) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_audio_speech_streaming(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.audio.speech( model='cogtts', input='你好呀,欢迎来到智谱开放平台', voice='tongtong', stream=True, response_format='mp3', encode_format='hex' ) with open("output.mp3", "wb") as f: for item in response: choice = item.choices[0] index = choice.index finish_reason = choice.finish_reason audio_delta = choice.delta.content if finish_reason is not None: break f.write(bytes.fromhex(audio_delta)) print(f"audio delta: {audio_delta[:64]}..., 长度:{len(audio_delta)}") except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) except Exception as e: print(e) def test_audio_customization(logging_conf): logging.config.dictConfig(logging_conf) client = ZhipuAI() # 填写您自己的APIKey with open(Path(__file__).parent / 'speech.wav', 'rb') as file: try: speech_file_path = Path(__file__).parent / 'speech.wav' response = client.audio.customization( model='cogtts', input='你好呀,欢迎来到智谱开放平台', voice_text='这是一条测试用例', voice_data=file, response_format='wav', ) response.stream_to_file(speech_file_path) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_batches.py ================================================ import logging import logging.config import os import zhipuai from zhipuai import ZhipuAI def test_batch_input_file(test_file_path, logging_conf) -> None: logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: batch_input_file = client.files.create( file=open(os.path.join(test_file_path, 'batchinput.jsonl'), 'rb'), purpose='batch', ) print(batch_input_file) # FileObject(id='20240514_ea19d21b-d256-4586-b0df-e80a45e3c286', bytes=490, created_at=1715673494, filename=None, object='file', purpose='batch', status=None, status_details=None, fileName='batchinput.jsonl') except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_batch_create(logging_conf) -> None: logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: create = client.batches.create( input_file_id='20240514_ea19d21b-d256-4586-b0df-e80a45e3c286', endpoint='/v4/chat/completions', completion_window='24h', metadata={'description': 'job test'}, auto_delete_input_file=True, ) print(create) # Batch(id='batch_1790292763050508288', completion_window='24h', created_at=1715674031399, endpoint='/v4/chat/completions', input_file_id='20240514_ea19d21b-d256-4586-b0df-e80a45e3c286', object='batch', status='validating', cancelled_at=None, cancelling_at=None, completed_at=None, error_file_id=None, errors=None, expired_at=None, expires_at=None, failed_at=None, finalizing_at=None, in_progress_at=None, metadata={'description': 'job test'}, output_file_id=None, request_counts=BatchRequestCounts(completed=None, failed=None, total=None)) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_batch_retrieve(logging_conf) -> None: logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: retrieve = client.batches.retrieve('batch_1790291013237211136') print(retrieve) # Batch(id='batch_1790291013237211136', completion_window='24h', created_at=1715673614000, endpoint='/v4/chat/completions', input_file_id='20240514_ea19d21b-d256-4586-b0df-e80a45e3c286', object='batch', status='validating', cancelled_at=None, cancelling_at=None, completed_at=None, error_file_id='', errors=None, expired_at=None, expires_at=None, failed_at=None, finalizing_at=None, in_progress_at=None, metadata={'description': 'job test'}, output_file_id='', request_counts=BatchRequestCounts(completed=None, failed=None, total=None)) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_batch_cancel(logging_conf) -> None: logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: cancel = client.batches.cancel('batch_1790291013237211136') print(cancel) # Batch(id='batch_1790291013237211136', completion_window='24h', created_at=1715673614000, endpoint='/v4/chat/completions', input_file_id='20240514_ea19d21b-d256-4586-b0df-e80a45e3c286', object='batch', status='cancelling', cancelled_at=None, cancelling_at=1715673698775, completed_at=None, error_file_id='', errors=None, expired_at=None, expires_at=None, failed_at=None, finalizing_at=None, in_progress_at=None, metadata={'description': 'job test'}, output_file_id='', request_counts=BatchRequestCounts(completed=None, failed=None, total=None)) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_batch_list(logging_conf) -> None: logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: list = client.batches.list(limit=10) print(list) if list.has_more: print('_________get_next_page___________') batch = list.get_next_page() print(batch) print('_________iter_pages___________') for batch in list.iter_pages(): print(batch) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_batch_result(test_file_path, logging_conf) -> None: logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: content = client.files.content('file-QDpVyDIhxj8mcFiduUydNqQN') with open(os.path.join(test_file_path, 'content_batchoutput.jsonl'), 'wb') as f: f.write(content.content) content.write_to_file(os.path.join(test_file_path, 'write_to_file_batchoutput.jsonl')) assert ( content.content == open(os.path.join(test_file_path, 'batchoutput.jsonl'), 'rb').read() ) assert ( content.content == open(os.path.join(test_file_path, 'write_to_file_batchoutput.jsonl'), 'rb').read() ) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_charglm3.py ================================================ # -*- coding: utf-8 -*- import logging import logging.config import zhipuai from zhipuai import ZhipuAI def test_completions_charglm(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 请填写您自己的APIKey try: response = client.chat.completions.create( model='charglm-3', # 填写需要调用的模型名称 messages=[{'role': 'user', 'content': '请问你在做什么'}], meta={ 'user_info': '我是陆星辰，是一个男性，是一位知名导演，也是苏梦远的合作导演。我擅长拍摄音乐题材的电影。苏梦远对我的态度是尊敬的，并视我为良师益友。', 'bot_info': '苏梦远，本名苏远心，是一位当红的国内女歌手及演员。在参加选秀节目后，凭借独特的嗓音及出众的舞台魅力迅速成名，进入娱乐圈。她外表美丽动人，但真正的魅力在于她的才华和勤奋。苏梦远是音乐学院毕业的优秀生，善于创作，拥有多首热门原创歌曲。除了音乐方面的成就，她还热衷于慈善事业，积极参加公益活动，用实际行动传递正能量。在工作中，她对待工作非常敬业，拍戏时总是全身心投入角色，赢得了业内人士的赞誉和粉丝的喜爱。虽然在娱乐圈，但她始终保持低调、谦逊的态度，深得同行尊重。在表达时，苏梦远喜欢使用“我们”和“一起”，强调团队精神。', 'bot_name': '苏梦远', 'user_name': '陆星辰', }, user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_async_completions(): client = ZhipuAI() # 请填写您自己的APIKey try: response = client.chat.asyncCompletions.create( model='charglm', # 填写需要调用的模型名称 messages=[{'role': 'user', 'content': '请问你在做什么'}], meta={ 'user_info': '我是陆星辰，是一个男性，是一位知名导演，也是苏梦远的合作导演。我擅长拍摄音乐题材的电影。苏梦远对我的态度是尊敬的，并视我为良师益友。', 'bot_info': '苏梦远，本名苏远心，是一位当红的国内女歌手及演员。在参加选秀节目后，凭借独特的嗓音及出众的舞台魅力迅速成名，进入娱乐圈。她外表美丽动人，但真正的魅力在于她的才华和勤奋。苏梦远是音乐学院毕业的优秀生，善于创作，拥有多首热门原创歌曲。除了音乐方面的成就，她还热衷于慈善事业，积极参加公益活动，用实际行动传递正能量。在工作中，她对待工作非常敬业，拍戏时总是全身心投入角色，赢得了业内人士的赞誉和粉丝的喜爱。虽然在娱乐圈，但她始终保持低调、谦逊的态度，深得同行尊重。在表达时，苏梦远喜欢使用“我们”和“一起”，强调团队精神。', 'bot_name': '苏梦远', 'user_name': '陆星辰', }, ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) # def test_retrieve_completion_result(): # client = ZhipuAI() # 请填写您自己的APIKey # try: # response = client.chat.asyncCompletions.retrieve_completion_result(id="1014908592669352541650991") # print(response) # # # except zhipuai.core._errors.APIRequestFailedError as err: # print(err) # except zhipuai.core._errors.APIInternalError as err: # print(err) # if __name__ == "__main__": # test_retrieve_completion_result() ================================================ FILE: tests/integration_tests/test_chat.py ================================================ import logging import logging.config import os.path import time import zhipuai from zhipuai import ZhipuAI def test_completions_temp0(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4', messages=[{'role': 'user', 'content': 'tell me a joke'}], top_p=0.7, temperature=0, max_tokens=2000, user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_completions_temp1(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4', messages=[{'role': 'user', 'content': 'tell me a joke'}], top_p=0.7, temperature=1, max_tokens=2000, user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_completions_top0(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4', messages=[{'role': 'user', 'content': 'tell me a joke'}], top_p=0, temperature=0.9, max_tokens=2000, user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_completions_top1(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4', messages=[{'role': 'user', 'content': 'tell me a joke'}], top_p=1, temperature=0.9, max_tokens=2000, user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_completions(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4', # 填写需要调用的模型名称 messages=[ { 'role': 'user', 'content': '作为一名营销专家，请为我的产品创作一个吸引人的slogan', }, { 'role': 'assistant', 'content': '当然，为了创作一个吸引人的slogan，请告诉我一些关于您产品的信息', }, {'role': 'user', 'content': '智谱AI开放平台'}, { 'role': 'assistant', 'content': '智启未来，谱绘无限一智谱AI，让创新触手可及!', }, {'role': 'user', 'content': '创造一个更精准、吸引人的slogan'}, ], tools=[ { 'type': 'web_search', 'web_search': { 'search_query': '帮我看看清华的升学率', 'search_result': True, }, } ], user_id='12345678', extra_body={'temperature': 0.5, 'max_tokens': 50}, ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_completions_disenable_web_search(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4', # 填写需要调用的模型名称 messages=[ { 'role': 'user', 'content': '作为一名营销专家，请为我的产品创作一个吸引人的slogan', }, { 'role': 'assistant', 'content': '当然，为了创作一个吸引人的slogan，请告诉我一些关于您产品的信息', }, {'role': 'user', 'content': '智谱AI开放平台'}, { 'role': 'assistant', 'content': '智启未来，谱绘无限一智谱AI，让创新触手可及!', }, {'role': 'user', 'content': '创造一个更精准、吸引人的slogan'}, ], tools=[ { 'type': 'web_search', 'web_search': { 'search_query': '帮我看看清华的升学率', 'search_result': True, 'enable': False, }, } ], user_id='12345678', extra_body={'temperature': 0.5, 'max_tokens': 50}, ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_completions_enable_web_search(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4', # 填写需要调用的模型名称 messages=[ { 'role': 'user', 'content': '作为一名营销专家，请为我的产品创作一个吸引人的slogan', }, { 'role': 'assistant', 'content': '当然，为了创作一个吸引人的slogan，请告诉我一些关于您产品的信息', }, {'role': 'user', 'content': '智谱AI开放平台'}, { 'role': 'assistant', 'content': '智启未来，谱绘无限一智谱AI，让创新触手可及!', }, {'role': 'user', 'content': '创造一个更精准、吸引人的slogan'}, ], tools=[ { 'type': 'web_search', 'web_search': { 'search_query': '帮我看看清华的升学率', 'search_result': True, 'enable': True, }, } ], extra_body={'temperature': 0.5, 'max_tokens': 50}, user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_completions_stream(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4', # 填写需要调用的模型名称 stream=True, messages=[ { 'role': 'user', 'content': '作为一名营销专家，请为我的产品创作一个吸引人的slogan', }, { 'role': 'assistant', 'content': '当然，为了创作一个吸引人的slogan，请告诉我一些关于您产品的信息', }, {'role': 'user', 'content': '智谱AI开放平台'}, { 'role': 'assistant', 'content': '智启未来，谱绘无限一智谱AI，让创新触手可及!', }, {'role': 'user', 'content': '创造一个更精准、吸引人的slogan'}, ], extra_body={'temperature': 0.5, 'max_tokens': 50}, user_id='12345678', ) for item in response: print(item) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) # Function to encode the image def encode_image(image_path): import base64 with open(image_path, 'rb') as image_file: return base64.b64encode(image_file.read()).decode('utf-8') def test_completions_vis(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4v', # 填写需要调用的模型名称 extra_body={'temperature': 0.5, 'max_tokens': 50}, messages=[ { 'role': 'user', 'content': [ {'type': 'text', 'text': '图里有什么'}, { 'type': 'image_url', 'image_url': { 'url': 'https://img1.baidu.com/it/u=1369931113,3388870256&fm=253&app=138&size=w931&n=0&f=JPEG&fmt=auto?sec=1703696400&t=f3028c7a1dca43a080aeb8239f09cc2f' }, }, ], } ], user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_completions_vis_base64(test_file_path, logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: base64_image = encode_image(os.path.join(test_file_path, 'img/MetaGLM.png')) # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4v', # 填写需要调用的模型名称 extra_body={'temperature': 0.5, 'max_tokens': 50}, messages=[ { 'role': 'user', 'content': [ {'type': 'text', 'text': '图里有什么'}, # { # "type": "image_url", # "image_url": { # "url": "https://img1.baidu.com/it/u=1369931113,3388870256&fm=253&app=138&size=w931&n=0&f=JPEG&fmt=auto?sec=1703696400&t=f3028c7a1dca43a080aeb8239f09cc2f" # } # }, { 'type': 'image_url', 'image_url': {'url': f'data:image/jpeg;base64,{base64_image}'}, }, ], } ], user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_async_completions(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 请填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.asyncCompletions.create( request_id=request_id, model='glm-4', # 填写需要调用的模型名称 messages=[ { 'role': 'user', 'content': '作为一名营销专家，请为我的产品创作一个吸引人的slogan', }, { 'role': 'assistant', 'content': '当然，为了创作一个吸引人的slogan，请告诉我一些关于您产品的信息', }, {'role': 'user', 'content': '智谱AI开放平台'}, { 'role': 'assistant', 'content': '智启未来，谱绘无限一智谱AI，让创新触手可及!', }, {'role': 'user', 'content': '创造一个更精准、吸引人的slogan'}, ], tools=[ { 'type': 'web_search', 'web_search': { 'search_query': '帮我看看清华的升学率', 'search_result': True, }, } ], extra_body={'temperature': 0.5, 'max_tokens': 50}, user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_retrieve_completion_result(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 请填写您自己的APIKey try: response = client.chat.asyncCompletions.retrieve_completion_result( id='1014908592669352541651237' ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_completions_sensitive_word_check(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4', messages=[{'role': 'user', 'content': 'tell me a joke'}], top_p=1, temperature=0.9, max_tokens=2000, sensitive_word_check={'type': 'ALL', 'status': 'DISABLE'}, user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_code_geex.py ================================================ import logging import logging.config import time import zhipuai from zhipuai import ZhipuAI def test_code_geex(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='codegeex-4', messages=[ { 'role': 'system', 'content': """你是一位智能编程助手，你叫CodeGeeX。你会为用户回答关于编程、代码、计算机方面的任何问题，并提供格式规范、可以执行、准确安全的代码，并在必要时提供详细的解释。 任务：请为输入代码提供格式规范的注释，包含多行注释和单行注释，请注意不要改动原始代码，只需要添加注释。 请用中文回答。""", }, {'role': 'user', 'content': """写一个快速排序函数"""}, ], top_p=0.7, temperature=0.9, max_tokens=2000, stop=['<|endoftext|>', '<|user|>', '<|assistant|>', '<|observation|>'], extra={ 'target': { 'path': '11111', 'language': 'Python', 'code_prefix': 'EventSource.Factory factory = EventSources.createFactory(OkHttpUtils.getInstance());', 'code_suffix': 'TaskMonitorLocal taskMonitorLocal = getTaskMonitorLocal(algoMqReq);', }, 'contexts': [ { 'path': '/1/2', 'code': 'if(!sensitiveUser){ZpTraceUtils.addAsyncAttribute(algoMqReq.getTaskOrderNo(), ApiTraceProperty.request_params.getCode(), modelSendMap);', } ], }, ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_code_geex_async(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.asyncCompletions.create( request_id=request_id, model='codegeex-4', messages=[ { 'role': 'system', 'content': """你是一位智能编程助手，你叫CodeGeeX。你会为用户回答关于编程、代码、计算机方面的任何问题，并提供格式规范、可以执行、准确安全的代码，并在必要时提供详细的解释。 任务：请为输入代码提供格式规范的注释，包含多行注释和单行注释，请注意不要改动原始代码，只需要添加注释。 请用中文回答。""", }, {'role': 'user', 'content': """写一个快速排序函数"""}, ], top_p=0.7, temperature=0.9, max_tokens=2000, stop=['<|endoftext|>', '<|user|>', '<|assistant|>', '<|observation|>'], extra={ 'target': { 'path': '11111', 'language': 'Python', 'code_prefix': 'EventSource.Factory factory = EventSources.createFactory(OkHttpUtils.getInstance());', 'code_suffix': 'TaskMonitorLocal taskMonitorLocal = getTaskMonitorLocal(algoMqReq);', }, 'contexts': [ { 'path': '/1/2', 'code': 'if(!sensitiveUser){ZpTraceUtils.addAsyncAttribute(algoMqReq.getTaskOrderNo(), ApiTraceProperty.request_params.getCode(), modelSendMap);', } ], }, ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_geex_result(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 请填写您自己的APIKey try: response = client.chat.asyncCompletions.retrieve_completion_result( id='1014908807577524653187108' ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_embedding.py ================================================ import logging import logging.config import zhipuai from zhipuai import ZhipuAI def test_embeddings(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() try: response = client.embeddings.create( model='embedding-2', # 填写需要调用的模型名称 input='你好', extra_body={'model_version': 'v1'}, ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_embeddings_dimensions(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() try: response = client.embeddings.create( model='embedding-3', # 填写需要调用的模型名称 input='你好', dimensions=512, extra_body={'model_version': 'v1'}, ) assert response.data[0].object == 'embedding' assert len(response.data[0].embedding) == 512 print(len(response.data[0].embedding)) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_emohaa.py ================================================ # -*- coding: utf-8 -*- import logging import logging.config import zhipuai from zhipuai import ZhipuAI def test_completions_emohaa(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 请填写您自己的APIKey try: response = client.chat.completions.create( model='emohaa', # 填写需要调用的模型名称 messages=[ { 'role': 'assistant', 'content': '你好，我是Emohaa，很高兴见到你。请问有什么我可以帮忙的吗？', }, { 'role': 'user', 'content': '今天我休息，决定去西安保密逛逛，心情很好地喷上了我最爱的烟熏木制香', }, { 'role': 'assistant', 'content': '今天我休息，决定去西安保密逛逛，心情很好地喷上了我最爱的烟熏木制香', }, ], meta={ 'user_info': '30岁的男性软件工程师，兴趣包括阅读、徒步和编程', 'bot_info': 'Emohaa是一款基于Hill助人理论的情感支持AI，拥有专业的心理咨询话术能力', 'bot_name': 'Emohaa', 'user_name': '陆星辰', }, ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_file.py ================================================ from __future__ import annotations import logging import logging.config import os import pytest import zhipuai from zhipuai import ZhipuAI @pytest.fixture(scope='class') def test_server(): class SharedData: client = ZhipuAI() file_id1 = None file_id2 = None return SharedData() class TestZhipuAIFileServer: def test_logs(self, logging_conf): logging.config.dictConfig(logging_conf) # type: ignore def test_files(self, test_server, test_file_path): try: result = test_server.client.files.create( file=open(os.path.join(test_file_path, 'demo.jsonl'), 'rb'), purpose='fine-tune', ) print(result) test_server.file_id1 = result.id except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_files_validation(self, test_server, test_file_path): try: result = test_server.client.files.create( file=open(os.path.join(test_file_path, 'demo.jsonl'), 'rb'), purpose='fine-tune', ) print(result) test_server.file_id2 = result.id except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_files_list(self, test_server): try: list = test_server.client.files.list() print(list) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_delete_files(self, test_server): try: delete1 = test_server.client.files.delete(file_id=test_server.file_id1) print(delete1) delete2 = test_server.client.files.delete(file_id=test_server.file_id2) print(delete2) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_file_parser.py ================================================ from __future__ import annotations import logging import logging.config import os import pytest import zhipuai from zhipuai import ZhipuAI def test_file_parser_create(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.file_parser.create(file=open('hitsuyoushorui-cn.pdf', 'rb'), file_type='pdf', tool_type='zhipu_pro') print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_file_parser_content(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.file_parser.content(task_id="66e8f7ab884448c8b4190f251f6c2982-1", format_type="text") print(response.content.decode('utf-8')) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_finetuning.py ================================================ import logging import logging.config import zhipuai from zhipuai import ZhipuAI def test_finetuning_create(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 请填写您自己的APIKey try: job = client.fine_tuning.jobs.create( model='chatglm3-6b', training_file='file-20240428021923715-xjng4', # 请填写已成功上传的文件id validation_file='file-20240428021923715-xjng4', # 请填写已成功上传的文件id suffix='demo_test', ) job_id = job.id print(job_id) fine_tuning_job = client.fine_tuning.jobs.retrieve(fine_tuning_job_id=job_id) print(fine_tuning_job) # ftjob-20240418110039323-j8lh2 except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_finetuning_retrieve(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 请填写您自己的APIKey try: fine_tuning_job = client.fine_tuning.jobs.retrieve( fine_tuning_job_id='ftjob-20240429112551154-48vq7' ) print(fine_tuning_job) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_finetuning_job_list(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 请填写您自己的APIKey try: job_list = client.fine_tuning.jobs.list() print(job_list) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_finetuning_job_cancel(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 请填写您自己的APIKey try: cancel = client.fine_tuning.jobs.cancel(fine_tuning_job_id='ftjob-20240429112551154-48vq7') print(cancel) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_finetuning_job_delete(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 请填写您自己的APIKey try: delete = client.fine_tuning.jobs.delete(fine_tuning_job_id='ftjob-20240126113041678-cs6s9') print(delete) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_model_check(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.chat.completions.create( model='chatglm3-6b-8572905046912426020-demo_test', # 填写需要调用的模型名称 messages=[ {'role': 'user', 'content': '你是一位乐于助人，知识渊博的全能AI助手。'}, {'role': 'user', 'content': '创造一个更精准、吸引人的slogan'}, ], extra_body={'temperature': 0.5, 'max_tokens': 50}, ) print(response.choices[0].message) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_model_delete(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: delete = client.fine_tuning.models.delete( fine_tuned_model='chatglm3-6b-8572905046912426020-demo_test' ) print(delete) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) if __name__ == '__main__': test_finetuning_create() ================================================ FILE: tests/integration_tests/test_images.py ================================================ import logging import logging.config import zhipuai from zhipuai import ZhipuAI def test_images(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.images.generations( model='cogview-3', # 填写需要调用的模型名称 prompt='一只可爱的小猫咪', extra_body={'user_id': '1222212'}, user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_images_sensitive_word_check(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.images.generations( model='cogview-3', # 填写需要调用的模型名称 prompt='一只可爱的小猫咪', sensitive_word_check={'type': 'ALL', 'status': 'DISABLE'}, extra_body={'user_id': '1222212'}, user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_knowledge.py ================================================ from __future__ import annotations import logging import logging.config import os import pytest import zhipuai from zhipuai import ZhipuAI @pytest.fixture(scope='class') def test_server(): class SharedData: client = ZhipuAI() test_knowledge_document_id = None test_knowledge_id = None return SharedData() class TestZhipuAIKnowledgeServer: def test_logs(self, logging_conf): logging.config.dictConfig(logging_conf) # type: ignore def test_knowledge_create(self, test_server): try: result = test_server.client.knowledge.create( embedding_id=1, name='test', description='测试', background='blue', icon='question', ) print(result) test_server.test_knowledge_id = result.id except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_knowledge_document_create(self, test_server, test_file_path): try: result = test_server.client.knowledge.document.create( file=open(os.path.join(test_file_path, 'file.xlsx'), 'rb'), purpose='retrieval', knowledge_id=test_server.test_knowledge_id, sentence_size=202, ) print(result) test_server.test_knowledge_document_id = result.successInfos[0].documentId except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_knowledge_modify(self, test_server): try: result = test_server.client.knowledge.modify( knowledge_id=test_server.test_knowledge_id, embedding_id=1, name='测试1', background='red', icon='book', ) print(result) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_knowledge_query(self, test_server): try: result = test_server.client.knowledge.query() print(result) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_knowledge_used(self, test_server): try: result = test_server.client.knowledge.used() print(result) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_knowledge_document_retrieve(self, test_server, test_file_path): try: result = test_server.client.knowledge.document.retrieve( test_server.test_knowledge_document_id ) print(result) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_knowledge_document_edit(self, test_server): try: result = test_server.client.knowledge.document.edit( document_id=test_server.test_knowledge_document_id, knowledge_type='1', sentence_size=204, ) print(result) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_knowledge_document_list(self, test_server): try: result = test_server.client.knowledge.document.list( test_server.test_knowledge_id, purpose='retrieval' ) print(result) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_knowledge_document_delete(self, test_server): try: file1 = test_server.client.knowledge.document.delete( test_server.test_knowledge_document_id ) print(file1) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_knowledge_delete(self, test_server): try: result = test_server.client.knowledge.delete(knowledge_id=test_server.test_knowledge_id) print(result) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_moderation.py ================================================ import logging import logging.config import time import zhipuai from zhipuai import ZhipuAI def test_completions_temp0(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI(disable_token_cache=False) # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.moderations.create( model='moderations', input={'type': 'text', 'text': 'hello world '} ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_tools.py ================================================ import logging import logging.config import zhipuai from zhipuai import ZhipuAI def test_tools(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.tools.web_search( model='web-search-pro', messages=[ { 'content': '你好', 'role': 'user', } ], stream=False, ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_tools_stream(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.tools.web_search( model='web-search-pro', messages=[ { 'content': '你好', 'role': 'user', } ], stream=True, ) for item in response: print(item) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_transcriptions.py ================================================ import logging import logging.config from pathlib import Path import zhipuai from zhipuai import ZhipuAI def test_transcriptions(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: with open(Path(__file__).parent / 'asr1.wav', 'rb') as audio_file: transcriptResponse = client.audio.transcriptions.create( model='glm-asr', file=audio_file, stream=False ) print(transcriptResponse) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_transcriptions_stream(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: with open(Path(__file__).parent / 'asr1.wav', 'rb') as audio_file: transcriptResponse = client.audio.transcriptions.create( model='glm-asr', file=audio_file, stream=True ) for item in transcriptResponse: print(item) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_videos.py ================================================ import logging import logging.config import zhipuai from zhipuai import ZhipuAI def test_videos(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.videos.generations( model='cogvideox', prompt='一个开船的人', user_id='1212222' ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_videos_sensitive_word_check(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.videos.generations( model='cogvideo', prompt='一个开船的人', sensitive_word_check={'type': 'ALL', 'status': 'DISABLE'}, user_id='1212222', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_videos_image_url(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.videos.generations( model='cogvideo', image_url='https://cdn.bigmodel.cn/static/platform/images/solutions/car/empowerment/icon-metric.png', prompt='一些相信光的人，举着奥特曼', user_id='12222211', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_retrieve_videos_result(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.videos.retrieve_videos_result(id='1014908869548405238276203') print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_vlm_thinking.py ================================================ import logging import logging.config import time import zhipuai from zhipuai import ZhipuAI def test_completions_vlm_thinking(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4.1v-thinking-flash', # 填写需要调用的模型名称 messages=[ { 'role': 'user', 'content': [ {'type': 'text', 'text': '图里有什么'}, { 'type': 'image_url', 'image_url': { 'url': 'https://img1.baidu.com/it/u=1369931113,3388870256&fm=253&app=138&size=w931&n=0&f=JPEG&fmt=auto?sec=1703696400&t=f3028c7a1dca43a080aeb8239f09cc2f' }, }, ], } ], temperature=0.5, max_tokens=1024, user_id='12345678', ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) def test_completions_vlm_thinking_stream(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: # 生成request_id request_id = time.time() print(f'request_id:{request_id}') response = client.chat.completions.create( request_id=request_id, model='glm-4.1v-thinking-flash', # 填写需要调用的模型名称 messages=[ { 'role': 'user', 'content': [ {'type': 'text', 'text': '图里有什么'}, { 'type': 'image_url', 'image_url': { 'url': 'https://img1.baidu.com/it/u=1369931113,3388870256&fm=253&app=138&size=w931&n=0&f=JPEG&fmt=auto?sec=1703696400&t=f3028c7a1dca43a080aeb8239f09cc2f' }, }, ], } ], temperature=0.5, max_tokens=1024, user_id='12345678', stream=True, ) for item in response: print(item) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/integration_tests/test_web_search.py ================================================ import logging import logging.config import zhipuai from zhipuai import ZhipuAI def test_web_search(logging_conf): logging.config.dictConfig(logging_conf) # type: ignore client = ZhipuAI() # 填写您自己的APIKey try: response = client.web_search.web_search( search_engine='search-std', search_query='2025特朗普向中国加征了多少关税', count=50, search_domain_filter='finance.sina.com.cn', search_recency_filter='oneYear', content_size='high', search_intent=True, ) print(response) except zhipuai.core._errors.APIRequestFailedError as err: print(err) except zhipuai.core._errors.APIInternalError as err: print(err) except zhipuai.core._errors.APIStatusError as err: print(err) ================================================ FILE: tests/unit_tests/batchinput.jsonl ================================================ {"custom_id": "request-1", "method": "POST", "url": "/v4/chat/completions", "body": {"model": "glm-4", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}} ================================================ FILE: tests/unit_tests/maybe/test_maybe_transform.py ================================================ # -*- coding: utf-8 -*- from zhipuai.core import maybe_transform from zhipuai.types import batch_create_params def test_response_joblist_model_cast() -> None: params = maybe_transform( { 'completion_window': '/v1/chat/completions', 'endpoint': None, 'metadata': {'key': 'value'}, }, batch_create_params.BatchCreateParams, ) assert isinstance(params, dict) ================================================ FILE: tests/unit_tests/response_model/__init__.py ================================================ ================================================ FILE: tests/unit_tests/response_model/test_response.py ================================================ # -*- coding: utf-8 -*- from typing import Type import httpx import pytest from zhipuai.core import BaseModel, HttpClient from zhipuai.core._base_type import ResponseT from zhipuai.core._request_opt import FinalRequestOptions from zhipuai.core._response import APIResponse from zhipuai.types.chat.async_chat_completion import ( AsyncCompletion, AsyncTaskStatus, ) from zhipuai.types.chat.chat_completion import ( Completion, ) from zhipuai.types.chat.chat_completion import ( CompletionChoice as ChatCompletionChoice, ) from zhipuai.types.chat.chat_completion import ( CompletionMessageToolCall as ChatCompletionMessageToolCall, ) from zhipuai.types.chat.chat_completion import ( CompletionUsage as ChatCompletionUsage, ) from zhipuai.types.embeddings import Embedding, EmbeddingsResponded from zhipuai.types.files.file_object import FileObject, ListOfFileObject from zhipuai.types.fine_tuning import FineTuningJobEvent from zhipuai.types.fine_tuning.fine_tuning_job import Error, FineTuningJob from zhipuai.types.fine_tuning.fine_tuning_job import ( Hyperparameters as FineTuningHyperparameters, ) from zhipuai.types.fine_tuning.fine_tuning_job_event import JobEvent, Metric from zhipuai.types.fine_tuning.models import FineTunedModelsStatus from zhipuai.types.image import GeneratedImage, ImagesResponded class MockClient: _strict_response_validation: bool = False def _process_response_data( self, *, data: object, cast_type: Type[ResponseT], response: httpx.Response, ) -> ResponseT: pass @pytest.mark.parametrize( 'R', [ AsyncTaskStatus, AsyncCompletion, Completion, ], ) def test_response_chat_model_cast(R: Type[BaseModel]) -> None: MockClient._process_response_data = HttpClient._process_response_data response = httpx.Response( status_code=200, content="""{ "id": "completion123", "request_id": "request456", "model": "model-name", "task_status": "completed", "choices": [ { "index": 0, "finish_reason": "normal", "message": { "content": "This is the completion content.", "role": "assistant", "tool_calls": [ { "id": "toolcall789", "function": { "arguments": "arg1, arg2", "name": "functionName" }, "type": "function_call" } ] } } ], "usage": { "prompt_tokens": 10, "completion_tokens": 15, "total_tokens": 25 } }""", ) opts = FinalRequestOptions.construct(method='get', url='path') http_response = APIResponse( raw=response, cast_type=R, client=MockClient(), stream=False, stream_cls=None, options=opts, ) model = http_response.parse() if R == AsyncTaskStatus: assert R == model.__class__ assert isinstance(model, AsyncTaskStatus) assert model.id == 'completion123' assert model.request_id == 'request456' assert model.model == 'model-name' assert model.task_status == 'completed' elif R == AsyncCompletion: assert R == model.__class__ assert isinstance(model, AsyncCompletion) assert model.id == 'completion123' assert model.request_id == 'request456' assert model.model == 'model-name' assert model.task_status == 'completed' assert isinstance(model.choices, list) assert model.choices[0].index == 0 assert model.choices[0].finish_reason == 'normal' assert ( model.choices[0].message.content == 'This is the completion content.' ) assert model.choices[0].message.role == 'assistant' assert isinstance(model.choices[0].message.tool_calls, list) assert model.choices[0].message.tool_calls[0].id == 'toolcall789' assert ( model.choices[0].message.tool_calls[0].function.arguments == 'arg1, arg2' ) assert ( model.choices[0].message.tool_calls[0].function.name == 'functionName' ) assert model.choices[0].message.tool_calls[0].type == 'function_call' assert model.usage.prompt_tokens == 10 assert model.usage.completion_tokens == 15 assert model.usage.total_tokens == 25 elif R == Completion: assert R == model.__class__ assert isinstance(model, Completion) assert model.id == 'completion123' assert model.request_id == 'request456' assert model.model == 'model-name' assert model.created == None assert isinstance(model.choices, list) assert isinstance(model.choices[0], ChatCompletionChoice) assert model.choices[0].index == 0 assert model.choices[0].finish_reason == 'normal' assert ( model.choices[0].message.content == 'This is the completion content.' ) assert model.choices[0].message.role == 'assistant' assert isinstance(model.choices[0].message.tool_calls, list) assert isinstance( model.choices[0].message.tool_calls[0], ChatCompletionMessageToolCall, ) assert model.choices[0].message.tool_calls[0].id == 'toolcall789' assert ( model.choices[0].message.tool_calls[0].function.arguments == 'arg1, arg2' ) assert ( model.choices[0].message.tool_calls[0].function.name == 'functionName' ) assert model.choices[0].message.tool_calls[0].type == 'function_call' assert isinstance(model.usage, ChatCompletionUsage) assert model.usage.prompt_tokens == 10 assert model.usage.completion_tokens == 15 assert model.usage.total_tokens == 25 else: assert False, f'Unexpected model type: {R}' @pytest.mark.parametrize( 'R', [ FineTunedModelsStatus, ], ) def test_response_finetuned_model_model_cast(R: Type[BaseModel]) -> None: MockClient._process_response_data = HttpClient._process_response_data response = httpx.Response( status_code=200, content="""{ "request_id": "12345", "model_name": "my-fine-tuned-model", "delete_status": "deleted" }""", ) opts = FinalRequestOptions.construct(method='get', url='path') http_response = APIResponse( raw=response, cast_type=R, client=MockClient(), stream=False, stream_cls=None, options=opts, ) model = http_response.parse() assert R == model.__class__ assert isinstance(model, FineTunedModelsStatus) assert model.request_id == '12345' assert model.model_name == 'my-fine-tuned-model' assert model.delete_status == 'deleted' @pytest.mark.parametrize( 'R', [ FineTuningJob, ], ) def test_response_job_model_cast(R: Type[BaseModel]) -> None: MockClient._process_response_data = HttpClient._process_response_data response = httpx.Response( status_code=200, content=""" { "id": "job123", "request_id": "req456", "created_at": 1617181723, "error": { "code": "404", "message": "Not Found", "param": "model_id" }, "fine_tuned_model": "ft_model_1", "finished_at": 1617182000, "hyperparameters": { "n_epochs": 10 }, "model": "base_model", "object": "fine_tuning_job", "result_files": [ "result1.txt", "result2.json" ], "status": "completed", "trained_tokens": 1000000, "training_file": "training_data.csv", "validation_file": "validation_data.csv" }""", ) opts = FinalRequestOptions.construct(method='get', url='path') http_response = APIResponse( raw=response, cast_type=R, client=MockClient(), stream=False, stream_cls=None, options=opts, ) model = http_response.parse() assert R == model.__class__ assert isinstance(model, FineTuningJob) assert model.id == 'job123' assert model.request_id == 'req456' assert model.created_at == 1617181723 assert isinstance(model.error, Error) assert model.error.code == '404' assert model.error.message == 'Not Found' assert model.error.param == 'model_id' assert model.fine_tuned_model == 'ft_model_1' assert model.finished_at == 1617182000 assert isinstance(model.hyperparameters, FineTuningHyperparameters) assert model.hyperparameters.n_epochs == 10 assert model.model == 'base_model' assert model.object == 'fine_tuning_job' assert model.result_files == ['result1.txt', 'result2.json'] assert model.status == 'completed' assert model.trained_tokens == 1000000 assert model.training_file == 'training_data.csv' assert model.validation_file == 'validation_data.csv' @pytest.mark.parametrize( 'R', [ FineTuningJobEvent, ], ) def test_response_joblist_model_cast(R: Type[BaseModel]) -> None: MockClient._process_response_data = HttpClient._process_response_data response = httpx.Response( status_code=200, content="""{ "object": "fine_tuning_job", "data": [ { "object": "job_event", "id": "event123", "type": "training", "created_at": 1617181723, "level": "info", "message": "Training has started.", "data": { "epoch": 1, "current_steps": 100, "total_steps": 1000, "elapsed_time": "00:10:00", "remaining_time": "05:20:00", "trained_tokens": 500000, "loss": 0.05, "eval_loss": 0.03, "acc": 0.9, "eval_acc": 0.95, "learning_rate": 0.001 } } ], "has_more": false }""", ) opts = FinalRequestOptions.construct(method='get', url='path') http_response = APIResponse( raw=response, cast_type=R, client=MockClient(), stream=False, stream_cls=None, options=opts, ) model = http_response.parse() assert R == model.__class__ assert isinstance(model, FineTuningJobEvent) assert isinstance(model.data, list) assert isinstance(model.data[0], JobEvent) assert model.data[0].object == 'job_event' assert model.data[0].id == 'event123' assert model.data[0].type == 'training' assert model.data[0].created_at == 1617181723 assert model.data[0].level == 'info' assert model.data[0].message == 'Training has started.' assert isinstance(model.data[0].data, Metric) assert model.data[0].data.epoch == 1 assert model.data[0].data.current_steps == 100 assert model.data[0].data.total_steps == 1000 assert model.data[0].data.elapsed_time == '00:10:00' assert model.data[0].data.remaining_time == '05:20:00' assert model.data[0].data.trained_tokens == 500000 assert model.data[0].data.loss == 0.05 assert model.data[0].data.eval_loss == 0.03 assert model.data[0].data.acc == 0.9 assert model.data[0].data.eval_acc == 0.95 assert model.data[0].data.learning_rate == 0.001 assert model.has_more == False @pytest.mark.parametrize( 'R', [EmbeddingsResponded], ) def test_response_embedding_model_cast(R: Type[BaseModel]) -> None: MockClient._process_response_data = HttpClient._process_response_data response = httpx.Response( status_code=200, content="""{ "object": "embeddings", "data": [ { "object": "embedding", "index": 1, "embedding": [0.1, 0.2] } ], "model": "some-model-name", "usage": { "prompt_tokens": 20, "completion_tokens": 30, "total_tokens": 50 } }""", ) opts = FinalRequestOptions.construct(method='get', url='path') http_response = APIResponse( raw=response, cast_type=R, client=MockClient(), stream=False, stream_cls=None, options=opts, ) model = http_response.parse() assert R == model.__class__ assert isinstance(model, EmbeddingsResponded) assert isinstance(model.data, list) assert isinstance(model.data[0], Embedding) assert model.data[0].object == 'embedding' assert model.data[0].index == 1 assert model.data[0].embedding == [0.1, 0.2] assert model.object == 'embeddings' assert model.model == 'some-model-name' assert model.usage.prompt_tokens == 20 assert model.usage.completion_tokens == 30 assert model.usage.total_tokens == 50 @pytest.mark.parametrize( 'R', [ FileObject, ], ) def test_response_file_list_model_cast(R: Type[BaseModel]) -> None: MockClient._process_response_data = HttpClient._process_response_data response = httpx.Response( status_code=200, content=""" { "id": "12345", "bytes": 1024, "created_at": 1617181723, "filename": "example.txt", "object": "file", "purpose": "example purpose", "status": "uploaded", "status_details": "File uploaded successfully" }""", ) opts = FinalRequestOptions.construct(method='get', url='path') http_response = APIResponse( raw=response, cast_type=R, client=MockClient(), stream=False, stream_cls=None, options=opts, ) model = http_response.parse() assert R == model.__class__ assert isinstance(model, FileObject) assert model.id == '12345' assert model.bytes == 1024 assert model.created_at == 1617181723 assert model.filename == 'example.txt' assert model.object == 'file' assert model.purpose == 'example purpose' assert model.status == 'uploaded' assert model.status_details == 'File uploaded successfully' @pytest.mark.parametrize( 'R', [ ListOfFileObject, ], ) def test_response_file_list_model_cast(R: Type[BaseModel]) -> None: MockClient._process_response_data = HttpClient._process_response_data response = httpx.Response( status_code=200, content="""{ "object": "list", "data": [ { "id": "12345", "bytes": 1024, "created_at": 1617181723, "filename": "example.txt", "object": "file", "purpose": "example purpose", "status": "uploaded", "status_details": "File uploaded successfully" } ], "has_more": true }""", ) opts = FinalRequestOptions.construct(method='get', url='path') http_response = APIResponse( raw=response, cast_type=R, client=MockClient(), stream=False, stream_cls=None, options=opts, ) model = http_response.parse() assert R == model.__class__ assert isinstance(model.data, list) assert isinstance(model.data[0], FileObject) assert model.data[0].id == '12345' assert model.data[0].bytes == 1024 assert model.data[0].created_at == 1617181723 assert model.data[0].filename == 'example.txt' assert model.data[0].object == 'file' assert model.data[0].purpose == 'example purpose' assert model.data[0].status == 'uploaded' assert model.data[0].status_details == 'File uploaded successfully' assert model.has_more == True @pytest.mark.parametrize('R', [ImagesResponded]) def test_response_image_model_cast(R: Type[BaseModel]) -> None: MockClient._process_response_data = HttpClient._process_response_data response = httpx.Response( status_code=200, content="""{ "created": 1234567890, "data": [ { "b64_json": "base64_encoded_string", "url": "http://example.com/image.png", "revised_prompt": "Revised prompt text" } ] }""", ) opts = FinalRequestOptions.construct(method='get', url='path') http_response = APIResponse( raw=response, cast_type=R, client=MockClient(), stream=False, stream_cls=None, options=opts, ) model = http_response.parse() assert R == model.__class__ assert isinstance(model.data, list) assert isinstance(model.data[0], GeneratedImage) assert model.data[0].b64_json == 'base64_encoded_string' ================================================ FILE: tests/unit_tests/sse_client/__init__.py ================================================ ================================================ FILE: tests/unit_tests/sse_client/test_stream.py ================================================ # -*- coding: utf-8 -*- from typing import Iterable, Type, cast import httpx from zhipuai.core import HttpClient, StreamResponse, get_args from zhipuai.core._base_type import ResponseT from zhipuai.types.chat.chat_completion_chunk import ChatCompletionChunk class MockClient: _strict_response_validation: bool = False def _process_response_data( self, *, data: object, cast_type: Type[ResponseT], response: httpx.Response, ) -> ResponseT: pass def test_stream_cls_chunk() -> None: MockClient._process_response_data = HttpClient._process_response_data def body() -> Iterable[bytes]: yield b'data: {"id":"8635243129834723621","created":1715329207,"model":\ "glm-4","choices":[{"index":0,"delta":{"role":"assistant","content":"1"}}]}\n\n' yield b'data: {"id":"8635243129834723621","created":1715329207,"model":\ "glm-4","choices":[{"index":0,"delta":{"role":"assistant","content":"2"}}]}\n\n' _stream_cls = StreamResponse[ChatCompletionChunk] http_response = httpx.Response(status_code=200, content=body()) stream_cls = _stream_cls( cast_type=cast(type, get_args(_stream_cls)[0]), response=http_response, client=MockClient(), ) chat_completion_chunk1 = next(stream_cls) assert chat_completion_chunk1.choices[0].delta.content == '1' assert chat_completion_chunk1.choices[0].delta.role == 'assistant' assert chat_completion_chunk1.choices[0].index == 0 assert chat_completion_chunk1.model == 'glm-4' chat_completion_chunk2 = next(stream_cls) assert chat_completion_chunk2.choices[0].delta.content == '2' assert chat_completion_chunk2.choices[0].delta.role == 'assistant' assert chat_completion_chunk2.choices[0].index == 0 assert chat_completion_chunk2.model == 'glm-4' ================================================ FILE: tests/unit_tests/test_agents.py ================================================ def test_agents_completion_error_field(): from zhipuai.types.agents.agents_completion import AgentsCompletion, AgentsError, AgentsCompletionChoice, AgentsCompletionMessage, AgentsCompletionUsage # 构造一个 AgentsError error = AgentsError(code="404", message="Not Found") # 构造一个完整的 AgentsCompletion completion = AgentsCompletion( agent_id="test_agent", conversation_id="conv_1", status="failed", choices=[ AgentsCompletionChoice( index=0, finish_reason="error", message=AgentsCompletionMessage(content="error", role="system") ) ], request_id="req_1", id="id_1", usage=AgentsCompletionUsage(prompt_tokens=1, completion_tokens=1, total_tokens=2), error=error ) # 检查 error 字段是否为 AgentsError 实例 assert isinstance(completion.error, AgentsError) assert completion.error.code == "404" assert completion.error.message == "Not Found" # 检查序列化 as_dict = completion.model_dump() assert as_dict["error"]["code"] == "404" assert as_dict["error"]["message"] == "Not Found" print("test_agents_completion_error_field passed.") ================================================ FILE: tests/unit_tests/test_audio.py ================================================ def test_audio_error_field(): from zhipuai.types.audio.audio_speech_chunk import AudioSpeechChunk, AudioError, AudioSpeechChoice, AudioSpeechDelta # 构造一个 AudioError error = AudioError(code="500", message="Internal Error") # 构造一个完整的 AudioSpeechChunk chunk = AudioSpeechChunk( choices=[ AudioSpeechChoice( delta=AudioSpeechDelta(content="audio", role="system"), finish_reason="error", index=0 ) ], request_id="req_2", created=123456, error=error ) # 检查 error 字段是否为 AudioError 实例 assert isinstance(chunk.error, AudioError) assert chunk.error.code == "500" assert chunk.error.message == "Internal Error" # 检查序列化 as_dict = chunk.model_dump() assert as_dict["error"]["code"] == "500" assert as_dict["error"]["message"] == "Internal Error" print("test_audio_error_field passed.") ================================================ FILE: tests/unit_tests/test_jwt.py ================================================ import jwt import pytest from zhipuai.core._jwt_token import generate_token def test_token() -> None: # 生成token token = generate_token('12345678.abcdefg') assert token is not None # 解析token payload = jwt.decode( token, 'abcdefg', algorithms='HS256', options={'verify_signature': False}, ) assert payload is not None assert payload.get('api_key') == '12345678' apikey = 'invalid_api_key' with pytest.raises(Exception): generate_token(apikey) ================================================ FILE: tests/unit_tests/test_request_opt.py ================================================ import pytest from zhipuai.core._request_opt import FinalRequestOptions, NotGiven # Test Initialization and Default Values def test_initialization(): params = FinalRequestOptions.construct( method='GET', url='http://example.com' ) assert isinstance(params.max_retries, NotGiven) assert isinstance(params.timeout, NotGiven) assert isinstance(params.headers, NotGiven) assert params.json_data is None # Test get_max_retries Method @pytest.mark.parametrize( 'max_retries_input, expected', [ (NotGiven(), 5), # Default case (3, 3), # Specific number ], ) def test_get_max_retries(max_retries_input, expected): params = FinalRequestOptions.construct( method='GET', url='http://example.com', max_retries=max_retries_input ) assert params.get_max_retries(5) == expected # Test construct Method def test_construct(): input_data = { 'max_retries': 3, 'timeout': 10.0, 'headers': {'Content-Type': 'application/json'}, } params = FinalRequestOptions.construct(**input_data) assert params.max_retries == input_data['max_retries'] assert params.timeout == input_data['timeout'] assert params.headers == input_data['headers'] ================================================ FILE: tests/unit_tests/test_response.py ================================================ import httpx from httpx import URL, ByteStream, Headers, Request, Response from typing_extensions import Dict, Type from zhipuai.core import StreamResponse from zhipuai.core._base_type import ResponseT from zhipuai.core._http_client import HttpClient from zhipuai.core._request_opt import FinalRequestOptions from zhipuai.core._response import APIResponse # Mock objects for HttpClient and StreamResponse if necessary class MockHttpClient: _strict_response_validation: bool = False # Implement necessary mock methods or attributes def _process_response_data( self, *, data: object, cast_type: Type[ResponseT], response: httpx.Response, ) -> ResponseT: return data class MockStreamResponse(StreamResponse[ResponseT]): # Implement necessary mock methods or attributes def __init__( self, *, cast_type: Type[ResponseT], response: httpx.Response, client: HttpClient, ) -> None: super().__init__(cast_type=cast_type, response=response, client=client) self.response = response self._cast_type = cast_type # self._data_process_func = client._process_response_data # self._strem_chunks = self.__stream__() def __iter__(self): for item in self.response.iter_lines(): yield item # Test Initialization def test_http_response_initialization(): raw_response = Response(200) opts = FinalRequestOptions.construct(method='get', url='path') http_response = APIResponse( raw=raw_response, cast_type=str, client=MockHttpClient(), stream=False, options=opts, ) assert http_response.http_response == raw_response # Test parse Method def test_parse_method(): raw_response = Response( 200, headers=Headers({'content-type': 'application/json'}), content=b'{"key": "value"}', ) opts = FinalRequestOptions.construct(method='get', url='path') http_response = APIResponse( raw=raw_response, cast_type=Dict[str, object], client=MockHttpClient(), stream=False, options=opts, ) parsed_data = http_response.parse() assert parsed_data == {'key': 'value'} http_response = APIResponse( raw=raw_response, cast_type=str, client=MockHttpClient(), stream=False, options=opts, ) parsed_data = http_response.parse() assert parsed_data == '{"key": "value"}' raw_response = Response( 200, content=b'{"key": "value"}', stream=ByteStream(b'{"key": "value"}\n"foo"\n"boo"\n'), ) http_response = APIResponse( raw=raw_response, cast_type=str, client=MockHttpClient(), stream=True, options=opts, stream_cls=MockStreamResponse[str], ) parsed_data = http_response.parse() excepted_data = ['{"key": "value"}', '"foo"', '"boo"'] data = [chunk.strip() for chunk in parsed_data] assert data == excepted_data # Test properties def test_properties(): opts = FinalRequestOptions.construct(method='get', url='path') headers = Headers({'content-type': 'application/json'}) request = Request(method='GET', url='http://example.com') raw_response = Response(200, headers=headers, request=request) http_response = APIResponse( raw=raw_response, cast_type=str, client=MockHttpClient(), stream=False, options=opts, ) assert http_response.headers == headers assert http_response.http_request == request assert http_response.status_code == 200 assert http_response.url == URL('http://example.com') assert http_response.method == 'GET' ================================================ FILE: tests/unit_tests/test_sdk_import.py ================================================ def test_sdk_import_unit(): import zhipuai print(zhipuai.__version__) def test_os_import_unit(): import os print(os) def test_sdk_import(): from zhipuai import ZhipuAI client = ZhipuAI(api_key='empty') # 请填写您自己的APIKey if client is not None: print('SDK导入成功') else: print('SDK导入失败') ================================================ FILE: tests/unit_tests/test_streaming.py ================================================ from typing import Iterator import pytest from zhipuai.core._sse_client import SSELineParser def test_basic() -> None: def body() -> Iterator[str]: yield 'event: completion' yield 'data: {"foo":true}' yield '' it = SSELineParser().iter_lines(body()) sse = next(it) assert sse.event == 'completion' assert sse.json_data() == {'foo': True} with pytest.raises(StopIteration): next(it) def test_data_missing_event() -> None: def body() -> Iterator[str]: yield 'data: {"foo":true}' yield '' it = SSELineParser().iter_lines(body()) sse = next(it) assert sse.event is None assert sse.json_data() == {'foo': True} with pytest.raises(StopIteration): next(it) def test_event_missing_data() -> None: def body() -> Iterator[str]: yield 'event: ping' yield '' it = SSELineParser().iter_lines(body()) sse = next(it) assert sse.event == 'ping' assert sse.data == '' with pytest.raises(StopIteration): next(it) def test_multiple_events() -> None: def body() -> Iterator[str]: yield 'event: ping' yield '' yield 'event: completion' yield '' it = SSELineParser().iter_lines(body()) sse = next(it) assert sse.event == 'ping' assert sse.data == '' sse = next(it) assert sse.event == 'completion' assert sse.data == '' with pytest.raises(StopIteration): next(it) def test_multiple_events_with_data() -> None: def body() -> Iterator[str]: yield 'event: ping' yield 'data: {"foo":true}' yield '' yield 'event: completion' yield 'data: {"bar":false}' yield '' it = SSELineParser().iter_lines(body()) sse = next(it) assert sse.event == 'ping' assert sse.json_data() == {'foo': True} sse = next(it) assert sse.event == 'completion' assert sse.json_data() == {'bar': False} with pytest.raises(StopIteration): next(it) ================================================ FILE: zhipuai/__init__.py ================================================ from ._client import ZhipuAI from .core import ( ZhipuAIError, APIStatusError, APIRequestFailedError, APIAuthenticationError, APIReachLimitError, APIInternalError, APIServerFlowExceedError, APIResponseError, APIResponseValidationError, APIConnectionError, APITimeoutError, ) from .__version__ import __version__ ================================================ FILE: zhipuai/__version__.py ================================================ __version__ = 'v2.1.5.20250725' ================================================ FILE: zhipuai/_client.py ================================================ from __future__ import annotations from typing import Union, Mapping from typing_extensions import override from .core import _jwt_token from .core import ZhipuAIError from .core import HttpClient, ZHIPUAI_DEFAULT_MAX_RETRIES from .core import NotGiven, NOT_GIVEN from . import api_resource import os import httpx from httpx import Timeout class ZhipuAI(HttpClient): chat: api_resource.chat.Chat api_key: str _disable_token_cache: bool = True source_channel: str def __init__( self, *, api_key: str | None = None, base_url: str | httpx.URL | None = None, timeout: Union[float, Timeout, None, NotGiven] = NOT_GIVEN, max_retries: int = ZHIPUAI_DEFAULT_MAX_RETRIES, http_client: httpx.Client | None = None, custom_headers: Mapping[str, str] | None = None, disable_token_cache: bool = True, _strict_response_validation: bool = False, source_channel: str | None = None ) -> None: if api_key is None: api_key = os.environ.get("ZHIPUAI_API_KEY") if api_key is None: raise ZhipuAIError("未提供api_key，请通过参数或环境变量提供") self.api_key = api_key self.source_channel = source_channel self._disable_token_cache = disable_token_cache if base_url is None: base_url = os.environ.get("ZHIPUAI_BASE_URL") if base_url is None: base_url = f"https://open.bigmodel.cn/api/paas/v4" from .__version__ import __version__ super().__init__( version=__version__, base_url=base_url, max_retries=max_retries, timeout=timeout, custom_httpx_client=http_client, custom_headers=custom_headers, _strict_response_validation=_strict_response_validation, ) self.chat = api_resource.chat.Chat(self) self.images = api_resource.images.Images(self) self.embeddings = api_resource.embeddings.Embeddings(self) self.files = api_resource.files.Files(self) self.fine_tuning = api_resource.fine_tuning.FineTuning(self) self.batches = api_resource.Batches(self) self.knowledge = api_resource.Knowledge(self) self.tools = api_resource.Tools(self) self.videos = api_resource.Videos(self) self.assistant = api_resource.Assistant(self) self.web_search = api_resource.WebSearchApi(self) self.audio = api_resource.audio.Audio(self) self.moderations = api_resource.moderation.Moderations(self) self.agents = api_resource.agents.Agents(self) self.file_parser = api_resource.file_parser.FileParser(self) @property @override def auth_headers(self) -> dict[str, str]: api_key = self.api_key source_channel = self.source_channel or "python-sdk" if self._disable_token_cache: return {"Authorization": f"Bearer {api_key}","x-source-channel": source_channel} else: return {"Authorization": f"Bearer {_jwt_token.generate_token(api_key)}","x-source-channel": source_channel} def __del__(self) -> None: if (not hasattr(self, "_has_custom_http_client") or not hasattr(self, "close") or not hasattr(self, "_client")): # if the '__init__' method raised an error, self would not have client attr return if self._has_custom_http_client: return self.close() ================================================ FILE: zhipuai/api_resource/__init__.py ================================================ from .chat import ( AsyncCompletions, Chat, Completions, ) from .images import ( Images ) from .embeddings import ( Embeddings ) from .files import ( Files, FilesWithRawResponse ) from .fine_tuning import ( FineTuning ) from .batches import ( Batches ) from .knowledge import ( Knowledge ) from .tools import ( Tools ) from .videos import ( Videos, ) from .assistant import ( Assistant, ) from .audio import ( Audio ) from .moderation import ( Moderations ) from .web_search import ( WebSearchApi ) from .agents import ( Agents ) from .audio import ( Audio ) from .file_parser import ( FileParser ) __all__ = [ 'Videos', 'AsyncCompletions', 'Chat', 'Completions', 'Images', 'Embeddings', 'Files', 'FilesWithRawResponse', 'FineTuning', 'Batches', 'Knowledge', 'Tools', 'Assistant', 'Audio', 'Moderation', 'FileParser' ] ================================================ FILE: zhipuai/api_resource/agents/__init__.py ================================================ from zhipuai.api_resource.agents.agents import Agents __all__= [ "Agents" ] ================================================ FILE: zhipuai/api_resource/agents/agents.py ================================================ from __future__ import annotations from typing import Union, List, Optional, TYPE_CHECKING, Dict import httpx import logging from typing_extensions import Literal from ...core import BaseAPI, deepcopy_minimal from ...core import NotGiven, NOT_GIVEN, Headers, Query, Body from ...core import make_request_options from ...core import StreamResponse from ...types.agents.agents_completion import AgentsCompletion from ...types.agents.agents_completion_chunk import AgentsCompletionChunk from ...types.sensitive_word_check import SensitiveWordCheckRequest logger = logging.getLogger(__name__) if TYPE_CHECKING: from ..._client import ZhipuAI class Agents(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def invoke( self, agent_id: Optional[str] | NotGiven = NOT_GIVEN, request_id: Optional[str] | NotGiven = NOT_GIVEN, stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN, messages: Union[str, List[str], List[int], object, None] | NotGiven = NOT_GIVEN, user_id: Optional[str] | NotGiven = NOT_GIVEN, custom_variables: object = NOT_GIVEN, sensitive_word_check: Optional[SensitiveWordCheckRequest] | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> AgentsCompletion | StreamResponse[AgentsCompletionChunk]: body = deepcopy_minimal({ "agent_id": agent_id, "request_id": request_id, "user_id": user_id, "messages": messages, "sensitive_word_check": sensitive_word_check, "stream": stream, "custom_variables": custom_variables }) return self._post( "/v1/agents", body=body, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=AgentsCompletion, stream=stream or False, stream_cls=StreamResponse[AgentsCompletionChunk], ) def async_result( self, agent_id: Optional[str] | NotGiven = NOT_GIVEN, async_id: Optional[str] | NotGiven = NOT_GIVEN, conversation_id: Optional[str] | NotGiven = NOT_GIVEN, custom_variables: object = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> AgentsCompletion: body = deepcopy_minimal({ "agent_id": agent_id, "async_id": async_id, "conversation_id": conversation_id, "custom_variables": custom_variables }) return self._post( "/v1/agents/async-result", body=body, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=AgentsCompletion, ) ================================================ FILE: zhipuai/api_resource/assistant/__init__.py ================================================ from zhipuai.api_resource.assistant.assistant import Assistant __all__= [ "Assistant" ] ================================================ FILE: zhipuai/api_resource/assistant/assistant.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING, List, Mapping, cast, Optional, Dict from typing_extensions import Literal from ...types.assistant import AssistantCompletion from ...types.assistant.assistant_conversation_resp import ConversationUsageList, ConversationUsageListResp from ...types.assistant.assistant_support_resp import AssistantSupportResp from ...core import BaseAPI, maybe_transform, StreamResponse from ...core import NOT_GIVEN, Body, Headers, NotGiven import httpx from ...core import ( make_request_options, ) from ...core import deepcopy_minimal, extract_files if TYPE_CHECKING: from ..._client import ZhipuAI from ...types.assistant import assistant_create_params from ...types.assistant import assistant_conversation_params __all__ = ["Assistant"] class Assistant(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def conversation( self, assistant_id: str, messages: List[assistant_create_params.ConversationMessage], model: str = None, *, stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN, conversation_id: Optional[str] = None, attachments: Optional[List[assistant_create_params.AssistantAttachments]] = None, metadata: dict | None = None, request_id: str = None, user_id: str = None, extra_parameters: Optional[assistant_create_params.ExtraParameters] = None, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> AssistantCompletion | StreamResponse[AssistantCompletion]: body = deepcopy_minimal( { "assistant_id": assistant_id, "messages": messages, "stream": stream, "conversation_id": conversation_id, "attachments": attachments, "metadata": metadata, "request_id": request_id, "user_id": user_id, "extra_parameters": extra_parameters } ) return self._post( "/assistant", body=maybe_transform(body, assistant_create_params.AssistantParameters), options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=AssistantCompletion, stream=stream or False, stream_cls=StreamResponse[AssistantCompletion], ) def query_support( self, *, assistant_id_list: List[str] = None, request_id: str = None, user_id: str = None, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> AssistantSupportResp: body = deepcopy_minimal( { "assistant_id_list": assistant_id_list, "request_id": request_id, "user_id": user_id, } ) return self._post( "/assistant/list", body=body, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=AssistantSupportResp, ) def query_conversation_usage( self, assistant_id: str, page: int = 1, page_size: int = 10, *, request_id: str = None, user_id: str = None, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> ConversationUsageListResp: body = deepcopy_minimal( { "assistant_id": assistant_id, "page": page, "page_size": page_size, "request_id": request_id, "user_id": user_id, } ) return self._post( "/assistant/conversation/list", body=maybe_transform(body, assistant_conversation_params.ConversationParameters), options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=ConversationUsageListResp, ) ================================================ FILE: zhipuai/api_resource/audio/__init__.py ================================================ from .audio import ( Audio ) from .transcriptions import ( Transcriptions ) __all__ = [ 'Audio', 'Transcriptions' ] ================================================ FILE: zhipuai/api_resource/audio/audio.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING, List, Mapping, cast, Optional, Dict from .transcriptions import Transcriptions from zhipuai.core._utils import extract_files from zhipuai.types.sensitive_word_check import SensitiveWordCheckRequest from zhipuai.types.audio import AudioSpeechParams from ...types.audio import audio_customization_param from zhipuai.core import BaseAPI, maybe_transform, StreamResponse from zhipuai.core import NOT_GIVEN, Body, Headers, NotGiven, FileTypes from zhipuai.core import _legacy_response import httpx from ...core import BaseAPI, cached_property from zhipuai.core import ( make_request_options, ) from zhipuai.core import deepcopy_minimal from ...types.audio.audio_speech_chunk import AudioSpeechChunk if TYPE_CHECKING: from zhipuai._client import ZhipuAI __all__ = ["Audio"] class Audio(BaseAPI): @cached_property def transcriptions(self) -> Transcriptions: return Transcriptions(self._client) def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def speech( self, *, model: str, input: str = None, voice: str = None, response_format: str = None, sensitive_word_check: Optional[SensitiveWordCheckRequest] | NotGiven = NOT_GIVEN, request_id: str = None, user_id: str = None, stream: bool = False, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, encode_format: str, ) -> _legacy_response.HttpxBinaryResponseContent | StreamResponse[AudioSpeechChunk]: body = deepcopy_minimal( { "model": model, "input": input, "voice": voice, "stream": stream, "response_format": response_format, "sensitive_word_check": sensitive_word_check, "request_id": request_id, "user_id": user_id, "encode_format": encode_format } ) return self._post( "/audio/speech", body=body, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=_legacy_response.HttpxBinaryResponseContent, stream= stream or False, stream_cls=StreamResponse[AudioSpeechChunk] ) def customization( self, *, model: str, input: str = None, voice_text: str = None, voice_data: FileTypes = None, response_format: str = None, sensitive_word_check: Optional[SensitiveWordCheckRequest] | NotGiven = NOT_GIVEN, request_id: str = None, user_id: str = None, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> _legacy_response.HttpxBinaryResponseContent: body = deepcopy_minimal( { "model": model, "input": input, "voice_text": voice_text, "voice_data": voice_data, "response_format": response_format, "sensitive_word_check": sensitive_word_check, "request_id": request_id, "user_id": user_id } ) files = extract_files(cast(Mapping[str, object], body), paths=[["voice_data"]]) if files: extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})} return self._post( "/audio/customization", body=maybe_transform(body, audio_customization_param.AudioCustomizationParam), files=files, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=_legacy_response.HttpxBinaryResponseContent ) ================================================ FILE: zhipuai/api_resource/audio/transcriptions.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING, List, Mapping, cast, Optional, Dict from ...types.audio import transcriptions_create_param import httpx import logging from typing_extensions import Literal from ...core import BaseAPI, deepcopy_minimal, maybe_transform, drop_prefix_image_data from ...core import make_request_options from ...core import StreamResponse from ...types.chat.chat_completion import Completion from ...types.chat.chat_completion_chunk import ChatCompletionChunk from ...types.sensitive_word_check import SensitiveWordCheckRequest from ...core import NOT_GIVEN, Body, Headers, NotGiven, FileTypes from zhipuai.core._utils import extract_files logger = logging.getLogger(__name__) if TYPE_CHECKING: from ..._client import ZhipuAI __all__ = ["Transcriptions"] class Transcriptions(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def create( self, *, file: FileTypes, model: str, request_id: Optional[str] | NotGiven = NOT_GIVEN, user_id: Optional[str] | NotGiven = NOT_GIVEN, stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, sensitive_word_check: Optional[SensitiveWordCheckRequest] | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN ) -> Completion | StreamResponse[ChatCompletionChunk]: if temperature is not None and temperature != NOT_GIVEN: if temperature <= 0: temperature = 0.01 if temperature >= 1: temperature = 0.99 body = deepcopy_minimal({ "model": model, "file": file, "request_id": request_id, "user_id": user_id, "temperature": temperature, "sensitive_word_check": sensitive_word_check, "stream": stream }) files = extract_files(cast(Mapping[str, object], body), paths=[["file"]]) if files: extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})} return self._post( "/audio/transcriptions", body=maybe_transform(body, transcriptions_create_param.TranscriptionsParam), files=files, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=Completion, stream=stream or False, stream_cls=StreamResponse[ChatCompletionChunk], ) ================================================ FILE: zhipuai/api_resource/batches.py ================================================ from __future__ import annotations import httpx from typing import TYPE_CHECKING, Literal, Optional, Dict from ..core import BaseAPI, NotGiven, NOT_GIVEN, Headers, Body, maybe_transform, make_request_options from ..core.pagination import SyncCursorPage from ..types import batch_create_params, batch_list_params from ..types.batch import Batch if TYPE_CHECKING: from .._client import ZhipuAI class Batches(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def create( self, *, completion_window: str | None = None, endpoint: Literal["/v1/chat/completions", "/v1/embeddings"], input_file_id: str, metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN, auto_delete_input_file: bool = True, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> Batch: return self._post( "/batches", body=maybe_transform( { "completion_window": completion_window, "endpoint": endpoint, "input_file_id": input_file_id, "metadata": metadata, "auto_delete_input_file":auto_delete_input_file }, batch_create_params.BatchCreateParams, ), options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=Batch, ) def retrieve( self, batch_id: str, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> Batch: """ Retrieves a batch. Args: extra_headers: Send extra headers extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ if not batch_id: raise ValueError(f"Expected a non-empty value for `batch_id` but received {batch_id!r}") return self._get( f"/batches/{batch_id}", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=Batch, ) def list( self, *, after: str | NotGiven = NOT_GIVEN, limit: int | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> SyncCursorPage[Batch]: """List your organization's batches. Args: after: A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list. limit: A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20. extra_headers: Send extra headers extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ return self._get_api_list( "/batches", page=SyncCursorPage[Batch], options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout, query=maybe_transform( { "after": after, "limit": limit, }, batch_list_params.BatchListParams, ), ), model=Batch, ) def cancel( self, batch_id: str, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> Batch: """ Cancels an in-progress batch. Args: batch_id: The ID of the batch to cancel. extra_headers: Send extra headers extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ if not batch_id: raise ValueError(f"Expected a non-empty value for `batch_id` but received {batch_id!r}") return self._post( f"/batches/{batch_id}/cancel", options=make_request_options( extra_headers=extra_headers,extra_body=extra_body, timeout=timeout ), cast_type=Batch, ) ================================================ FILE: zhipuai/api_resource/chat/__init__.py ================================================ from .async_completions import ( AsyncCompletions ) from .chat import ( Chat ) from .completions import ( Completions ) __all__ = [ 'AsyncCompletions' 'Chat' 'Completions' ] ================================================ FILE: zhipuai/api_resource/chat/async_completions.py ================================================ from __future__ import annotations from typing import Union, List, Optional, TYPE_CHECKING, Dict import httpx import logging from typing_extensions import Literal from ...core import BaseAPI, maybe_transform, drop_prefix_image_data from ...core import NotGiven, NOT_GIVEN, Headers, Body from ...core import make_request_options from ...types.chat.async_chat_completion import AsyncTaskStatus, AsyncCompletion from ...types.chat.code_geex import code_geex_params from ...types.sensitive_word_check import SensitiveWordCheckRequest logger = logging.getLogger(__name__) if TYPE_CHECKING: from ..._client import ZhipuAI class AsyncCompletions(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def create( self, *, model: str, request_id: Optional[str] | NotGiven = NOT_GIVEN, user_id: Optional[str] | NotGiven = NOT_GIVEN, do_sample: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, top_p: Optional[float] | NotGiven = NOT_GIVEN, max_tokens: int | NotGiven = NOT_GIVEN, seed: int | NotGiven = NOT_GIVEN, messages: Union[str, List[str], List[int], List[List[int]], None], stop: Optional[Union[str, List[str], None]] | NotGiven = NOT_GIVEN, sensitive_word_check: Optional[SensitiveWordCheckRequest] | NotGiven = NOT_GIVEN, tools: Optional[object] | NotGiven = NOT_GIVEN, tool_choice: str | NotGiven = NOT_GIVEN, meta: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN, extra: Optional[code_geex_params.CodeGeexExtra] | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, response_format: object | None = None, thinking: object | None = None, ) -> AsyncTaskStatus: _cast_type = AsyncTaskStatus logger.debug(f"temperature:{temperature}, top_p:{top_p}") if temperature is not None and temperature != NOT_GIVEN: if temperature <= 0: do_sample = False temperature = 0.01 # logger.warning("temperature:取值范围是：(0.0, 1.0) 开区间，do_sample重写为:false（参数top_p temperture不生效）") if temperature >= 1: temperature = 0.99 # logger.warning("temperature:取值范围是：(0.0, 1.0) 开区间") if top_p is not None and top_p != NOT_GIVEN: if top_p >= 1: top_p = 0.99 # logger.warning("top_p:取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1") if top_p <= 0: top_p = 0.01 # logger.warning("top_p:取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1") logger.debug(f"temperature:{temperature}, top_p:{top_p}") if isinstance(messages, List): for item in messages: if item.get('content'): item['content'] = drop_prefix_image_data(item['content']) body = { "model": model, "request_id": request_id, "user_id": user_id, "temperature": temperature, "top_p": top_p, "do_sample": do_sample, "max_tokens": max_tokens, "seed": seed, "messages": messages, "stop": stop, "sensitive_word_check": sensitive_word_check, "tools": tools, "tool_choice": tool_choice, "meta": meta, "extra": maybe_transform(extra, code_geex_params.CodeGeexExtra), "response_format": response_format, "thinking": thinking } return self._post( "/async/chat/completions", body=body, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=_cast_type, stream=False, ) def retrieve_completion_result( self, id: str, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> Union[AsyncCompletion, AsyncTaskStatus]: _cast_type = Union[AsyncCompletion, AsyncTaskStatus] return self._get( path=f"/async-result/{id}", cast_type=_cast_type, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), ) ================================================ FILE: zhipuai/api_resource/chat/chat.py ================================================ from typing import TYPE_CHECKING from .completions import Completions from .async_completions import AsyncCompletions from ...core import BaseAPI, cached_property if TYPE_CHECKING: from ..._client import ZhipuAI class Chat(BaseAPI): @cached_property def completions(self) -> Completions: return Completions(self._client) @cached_property def asyncCompletions(self) -> AsyncCompletions: return AsyncCompletions(self._client) ================================================ FILE: zhipuai/api_resource/chat/completions.py ================================================ from __future__ import annotations from typing import Union, List, Optional, TYPE_CHECKING, Dict import httpx import logging from typing_extensions import Literal from ...core import BaseAPI, deepcopy_minimal, maybe_transform, drop_prefix_image_data from ...core import NotGiven, NOT_GIVEN, Headers, Query, Body from ...core import make_request_options from ...core import StreamResponse from ...types.chat.chat_completion import Completion from ...types.chat.chat_completion_chunk import ChatCompletionChunk from ...types.chat.code_geex import code_geex_params from ...types.sensitive_word_check import SensitiveWordCheckRequest logger = logging.getLogger(__name__) if TYPE_CHECKING: from ..._client import ZhipuAI class Completions(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def create( self, *, model: str, request_id: Optional[str] | NotGiven = NOT_GIVEN, user_id: Optional[str] | NotGiven = NOT_GIVEN, do_sample: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN, stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, top_p: Optional[float] | NotGiven = NOT_GIVEN, max_tokens: int | NotGiven = NOT_GIVEN, seed: int | NotGiven = NOT_GIVEN, messages: Union[str, List[str], List[int], object, None], stop: Optional[Union[str, List[str], None]] | NotGiven = NOT_GIVEN, sensitive_word_check: Optional[SensitiveWordCheckRequest] | NotGiven = NOT_GIVEN, tools: Optional[object] | NotGiven = NOT_GIVEN, tool_choice: str | NotGiven = NOT_GIVEN, meta: Optional[Dict[str,str]] | NotGiven = NOT_GIVEN, extra: Optional[code_geex_params.CodeGeexExtra] | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, response_format : object | None = None, thinking : object | None = None, ) -> Completion | StreamResponse[ChatCompletionChunk]: logger.debug(f"temperature:{temperature}, top_p:{top_p}") if temperature is not None and temperature != NOT_GIVEN: if temperature <= 0: do_sample = False temperature = 0.01 # logger.warning("temperature:取值范围是：(0.0, 1.0) 开区间，do_sample重写为:false（参数top_p temperture不生效）") if temperature >= 1: temperature = 0.99 # logger.warning("temperature:取值范围是：(0.0, 1.0) 开区间") if top_p is not None and top_p != NOT_GIVEN: if top_p >= 1: top_p = 0.99 # logger.warning("top_p:取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1") if top_p <= 0: top_p = 0.01 # logger.warning("top_p:取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1") logger.debug(f"temperature:{temperature}, top_p:{top_p}") if isinstance(messages, List): for item in messages: if item.get('content'): item['content'] = drop_prefix_image_data(item['content']) body = deepcopy_minimal({ "model": model, "request_id": request_id, "user_id": user_id, "temperature": temperature, "top_p": top_p, "do_sample": do_sample, "max_tokens": max_tokens, "seed": seed, "messages": messages, "stop": stop, "sensitive_word_check": sensitive_word_check, "stream": stream, "tools": tools, "tool_choice": tool_choice, "meta": meta, "extra": maybe_transform(extra, code_geex_params.CodeGeexExtra), "response_format": response_format, "thinking": thinking }) return self._post( "/chat/completions", body=body, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=Completion, stream=stream or False, stream_cls=StreamResponse[ChatCompletionChunk], ) ================================================ FILE: zhipuai/api_resource/embeddings.py ================================================ from __future__ import annotations from typing import Union, List, Optional, TYPE_CHECKING import httpx from ..core import BaseAPI, Body from ..core import NotGiven, NOT_GIVEN, Headers from ..core import make_request_options from ..types.embeddings import EmbeddingsResponded if TYPE_CHECKING: from .._client import ZhipuAI class Embeddings(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def create( self, *, input: Union[str, List[str], List[int], List[List[int]]], model: Union[str], dimensions: Union[int]| NotGiven = NOT_GIVEN, encoding_format: str | NotGiven = NOT_GIVEN, user: str | NotGiven = NOT_GIVEN, request_id: Optional[str] | NotGiven = NOT_GIVEN, sensitive_word_check: Optional[object] | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, disable_strict_validation: Optional[bool] | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> EmbeddingsResponded: _cast_type = EmbeddingsResponded if disable_strict_validation: _cast_type = object return self._post( "/embeddings", body={ "input": input, "model": model, "dimensions": dimensions, "encoding_format": encoding_format, "user": user, "request_id": request_id, "sensitive_word_check": sensitive_word_check, }, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=_cast_type, stream=False, ) ================================================ FILE: zhipuai/api_resource/file_parser/__init__.py ================================================ from .file_parser import FileParser __all__ = ['FileParser'] ================================================ FILE: zhipuai/api_resource/file_parser/file_parser.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING, Mapping, cast import httpx from typing_extensions import Literal from ...core import BaseAPI, maybe_transform from ...core import NOT_GIVEN, Body, Headers, NotGiven, FileTypes from ...core import _legacy_binary_response from ...core import _legacy_response from ...core import deepcopy_minimal, extract_files from ...core import ( make_request_options, ) from ...types.file_parser.file_parser_create_params import FileParserCreateParams from ...types.file_parser.file_parser_resp import FileParserTaskCreateResp if TYPE_CHECKING: from ..._client import ZhipuAI __all__ = ["FileParser"] class FileParser(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def create( self, *, file: FileTypes = None, file_type: str = None, tool_type: Literal["simple", "doc2x", "tencent", "zhipu-pro"], extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> FileParserTaskCreateResp: if not file: raise ValueError("At least one `file` must be provided.") body = deepcopy_minimal( { "file": file, "file_type": file_type, "tool_type": tool_type, } ) files = extract_files(cast(Mapping[str, object], body), paths=[["file"]]) if files: # It should be noted that the actual Content-Type header that will be # sent to the server will contain a `boundary` parameter, e.g. # multipart/form-data; boundary=---abc-- extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})} return self._post( "/files/parser/create", body=maybe_transform(body, FileParserCreateParams), files=files, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=FileParserTaskCreateResp, ) def content( self, task_id: str, *, format_type: Literal["text", "download_link"], extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> _legacy_response.HttpxBinaryResponseContent: """ Returns the contents of the specified file. Args: extra_headers: Send extra headers extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ if not task_id: raise ValueError(f"Expected a non-empty value for `task_id` but received {task_id!r}") extra_headers = {"Accept": "application/binary", **(extra_headers or {})} return self._get( f"/files/parser/result/{task_id}/{format_type}", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=_legacy_binary_response.HttpxBinaryResponseContent, ) ================================================ FILE: zhipuai/api_resource/files.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING, List, Mapping, cast from typing_extensions import Literal from ..core import BaseAPI, maybe_transform from ..core import NOT_GIVEN, Body, Headers, NotGiven, FileTypes import httpx from ..core import ( make_request_options, ) from ..core import deepcopy_minimal, extract_files from ..types.files import FileObject, ListOfFileObject, file_create_params, FileDeleted from ..types.files import UploadDetail from ..core import _legacy_binary_response from ..core import _legacy_response if TYPE_CHECKING: from .._client import ZhipuAI __all__ = ["Files", "FilesWithRawResponse"] class Files(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def create( self, *, file: FileTypes = None, upload_detail: List[UploadDetail] = None, purpose: Literal["fine-tune", "retrieval", "batch"], knowledge_id: str = None, sentence_size: int = None, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> FileObject: if not file and not upload_detail: raise ValueError("At least one of `file` and `upload_detail` must be provided.") body = deepcopy_minimal( { "file": file, "upload_detail": upload_detail, "purpose": purpose, "knowledge_id": knowledge_id, "sentence_size": sentence_size, } ) files = extract_files(cast(Mapping[str, object], body), paths=[["file"]]) if files: # It should be noted that the actual Content-Type header that will be # sent to the server will contain a `boundary` parameter, e.g. # multipart/form-data; boundary=---abc-- extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})} return self._post( "/files", body=maybe_transform(body, file_create_params.FileCreateParams), files=files, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=FileObject, ) # def retrieve( # self, # file_id: str, # *, # extra_headers: Headers | None = None, # extra_body: Body | None = None, # timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, # ) -> FileObject: # """ # Returns information about a specific file. # # Args: # file_id: The ID of the file to retrieve information about # extra_headers: Send extra headers # # extra_body: Add additional JSON properties to the request # # timeout: Override the client-level default timeout for this request, in seconds # """ # if not file_id: # raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}") # return self._get( # f"/files/{file_id}", # options=make_request_options( # extra_headers=extra_headers, extra_body=extra_body, timeout=timeout # ), # cast_type=FileObject, # ) def list( self, *, purpose: str | NotGiven = NOT_GIVEN, limit: int | NotGiven = NOT_GIVEN, after: str | NotGiven = NOT_GIVEN, order: str | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> ListOfFileObject: return self._get( "/files", cast_type=ListOfFileObject, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout, query={ "purpose": purpose, "limit": limit, "after": after, "order": order, }, ), ) def delete( self, file_id: str, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> FileDeleted: """ Delete a file. Args: file_id: The ID of the file to delete extra_headers: Send extra headers extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ if not file_id: raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}") return self._delete( f"/files/{file_id}", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=FileDeleted, ) def content( self, file_id: str, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> _legacy_response.HttpxBinaryResponseContent: """ Returns the contents of the specified file. Args: extra_headers: Send extra headers extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ if not file_id: raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}") extra_headers = {"Accept": "application/binary", **(extra_headers or {})} return self._get( f"/files/{file_id}/content", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=_legacy_binary_response.HttpxBinaryResponseContent, ) class FilesWithRawResponse: def __init__(self, files: Files) -> None: self._files = files self.create = _legacy_response.to_raw_response_wrapper( files.create, ) self.list = _legacy_response.to_raw_response_wrapper( files.list, ) self.content = _legacy_response.to_raw_response_wrapper( files.content, ) ================================================ FILE: zhipuai/api_resource/fine_tuning/__init__.py ================================================ from .jobs import ( Jobs ) from .models import ( FineTunedModels ) from .fine_tuning import ( FineTuning ) __all__ = [ 'Jobs', 'FineTunedModels', 'FineTuning' ] ================================================ FILE: zhipuai/api_resource/fine_tuning/fine_tuning.py ================================================ from typing import TYPE_CHECKING from .jobs import Jobs from .models import FineTunedModels from ...core import BaseAPI, cached_property if TYPE_CHECKING: from ..._client import ZhipuAI class FineTuning(BaseAPI): @cached_property def jobs(self) -> Jobs: return Jobs(self._client) @cached_property def models(self) -> FineTunedModels: return FineTunedModels(self._client) ================================================ FILE: zhipuai/api_resource/fine_tuning/jobs/__init__.py ================================================ from .jobs import Jobs __all__ = [ "Jobs" ] ================================================ FILE: zhipuai/api_resource/fine_tuning/jobs/jobs.py ================================================ from __future__ import annotations from typing import Optional, TYPE_CHECKING import httpx from ....core import BaseAPI from ....core import NOT_GIVEN, Headers, NotGiven, Body from ....core import ( make_request_options, ) from ....types.fine_tuning import ( FineTuningJob, job_create_params, ListOfFineTuningJob, FineTuningJobEvent, ) if TYPE_CHECKING: from ...._client import ZhipuAI __all__ = ["Jobs"] class Jobs(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def create( self, *, model: str, training_file: str, hyperparameters: job_create_params.Hyperparameters | NotGiven = NOT_GIVEN, suffix: Optional[str] | NotGiven = NOT_GIVEN, request_id: Optional[str] | NotGiven = NOT_GIVEN, validation_file: Optional[str] | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> FineTuningJob: return self._post( "/fine_tuning/jobs", body={ "model": model, "training_file": training_file, "hyperparameters": hyperparameters, "suffix": suffix, "validation_file": validation_file, "request_id": request_id, }, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=FineTuningJob, ) def retrieve( self, fine_tuning_job_id: str, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> FineTuningJob: return self._get( f"/fine_tuning/jobs/{fine_tuning_job_id}", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=FineTuningJob, ) def list( self, *, after: str | NotGiven = NOT_GIVEN, limit: int | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> ListOfFineTuningJob: return self._get( "/fine_tuning/jobs", cast_type=ListOfFineTuningJob, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout, query={ "after": after, "limit": limit, }, ), ) def cancel( self, fine_tuning_job_id: str, *, # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. # The extra values given here take precedence over values defined on the client or passed to this method. extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> FineTuningJob: if not fine_tuning_job_id: raise ValueError(f"Expected a non-empty value for `fine_tuning_job_id` but received {fine_tuning_job_id!r}") return self._post( f"/fine_tuning/jobs/{fine_tuning_job_id}/cancel", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=FineTuningJob, ) def list_events( self, fine_tuning_job_id: str, *, after: str | NotGiven = NOT_GIVEN, limit: int | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> FineTuningJobEvent: return self._get( f"/fine_tuning/jobs/{fine_tuning_job_id}/events", cast_type=FineTuningJobEvent, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout, query={ "after": after, "limit": limit, }, ), ) def delete( self, fine_tuning_job_id: str, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> FineTuningJob: if not fine_tuning_job_id: raise ValueError(f"Expected a non-empty value for `fine_tuning_job_id` but received {fine_tuning_job_id!r}") return self._delete( f"/fine_tuning/jobs/{fine_tuning_job_id}", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=FineTuningJob, ) ================================================ FILE: zhipuai/api_resource/fine_tuning/models/__init__.py ================================================ from .fine_tuned_models import FineTunedModels __all__ = ['FineTunedModels'] ================================================ FILE: zhipuai/api_resource/fine_tuning/models/fine_tuned_models.py ================================================ from __future__ import annotations from typing import Optional, TYPE_CHECKING import httpx from ....core import BaseAPI from ....core import NOT_GIVEN, Headers, NotGiven, Body from ....core import ( make_request_options, ) from ....types.fine_tuning.models import ( FineTunedModelsStatus ) if TYPE_CHECKING: from ...._client import ZhipuAI __all__ = ["FineTunedModels"] class FineTunedModels(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def delete( self, fine_tuned_model: str, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> FineTunedModelsStatus: if not fine_tuned_model: raise ValueError(f"Expected a non-empty value for `fine_tuned_model` but received {fine_tuned_model!r}") return self._delete( f"fine_tuning/fine_tuned_models/{fine_tuned_model}", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=FineTunedModelsStatus, ) ================================================ FILE: zhipuai/api_resource/images.py ================================================ from __future__ import annotations from typing import Union, List, Optional, TYPE_CHECKING import httpx from ..core import BaseAPI from ..core import NotGiven, NOT_GIVEN, Headers, Body from ..core import make_request_options from ..types.image import ImagesResponded from ..types.sensitive_word_check import SensitiveWordCheckRequest if TYPE_CHECKING: from .._client import ZhipuAI class Images(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def generations( self, *, prompt: str, model: str | NotGiven = NOT_GIVEN, n: Optional[int] | NotGiven = NOT_GIVEN, quality: Optional[str] | NotGiven = NOT_GIVEN, response_format: Optional[str] | NotGiven = NOT_GIVEN, size: Optional[str] | NotGiven = NOT_GIVEN, style: Optional[str] | NotGiven = NOT_GIVEN, sensitive_word_check: Optional[SensitiveWordCheckRequest] | NotGiven = NOT_GIVEN, user: str | NotGiven = NOT_GIVEN, request_id: Optional[str] | NotGiven = NOT_GIVEN, user_id: Optional[str] | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, disable_strict_validation: Optional[bool] | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> ImagesResponded: _cast_type = ImagesResponded if disable_strict_validation: _cast_type = object return self._post( "/images/generations", body={ "prompt": prompt, "model": model, "n": n, "quality": quality, "response_format": response_format, "sensitive_word_check": sensitive_word_check, "size": size, "style": style, "user": user, "user_id": user_id, "request_id": request_id, }, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=_cast_type, stream=False, ) ================================================ FILE: zhipuai/api_resource/knowledge/__init__.py ================================================ from .knowledge import Knowledge __all__ = ['Knowledge'] ================================================ FILE: zhipuai/api_resource/knowledge/document/__init__.py ================================================ from .document import Document __all__ = ['Document'] ================================================ FILE: zhipuai/api_resource/knowledge/document/document.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING, List, Mapping, cast, Optional, Dict from typing_extensions import Literal from ....core import BaseAPI, maybe_transform from ....core import NOT_GIVEN, Body, Headers, NotGiven, FileTypes import httpx from ....core import ( make_request_options, ) from ....core import deepcopy_minimal, extract_files from ....types.knowledge.document import DocumentData, DocumentObject, document_edit_params, document_list_params from ....types.files import UploadDetail, file_create_params from ....types.knowledge.document.document_list_resp import DocumentPage if TYPE_CHECKING: from ...._client import ZhipuAI __all__ = ["Document"] class Document(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def create( self, *, file: FileTypes = None, custom_separator: Optional[List[str]] = None, upload_detail: List[UploadDetail] = None, purpose: Literal["retrieval"], knowledge_id: str = None, sentence_size: int = None, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> DocumentObject: if not file and not upload_detail: raise ValueError("At least one of `file` and `upload_detail` must be provided.") body = deepcopy_minimal( { "file": file, "upload_detail": upload_detail, "purpose": purpose, "custom_separator": custom_separator, "knowledge_id": knowledge_id, "sentence_size": sentence_size, } ) files = extract_files(cast(Mapping[str, object], body), paths=[["file"]]) if files: # It should be noted that the actual Content-Type header that will be # sent to the server will contain a `boundary` parameter, e.g. # multipart/form-data; boundary=---abc-- extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})} return self._post( "/files", body=maybe_transform(body, file_create_params.FileCreateParams), files=files, options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=DocumentObject, ) def edit( self, document_id: str, knowledge_type: str, *, custom_separator: Optional[List[str]] = None, sentence_size: Optional[int] = None, callback_url: Optional[str] = None, callback_header: Optional[Dict[str, str]] = None, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> httpx.Response: """ Args: document_id: 知识id knowledge_type: 知识类型: 1:文章知识: 支持pdf,url,docx 2.问答知识-文档: 支持pdf,url,docx 3.问答知识-表格: 支持xlsx 4.商品库-表格: 支持xlsx 5.自定义: 支持pdf,url,docx extra_headers: Send extra headers extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds :param knowledge_type: :param document_id: :param timeout: :param extra_body: :param callback_header: :param sentence_size: :param extra_headers: :param callback_url: :param custom_separator: """ if not document_id: raise ValueError(f"Expected a non-empty value for `document_id` but received {document_id!r}") body = deepcopy_minimal( { "id": document_id, "knowledge_type": knowledge_type, "custom_separator": custom_separator, "sentence_size": sentence_size, "callback_url": callback_url, "callback_header": callback_header, } ) return self._put( f"/document/{document_id}", body=maybe_transform(body, document_edit_params.DocumentEditParams), options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=httpx.Response, ) def list( self, knowledge_id: str, *, purpose: str | NotGiven = NOT_GIVEN, page: str | NotGiven = NOT_GIVEN, limit: str | NotGiven = NOT_GIVEN, order: Literal["desc", "asc"] | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> DocumentPage: return self._get( "/files", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout, query=maybe_transform( { "knowledge_id": knowledge_id, "purpose": purpose, "page": page, "limit": limit, "order": order, }, document_list_params.DocumentListParams, ), ), cast_type=DocumentPage, ) def delete( self, document_id: str, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> httpx.Response: """ Delete a file. Args: document_id: 知识id extra_headers: Send extra headers extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ if not document_id: raise ValueError(f"Expected a non-empty value for `document_id` but received {document_id!r}") return self._delete( f"/document/{document_id}", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=httpx.Response, ) def retrieve( self, document_id: str, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> DocumentData: """ Args: extra_headers: Send extra headers extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ if not document_id: raise ValueError(f"Expected a non-empty value for `document_id` but received {document_id!r}") return self._get( f"/document/{document_id}", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=DocumentData, ) ================================================ FILE: zhipuai/api_resource/knowledge/knowledge.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING, List, Mapping, cast, Optional from typing_extensions import Literal from ...core import NOT_GIVEN, Body, Headers, NotGiven, FileTypes, BaseAPI, maybe_transform import httpx from ...core import ( make_request_options, ) from ...core import deepcopy_minimal, cached_property from ...types.knowledge import knowledge_create_params, knowledge_list_params from ...types.knowledge import KnowledgeInfo, KnowledgeUsed from ...core.pagination import SyncCursorPage from .document import Document from ...types.knowledge.knowledge_list_resp import KnowledgePage if TYPE_CHECKING: from ..._client import ZhipuAI __all__ = ["Knowledge"] class Knowledge(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) @cached_property def document(self) -> Document: return Document(self._client) def create( self, embedding_id: int, name: str, *, customer_identifier: Optional[str] = None, description: Optional[str] = None, background: Optional[Literal['blue', 'red', 'orange', 'purple', 'sky']] = None, icon: Optional[Literal['question', 'book', 'seal', 'wrench', 'tag', 'horn', 'house']] = None, bucket_id: Optional[str] = None, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> KnowledgeInfo: body = deepcopy_minimal( { "embedding_id": embedding_id, "name": name, "customer_identifier": customer_identifier, "description": description, "background": background, "icon": icon, "bucket_id": bucket_id, } ) return self._post( "/knowledge", body=maybe_transform(body, knowledge_create_params.KnowledgeBaseParams), options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=KnowledgeInfo, ) def modify( self, knowledge_id: str, embedding_id: int, *, name: str, description: Optional[str] = None, background: Optional[Literal['blue', 'red', 'orange', 'purple', 'sky']] = None, icon: Optional[Literal['question', 'book', 'seal', 'wrench', 'tag', 'horn', 'house']] = None, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> httpx.Response: body = deepcopy_minimal( { "id": knowledge_id, "embedding_id": embedding_id, "name": name, "description": description, "background": background, "icon": icon, } ) return self._put( f"/knowledge/{knowledge_id}", body=maybe_transform(body, knowledge_create_params.KnowledgeBaseParams), options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=httpx.Response, ) def query( self, *, page: int | NotGiven = 1, size: int | NotGiven = 10, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> KnowledgePage: return self._get( "/knowledge", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout, query=maybe_transform( { "page": page, "size": size, }, knowledge_list_params.KnowledgeListParams, ), ), cast_type=KnowledgePage, ) def delete( self, knowledge_id: str, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> httpx.Response: """ Delete a file. Args: knowledge_id: 知识库ID extra_headers: Send extra headers extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ if not knowledge_id: raise ValueError(f"Expected a non-empty value for `knowledge_id`") return self._delete( f"/knowledge/{knowledge_id}", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=httpx.Response, ) def used( self, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> KnowledgeUsed: """ Returns the contents of the specified file. Args: extra_headers: Send extra headers extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds """ return self._get( f"/knowledge/capacity", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=KnowledgeUsed, ) ================================================ FILE: zhipuai/api_resource/moderation/__init__.py ================================================ from .moderations import ( Moderations ) __all__ = [ 'Moderations' ] ================================================ FILE: zhipuai/api_resource/moderation/moderations.py ================================================ from __future__ import annotations from typing import Union, List, TYPE_CHECKING, Dict import logging from ...core import BaseAPI, deepcopy_minimal from ...types.moderation.moderation_completion import Completion logger = logging.getLogger(__name__) if TYPE_CHECKING: from ..._client import ZhipuAI __all__ = ["Moderations"] class Moderations(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def create( self, *, model: str, input: Union[str, List[str], Dict], ) -> Completion: body = deepcopy_minimal({ "model": model, "input": input }) return self._post( "/moderations", body=body, cast_type=Completion ) ================================================ FILE: zhipuai/api_resource/tools/__init__.py ================================================ from .tools import Tools __all__ = ['Tools'] ================================================ FILE: zhipuai/api_resource/tools/tools.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING, List, Union, Dict, Optional from typing_extensions import Literal from ...core import NOT_GIVEN, Body, Headers, NotGiven, BaseAPI, maybe_transform, StreamResponse, deepcopy_minimal import httpx from ...core import ( make_request_options, ) import logging from ...types.tools import tools_web_search_params, WebSearch, WebSearchChunk logger = logging.getLogger(__name__) if TYPE_CHECKING: from ..._client import ZhipuAI __all__ = ["Tools"] class Tools(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def web_search( self, *, model: str, request_id: Optional[str] | NotGiven = NOT_GIVEN, stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN, messages: Union[str, List[str], List[int], object, None], scope: Optional[str] | NotGiven = NOT_GIVEN, location: Optional[str] | NotGiven = NOT_GIVEN, recent_days: Optional[int] | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> WebSearch | StreamResponse[WebSearchChunk]: body = deepcopy_minimal( { "model": model, "request_id": request_id, "messages": messages, "stream": stream, "scope": scope, "location": location, "recent_days": recent_days, }) return self._post( "/tools", body= maybe_transform(body, tools_web_search_params.WebSearchParams), options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=WebSearch, stream=stream or False, stream_cls=StreamResponse[WebSearchChunk], ) ================================================ FILE: zhipuai/api_resource/videos/__init__.py ================================================ from .videos import ( Videos, ) __all__ = [ 'Videos', ] ================================================ FILE: zhipuai/api_resource/videos/videos.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING, List, Mapping, cast, Optional, Dict from typing_extensions import Literal from ...types.sensitive_word_check import SensitiveWordCheckRequest from ...types.video import video_create_params from ...types.video import VideoObject from ...core import BaseAPI, maybe_transform from ...core import NOT_GIVEN, Body, Headers, NotGiven import httpx from ...core import ( make_request_options, ) from ...core import deepcopy_minimal, extract_files if TYPE_CHECKING: from ..._client import ZhipuAI __all__ = ["Videos"] class Videos(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def generations( self, model: str, *, prompt: str = None, image_url: object = None, quality: str = None, with_audio: bool = None, size: str = None, duration: int = None, fps: int = None, sensitive_word_check: Optional[SensitiveWordCheckRequest] | NotGiven = NOT_GIVEN, request_id: str = None, user_id: str = None, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> VideoObject: if not model and not model: raise ValueError("At least one of `model` and `prompt` must be provided.") body = deepcopy_minimal( { "model": model, "prompt": prompt, "image_url": image_url, "sensitive_word_check": sensitive_word_check, "request_id": request_id, "user_id": user_id, "quality": quality, "with_audio": with_audio, "size": size, "duration": duration, "fps": fps } ) return self._post( "/videos/generations", body=maybe_transform(body, video_create_params.VideoCreateParams), options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=VideoObject, ) def retrieve_videos_result( self, id: str, *, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> VideoObject: if not id: raise ValueError("At least one of `id` must be provided.") return self._get( f"/async-result/{id}", options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=VideoObject, ) ================================================ FILE: zhipuai/api_resource/web_search/__init__.py ================================================ from .web_search import WebSearchApi __all__ = ['WebSearchApi'] ================================================ FILE: zhipuai/api_resource/web_search/web_search.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING, List, Union, Dict, Optional from ...types.sensitive_word_check import SensitiveWordCheckRequest from ...core import NOT_GIVEN, Body, Headers, NotGiven, BaseAPI, maybe_transform, StreamResponse, deepcopy_minimal import httpx from ...core import ( make_request_options, ) import logging from ...types.web_search import web_search_create_params from ...types.web_search.web_search_resp import WebSearchResp logger = logging.getLogger(__name__) if TYPE_CHECKING: from ..._client import ZhipuAI __all__ = ["WebSearchApi"] class WebSearchApi(BaseAPI): def __init__(self, client: "ZhipuAI") -> None: super().__init__(client) def web_search( self, *, request_id: Optional[str] | NotGiven = NOT_GIVEN, search_engine: Optional[str] | NotGiven = NOT_GIVEN, search_query: Optional[str] | NotGiven = NOT_GIVEN, user_id: Optional[str] | NotGiven = NOT_GIVEN, sensitive_word_check: Optional[SensitiveWordCheckRequest] | NotGiven = NOT_GIVEN, count: Optional[int] | NotGiven = NOT_GIVEN, search_domain_filter: Optional[str] | NotGiven = NOT_GIVEN, search_recency_filter: Optional[str] | NotGiven = NOT_GIVEN, content_size: Optional[str] | NotGiven = NOT_GIVEN, search_intent: Optional[bool] | NotGiven = NOT_GIVEN, location: Optional[str] | NotGiven = NOT_GIVEN, extra_headers: Headers | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, ) -> WebSearchResp: body = deepcopy_minimal( { "request_id": request_id, "search_engine": search_engine, "search_query": search_query, "user_id": user_id, "sensitive_word_check": sensitive_word_check, "count":count, "search_domain_filter": search_domain_filter, "search_recency_filter": search_recency_filter, "content_size": content_size, "search_intent": search_intent, "location": location }) return self._post( "/web_search", body= maybe_transform(body, web_search_create_params.WebSearchCreatParams), options=make_request_options( extra_headers=extra_headers, extra_body=extra_body, timeout=timeout ), cast_type=WebSearchResp ) ================================================ FILE: zhipuai/core/__init__.py ================================================ from ._base_models import ( BaseModel, construct_type ) from ._base_api import BaseAPI from ._base_type import ( NOT_GIVEN, Headers, NotGiven, Body, IncEx, ModelT, Query, FileTypes, ) from ._base_compat import ( PYDANTIC_V2, ConfigDict, GenericModel, get_args, is_union, parse_obj, get_origin, is_literal_type, get_model_config, get_model_fields, field_get_default, cached_property, ) from ._files import ( is_file_content ) from ._errors import ( ZhipuAIError, APIStatusError, APIRequestFailedError, APIAuthenticationError, APIReachLimitError, APIInternalError, APIServerFlowExceedError, APIResponseError, APIResponseValidationError, APIConnectionError, APITimeoutError, ) from ._http_client import ( make_request_options, HttpClient ) from ._utils import ( is_list, is_mapping, parse_date, parse_datetime, is_given, maybe_transform, deepcopy_minimal, extract_files, drop_prefix_image_data, ) from ._sse_client import StreamResponse from ._constants import ( ZHIPUAI_DEFAULT_TIMEOUT, ZHIPUAI_DEFAULT_MAX_RETRIES, ZHIPUAI_DEFAULT_LIMITS, ) __all__ = [ "BaseModel", "construct_type", "BaseAPI", "NOT_GIVEN", "Headers", "NotGiven", "Body", "IncEx", "ModelT", "Query", "FileTypes", "PYDANTIC_V2", "ConfigDict", "GenericModel", "get_args", "is_union", "parse_obj", "get_origin", "is_literal_type", "get_model_config", "get_model_fields", "field_get_default", "is_file_content", "ZhipuAIError", "APIStatusError", "APIRequestFailedError", "APIAuthenticationError", "APIReachLimitError", "APIInternalError", "APIServerFlowExceedError", "APIResponseError", "APIResponseValidationError", "APITimeoutError", "make_request_options", "HttpClient", "ZHIPUAI_DEFAULT_TIMEOUT", "ZHIPUAI_DEFAULT_MAX_RETRIES", "ZHIPUAI_DEFAULT_LIMITS", "is_list", "is_mapping", "parse_date", "parse_datetime", "is_given", "maybe_transform", "deepcopy_minimal", "extract_files", "StreamResponse", ] ================================================ FILE: zhipuai/core/_base_api.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING if TYPE_CHECKING: from .._client import ZhipuAI class BaseAPI: _client: ZhipuAI def __init__(self, client: ZhipuAI) -> None: self._client = client self._delete = client.delete self._get = client.get self._post = client.post self._put = client.put self._patch = client.patch self._get_api_list = client.get_api_list ================================================ FILE: zhipuai/core/_base_compat.py ================================================ from __future__ import annotations from typing import TYPE_CHECKING, Any, Union, Generic, TypeVar, Callable, cast, overload from datetime import date, datetime from typing_extensions import Self import pydantic from pydantic.fields import FieldInfo from zhipuai.core._base_type import StrBytesIntFloat _T = TypeVar("_T") _ModelT = TypeVar("_ModelT", bound=pydantic.BaseModel) # --------------- Pydantic v2 compatibility --------------- # Pyright incorrectly reports some of our functions as overriding a method when they don't # pyright: reportIncompatibleMethodOverride=false PYDANTIC_V2 = pydantic.VERSION.startswith("2.") # v1 re-exports if TYPE_CHECKING: def parse_date(value: date | StrBytesIntFloat) -> date: # noqa: ARG001 ... def parse_datetime(value: Union[datetime, StrBytesIntFloat]) -> datetime: # noqa: ARG001 ... def get_args(t: type[Any]) -> tuple[Any, ...]: # noqa: ARG001 ... def is_union(tp: type[Any] | None) -> bool: # noqa: ARG001 ... def get_origin(t: type[Any]) -> type[Any] | None: # noqa: ARG001 ... def is_literal_type(type_: type[Any]) -> bool: # noqa: ARG001 ... def is_typeddict(type_: type[Any]) -> bool: # noqa: ARG001 ... else: if PYDANTIC_V2: from pydantic.v1.typing import ( get_args as get_args, is_union as is_union, get_origin as get_origin, is_typeddict as is_typeddict, is_literal_type as is_literal_type, ) from pydantic.v1.datetime_parse import parse_date as parse_date, parse_datetime as parse_datetime else: from pydantic.typing import ( get_args as get_args, is_union as is_union, get_origin as get_origin, is_typeddict as is_typeddict, is_literal_type as is_literal_type, ) from pydantic.datetime_parse import parse_date as parse_date, parse_datetime as parse_datetime # refactored config if TYPE_CHECKING: from pydantic import ConfigDict as ConfigDict else: if PYDANTIC_V2: from pydantic import ConfigDict else: # TODO: provide an error message here? ConfigDict = None # renamed methods / properties def parse_obj(model: type[_ModelT], value: object) -> _ModelT: if PYDANTIC_V2: return model.model_validate(value) else: return cast(_ModelT, model.parse_obj(value)) # pyright: ignore[reportDeprecated, reportUnnecessaryCast] def field_is_required(field: FieldInfo) -> bool: if PYDANTIC_V2: return field.is_required() return field.required # type: ignore def field_get_default(field: FieldInfo) -> Any: value = field.get_default() if PYDANTIC_V2: from pydantic_core import PydanticUndefined if value == PydanticUndefined: return None return value return value def field_outer_type(field: FieldInfo) -> Any: if PYDANTIC_V2: return field.annotation return field.outer_type_ # type: ignore def get_model_config(model: type[pydantic.BaseModel]) -> Any: if PYDANTIC_V2: return model.model_config return model.__config__ # type: ignore def get_model_fields(model: type[pydantic.BaseModel]) -> dict[str, FieldInfo]: if PYDANTIC_V2: return model.model_fields return model.__fields__ # type: ignore def model_copy(model: _ModelT) -> _ModelT: if PYDANTIC_V2: return model.model_copy() return model.copy() # type: ignore def model_json(model: pydantic.BaseModel, *, indent: int | None = None) -> str: if PYDANTIC_V2: return model.model_dump_json(indent=indent) return model.json(indent=indent) # type: ignore def model_dump( model: pydantic.BaseModel, *, exclude_unset: bool = False, exclude_defaults: bool = False, ) -> dict[str, Any]: if PYDANTIC_V2: return model.model_dump( exclude_unset=exclude_unset, exclude_defaults=exclude_defaults, ) return cast( "dict[str, Any]", model.dict( # pyright: ignore[reportDeprecated, reportUnnecessaryCast] exclude_unset=exclude_unset, exclude_defaults=exclude_defaults, ), ) def model_parse(model: type[_ModelT], data: Any) -> _ModelT: if PYDANTIC_V2: return model.model_validate(data) return model.parse_obj(data) # pyright: ignore[reportDeprecated] # generic models if TYPE_CHECKING: class GenericModel(pydantic.BaseModel): ... else: if PYDANTIC_V2: # there no longer needs to be a distinction in v2 but # we still have to create our own subclass to avoid # inconsistent MRO ordering errors class GenericModel(pydantic.BaseModel): ... else: import pydantic.generics class GenericModel(pydantic.generics.GenericModel, pydantic.BaseModel): ... # cached properties if TYPE_CHECKING: cached_property = property # we define a separate type (copied from typeshed) # that represents that `cached_property` is `set`able # at runtime, which differs from `@property`. # # this is a separate type as editors likely special case # `@property` and we don't want to cause issues just to have # more helpful internal types. class typed_cached_property(Generic[_T]): func: Callable[[Any], _T] attrname: str | None def __init__(self, func: Callable[[Any], _T]) -> None: ... @overload def __get__(self, instance: None, owner: type[Any] | None = None) -> Self: ... @overload def __get__(self, instance: object, owner: type[Any] | None = None) -> _T: ... def __get__(self, instance: object, owner: type[Any] | None = None) -> _T | Self: raise NotImplementedError() def __set_name__(self, owner: type[Any], name: str) -> None: ... # __set__ is not defined at runtime, but @cached_property is designed to be settable def __set__(self, instance: object, value: _T) -> None: ... else: try: from functools import cached_property as cached_property except ImportError: from cached_property import cached_property as cached_property typed_cached_property = cached_property ================================================ FILE: zhipuai/core/_base_models.py ================================================ from __future__ import annotations import inspect import os from typing import TYPE_CHECKING, Any, Type, Generic, TypeVar, cast, Dict, Callable from datetime import date, datetime from typing_extensions import ( Literal, ClassVar, Protocol, override, runtime_checkable, TypeGuard, ParamSpec, ) import pydantic import pydantic.generics from pydantic.fields import FieldInfo from pydantic import root_validator from ._base_type import ( IncEx, ModelT, ) from ._utils import is_list, is_mapping, parse_date, parse_datetime, is_annotated_type, extract_type_arg, \ strip_annotated_type, PropertyInfo, coerce_boolean from ._base_compat import ( PYDANTIC_V2, ConfigDict, GenericModel as BaseGenericModel, get_args, is_union, parse_obj, get_origin, is_literal_type, get_model_config, get_model_fields, field_get_default, ) if TYPE_CHECKING: from pydantic_core.core_schema import ModelField, LiteralSchema, ModelFieldsSchema __all__ = ["BaseModel", "GenericModel"] _BaseModelT = TypeVar("_BaseModelT", bound="BaseModel") _T = TypeVar("_T") P = ParamSpec("P") @runtime_checkable class _ConfigProtocol(Protocol): allow_population_by_field_name: bool class BaseModel(pydantic.BaseModel): if PYDANTIC_V2: model_config: ClassVar[ConfigDict] = ConfigDict( extra="allow", defer_build=coerce_boolean(os.environ.get("DEFER_PYDANTIC_BUILD", "true")) ) else: @property @override def model_fields_set(self) -> set[str]: # a forwards-compat shim for pydantic v2 return self.__fields_set__ # type: ignore class Config(pydantic.BaseConfig): # pyright: ignore[reportDeprecated] extra: Any = pydantic.Extra.allow # type: ignore def to_dict( self, *, mode: Literal["json", "python"] = "python", use_api_names: bool = True, exclude_unset: bool = True, exclude_defaults: bool = False, exclude_none: bool = False, warnings: bool = True, ) -> dict[str, object]: """Recursively generate a dictionary representation of the model, optionally specifying which fields to include or exclude. By default, fields that were not set by the API will not be included, and keys will match the API response, *not* the property names from the model. For example, if the API responds with `"fooBar": true` but we've defined a `foo_bar: bool` property, the output will use the `"fooBar"` key (unless `use_api_names=False` is passed). Args: mode: If mode is 'json', the dictionary will only contain JSON serializable types. e.g. `datetime` will be turned into a string, `"2024-3-22T18:11:19.117000Z"`. If mode is 'python', the dictionary may contain any Python objects. e.g. `datetime(2024, 3, 22)` use_api_names: Whether to use the key that the API responded with or the property name. Defaults to `True`. exclude_unset: Whether to exclude fields that have not been explicitly set. exclude_defaults: Whether to exclude fields that are set to their default value from the output. exclude_none: Whether to exclude fields that have a value of `None` from the output. warnings: Whether to log warnings when invalid fields are encountered. This is only supported in Pydantic v2. """ return self.model_dump( mode=mode, by_alias=use_api_names, exclude_unset=exclude_unset, exclude_defaults=exclude_defaults, exclude_none=exclude_none, warnings=warnings, ) def to_json( self, *, indent: int | None = 2, use_api_names: bool = True, exclude_unset: bool = True, exclude_defaults: bool = False, exclude_none: bool = False, warnings: bool = True, ) -> str: """Generates a JSON string representing this model as it would be received from or sent to the API (but with indentation). By default, fields that were not set by the API will not be included, and keys will match the API response, *not* the property names from the model. For example, if the API responds with `"fooBar": true` but we've defined a `foo_bar: bool` property, the output will use the `"fooBar"` key (unless `use_api_names=False` is passed). Args: indent: Indentation to use in the JSON output. If `None` is passed, the output will be compact. Defaults to `2` use_api_names: Whether to use the key that the API responded with or the property name. Defaults to `True`. exclude_unset: Whether to exclude fields that have not been explicitly set. exclude_defaults: Whether to exclude fields that have the default value. exclude_none: Whether to exclude fields that have a value of `None`. warnings: Whether to show any warnings that occurred during serialization. This is only supported in Pydantic v2. """ return self.model_dump_json( indent=indent, by_alias=use_api_names, exclude_unset=exclude_unset, exclude_defaults=exclude_defaults, exclude_none=exclude_none, warnings=warnings, ) @override def __str__(self) -> str: # mypy complains about an invalid self arg return f'{self.__repr_name__()}({self.__repr_str__(", ")})' # type: ignore[misc] # Override the 'construct' method in a way that supports recursive parsing without validation. # Based on https://github.com/samuelcolvin/pydantic/issues/1168#issuecomment-817742836. @classmethod @override def construct( cls: Type[ModelT], _fields_set: set[str] | None = None, **values: object, ) -> ModelT: m = cls.__new__(cls) fields_values: dict[str, object] = {} config = get_model_config(cls) populate_by_name = ( config.allow_population_by_field_name if isinstance(config, _ConfigProtocol) else config.get("populate_by_name") ) if _fields_set is None: _fields_set = set() model_fields = get_model_fields(cls) for name, field in model_fields.items(): key = field.alias if key is None or (key not in values and populate_by_name): key = name if key in values: fields_values[name] = _construct_field(value=values[key], field=field, key=key) _fields_set.add(name) else: fields_values[name] = field_get_default(field) _extra = {} for key, value in values.items(): if key not in model_fields: if PYDANTIC_V2: _extra[key] = value else: _fields_set.add(key) fields_values[key] = value object.__setattr__(m, "__dict__", fields_values) if PYDANTIC_V2: # these properties are copied from Pydantic's `model_construct()` method object.__setattr__(m, "__pydantic_private__", None) object.__setattr__(m, "__pydantic_extra__", _extra) object.__setattr__(m, "__pydantic_fields_set__", _fields_set) else: # init_private_attributes() does not exist in v2 m._init_private_attributes() # type: ignore # copied from Pydantic v1's `construct()` method object.__setattr__(m, "__fields_set__", _fields_set) return m if not TYPE_CHECKING: # type checkers incorrectly complain about this assignment # because the type signatures are technically different # although not in practice model_construct = construct if not PYDANTIC_V2: # we define aliases for some of the new pydantic v2 methods so # that we can just document these methods without having to specify # a specific pydantic version as some users may not know which # pydantic version they are currently using @override def model_dump( self, *, mode: Literal["json", "python"] | str = "python", include: IncEx = None, exclude: IncEx = None, by_alias: bool = False, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, round_trip: bool = False, warnings: bool | Literal["none", "warn", "error"] = True, context: dict[str, Any] | None = None, serialize_as_any: bool = False, ) -> dict[str, Any]: """Usage docs: https://docs.pydantic.dev/2.4/concepts/serialization/#modelmodel_dump Generate a dictionary representation of the model, optionally specifying which fields to include or exclude. Args: mode: The mode in which `to_python` should run. If mode is 'json', the dictionary will only contain JSON serializable types. If mode is 'python', the dictionary may contain any Python objects. include: A list of fields to include in the output. exclude: A list of fields to exclude from the output. by_alias: Whether to use the field's alias in the dictionary key if defined. exclude_unset: Whether to exclude fields that are unset or None from the output. exclude_defaults: Whether to exclude fields that are set to their default value from the output. exclude_none: Whether to exclude fields that have a value of `None` from the output. round_trip: Whether to enable serialization and deserialization round-trip support. warnings: Whether to log warnings when invalid fields are encountered. Returns: A dictionary representation of the model. """ if mode != "python": raise ValueError("mode is only supported in Pydantic v2") if round_trip != False: raise ValueError("round_trip is only supported in Pydantic v2") if warnings != True: raise ValueError("warnings is only supported in Pydantic v2") if context is not None: raise ValueError("context is only supported in Pydantic v2") if serialize_as_any != False: raise ValueError("serialize_as_any is only supported in Pydantic v2") return super().dict( # pyright: ignore[reportDeprecated] include=include, exclude=exclude, by_alias=by_alias, exclude_unset=exclude_unset, exclude_defaults=exclude_defaults, exclude_none=exclude_none, ) @override def model_dump_json( self, *, indent: int | None = None, include: IncEx = None, exclude: IncEx = None, by_alias: bool = False, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, round_trip: bool = False, warnings: bool | Literal["none", "warn", "error"] = True, context: dict[str, Any] | None = None, serialize_as_any: bool = False, ) -> str: """Usage docs: https://docs.pydantic.dev/2.4/concepts/serialization/#modelmodel_dump_json Generates a JSON representation of the model using Pydantic's `to_json` method. Args: indent: Indentation to use in the JSON output. If None is passed, the output will be compact. include: Field(s) to include in the JSON output. Can take either a string or set of strings. exclude: Field(s) to exclude from the JSON output. Can take either a string or set of strings. by_alias: Whether to serialize using field aliases. exclude_unset: Whether to exclude fields that have not been explicitly set. exclude_defaults: Whether to exclude fields that have the default value. exclude_none: Whether to exclude fields that have a value of `None`. round_trip: Whether to use serialization/deserialization between JSON and class instance. warnings: Whether to show any warnings that occurred during serialization. Returns: A JSON string representation of the model. """ if round_trip != False: raise ValueError("round_trip is only supported in Pydantic v2") if warnings != True: raise ValueError("warnings is only supported in Pydantic v2") if context is not None: raise ValueError("context is only supported in Pydantic v2") if serialize_as_any != False: raise ValueError("serialize_as_any is only supported in Pydantic v2") return super().json( # type: ignore[reportDeprecated] indent=indent, include=include, exclude=exclude, by_alias=by_alias, exclude_unset=exclude_unset, exclude_defaults=exclude_defaults, exclude_none=exclude_none, ) def _construct_field(value: object, field: FieldInfo, key: str) -> object: if value is None: return field_get_default(field) if PYDANTIC_V2: type_ = field.annotation else: type_ = cast(type, field.outer_type_) # type: ignore if type_ is None: raise RuntimeError(f"Unexpected field type is None for {key}") return construct_type(value=value, type_=type_) def is_basemodel(type_: type) -> bool: """Returns whether or not the given type is either a `BaseModel` or a union of `BaseModel`""" if is_union(type_): for variant in get_args(type_): if is_basemodel(variant): return True return False return is_basemodel_type(type_) def is_basemodel_type(type_: type) -> TypeGuard[type[BaseModel] | type[GenericModel]]: origin = get_origin(type_) or type_ return issubclass(origin, BaseModel) or issubclass(origin, GenericModel) def build( base_model_cls: Callable[P, _BaseModelT], *args: P.args, **kwargs: P.kwargs, ) -> _BaseModelT: """Construct a BaseModel class without validation. This is useful for cases where you need to instantiate a `BaseModel` from an API response as this provides type-safe params which isn't supported by helpers like `construct_type()`. ```py build(MyModel, my_field_a="foo", my_field_b=123) ``` """ if args: raise TypeError( "Received positional arguments which are not supported; Keyword arguments must be used instead", ) return cast(_BaseModelT, construct_type(type_=base_model_cls, value=kwargs)) def construct_type_unchecked(*, value: object, type_: type[_T]) -> _T: """Loose coercion to the expected type with construction of nested values. Note: the returned value from this function is not guaranteed to match the given type. """ return cast(_T, construct_type(value=value, type_=type_)) def construct_type(*, value: object, type_: type) -> object: """Loose coercion to the expected type with construction of nested values. If the given value does not match the expected type then it is returned as-is. """ # we allow `object` as the input type because otherwise, passing things like # `Literal['value']` will be reported as a type error by type checkers type_ = cast("type[object]", type_) # unwrap `Annotated[T, ...]` -> `T` if is_annotated_type(type_): meta: tuple[Any, ...] = get_args(type_)[1:] type_ = extract_type_arg(type_, 0) else: meta = tuple() # we need to use the origin class for any types that are subscripted generics # e.g. Dict[str, object] origin = get_origin(type_) or type_ args = get_args(type_) if is_union(origin): try: return validate_type(type_=cast("type[object]", type_), value=value) except Exception: pass # if the type is a discriminated union then we want to construct the right variant # in the union, even if the data doesn't match exactly, otherwise we'd break code # that relies on the constructed class types, e.g. # # class FooType: # kind: Literal['foo'] # value: str # # class BarType: # kind: Literal['bar'] # value: int # # without this block, if the data we get is something like `{'kind': 'bar', 'value': 'foo'}` then # we'd end up constructing `FooType` when it should be `BarType`. discriminator = _build_discriminated_union_meta(union=type_, meta_annotations=meta) if discriminator and is_mapping(value): variant_value = value.get(discriminator.field_alias_from or discriminator.field_name) if variant_value and isinstance(variant_value, str): variant_type = discriminator.mapping.get(variant_value) if variant_type: return construct_type(type_=variant_type, value=value) # if the data is not valid, use the first variant that doesn't fail while deserializing for variant in args: try: return construct_type(value=value, type_=variant) except Exception: continue raise RuntimeError(f"Could not convert data into a valid instance of {type_}") if origin == dict: if not is_mapping(value): return value _, items_type = get_args(type_) # Dict[_, items_type] return {key: construct_type(value=item, type_=items_type) for key, item in value.items()} if not is_literal_type(type_) and (issubclass(origin, BaseModel) or issubclass(origin, GenericModel)): if is_list(value): return [cast(Any, type_).construct(**entry) if is_mapping(entry) else entry for entry in value] if is_mapping(value): if issubclass(type_, BaseModel): return type_.construct(**value) # type: ignore[arg-type] return cast(Any, type_).construct(**value) if origin == list: if not is_list(value): return value inner_type = args[0] # List[inner_type] return [construct_type(value=entry, type_=inner_type) for entry in value] if origin == float: if isinstance(value, int): coerced = float(value) if coerced != value: return value return coerced return value if type_ == datetime: try: return parse_datetime(value) # type: ignore except Exception: return value if type_ == date: try: return parse_date(value) # type: ignore except Exception: return value return value @runtime_checkable class CachedDiscriminatorType(Protocol): __discriminator__: DiscriminatorDetails class DiscriminatorDetails: field_name: str """The name of the discriminator field in the variant class, e.g. ```py class Foo(BaseModel): type: Literal['foo'] ``` Will result in field_name='type' """ field_alias_from: str | None """The name of the discriminator field in the API response, e.g. ```py class Foo(BaseModel): type: Literal['foo'] = Field(alias='type_from_api') ``` Will result in field_alias_from='type_from_api' """ mapping: dict[str, type] """Mapping of discriminator value to variant type, e.g. {'foo': FooVariant, 'bar': BarVariant} """ def __init__( self, *, mapping: dict[str, type], discriminator_field: str, discriminator_alias: str | None, ) -> None: self.mapping = mapping self.field_name = discriminator_field self.field_alias_from = discriminator_alias def _build_discriminated_union_meta(*, union: type, meta_annotations: tuple[Any, ...]) -> DiscriminatorDetails | None: if isinstance(union, CachedDiscriminatorType): return union.__discriminator__ discriminator_field_name: str | None = None for annotation in meta_annotations: if isinstance(annotation, PropertyInfo) and annotation.discriminator is not None: discriminator_field_name = annotation.discriminator break if not discriminator_field_name: return None mapping: dict[str, type] = {} discriminator_alias: str | None = None for variant in get_args(union): variant = strip_annotated_type(variant) if is_basemodel_type(variant): if PYDANTIC_V2: field = _extract_field_schema_pv2(variant, discriminator_field_name) if not field: continue # Note: if one variant defines an alias then they all should discriminator_alias = field.get("serialization_alias") field_schema = field["schema"] if field_schema["type"] == "literal": for entry in cast("LiteralSchema", field_schema)["expected"]: if isinstance(entry, str): mapping[entry] = variant else: field_info = cast("dict[str, FieldInfo]", variant.__fields__).get( discriminator_field_name) # pyright: ignore[reportDeprecated, reportUnnecessaryCast] if not field_info: continue # Note: if one variant defines an alias then they all should discriminator_alias = field_info.alias if field_info.annotation and is_literal_type(field_info.annotation): for entry in get_args(field_info.annotation): if isinstance(entry, str): mapping[entry] = variant if not mapping: return None details = DiscriminatorDetails( mapping=mapping, discriminator_field=discriminator_field_name, discriminator_alias=discriminator_alias, ) cast(CachedDiscriminatorType, union).__discriminator__ = details return details def _extract_field_schema_pv2(model: type[BaseModel], field_name: str) -> ModelField | None: schema = model.__pydantic_core_schema__ if schema["type"] != "model": return None fields_schema = schema["schema"] if fields_schema["type"] != "model-fields": return None fields_schema = cast("ModelFieldsSchema", fields_schema) field = fields_schema["fields"].get(field_name) if not field: return None return cast("ModelField", field) # pyright: ignore[reportUnnecessaryCast] def validate_type(*, type_: type[_T], value: object) -> _T: """Strict validation that the given value matches the expected type""" if inspect.isclass(type_) and issubclass(type_, pydantic.BaseModel): return cast(_T, parse_obj(type_, value)) return cast(_T, _validate_non_model_type(type_=type_, value=value)) # our use of subclasssing here causes weirdness for type checkers, # so we just pretend that we don't subclass if TYPE_CHECKING: GenericModel = BaseModel else: class GenericModel(BaseGenericModel, BaseModel): pass if PYDANTIC_V2: from pydantic import TypeAdapter def _validate_non_model_type(*, type_: type[_T], value: object) -> _T: return TypeAdapter(type_).validate_python(value) elif not TYPE_CHECKING: class TypeAdapter(Generic[_T]): """Used as a placeholder to easily convert runtime types to a Pydantic format to provide validation. For example: ```py validated = RootModel[int](__root__="5").__root__ # validated: 5 ``` """ def __init__(self, type_: Type[_T]): self.type_ = type_ def validate_python(self, value: Any) -> _T: if not isinstance(value, self.type_): raise ValueError(f"Invalid type: {value} is not of type {self.type_}") return value def _validate_non_model_type(*, type_: type[_T], value: object) -> _T: return TypeAdapter(type_).validate_python(value) ================================================ FILE: zhipuai/core/_base_type.py ================================================ from __future__ import annotations from os import PathLike from typing import ( IO, TYPE_CHECKING, Any, Dict, List, Type, Tuple, Union, Mapping, TypeVar, Callable, Optional, Sequence, ) import pydantic from httpx import Response from typing_extensions import Literal, Protocol, TypeAlias, TypedDict, override, runtime_checkable Query = Mapping[str, object] Body = object AnyMapping = Mapping[str, object] PrimitiveData = Union[str, int, float, bool, None] Data = Union[PrimitiveData, List[Any], Tuple[Any], "Mapping[str, Any]"] ModelT = TypeVar("ModelT", bound=pydantic.BaseModel) _T = TypeVar("_T") if TYPE_CHECKING: NoneType: Type[None] else: NoneType = type(None) # Sentinel class used until PEP 0661 is accepted class NotGiven: """ A sentinel singleton class used to distinguish omitted keyword arguments from those passed in with the value None (which may have different behavior). For example: ```py def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response: ... get(timeout=1) # 1s timeout get(timeout=None) # No timeout get() # Default timeout behavior, which may not be statically known at the method definition. ``` """ def __bool__(self) -> Literal[False]: return False @override def __repr__(self) -> str: return "NOT_GIVEN" NotGivenOr = Union[_T, NotGiven] NOT_GIVEN = NotGiven() class Omit: """In certain situations you need to be able to represent a case where a default value has to be explicitly removed and `None` is not an appropriate substitute, for example: ```py # as the default `Content-Type` header is `application/json` that will be sent client.post('/upload/files', files={'file': b'my raw file content'}) # you can't explicitly override the header as it has to be dynamically generated # to look something like: 'multipart/form-data; boundary=0d8382fcf5f8c3be01ca2e11002d2983' client.post(..., headers={'Content-Type': 'multipart/form-data'}) # instead you can remove the default `application/json` header by passing Omit client.post(..., headers={'Content-Type': Omit()}) ``` """ def __bool__(self) -> Literal[False]: return False @runtime_checkable class ModelBuilderProtocol(Protocol): @classmethod def build( cls: type[_T], *, response: Response, data: object, ) -> _T: ... Headers = Mapping[str, Union[str, Omit]] class HeadersLikeProtocol(Protocol): def get(self, __key: str) -> str | None: ... HeadersLike = Union[Headers, HeadersLikeProtocol] ResponseT = TypeVar( "ResponseT", bound="Union[str, None, BaseModel, List[Any], Dict[str, Any], Response, UnknownResponse, ModelBuilderProtocol, BinaryResponseContent]", ) StrBytesIntFloat = Union[str, bytes, int, float] # Note: copied from Pydantic # https://github.com/pydantic/pydantic/blob/32ea570bf96e84234d2992e1ddf40ab8a565925a/pydantic/main.py#L49 IncEx: TypeAlias = "set[int] | set[str] | dict[int, Any] | dict[str, Any] | None" PostParser = Callable[[Any], Any] @runtime_checkable class InheritsGeneric(Protocol): """Represents a type that has inherited from `Generic` The `__orig_bases__` property can be used to determine the resolved type variable for a given base class. """ __orig_bases__: tuple[_GenericAlias] class _GenericAlias(Protocol): __origin__: type[object] class HttpxSendArgs(TypedDict, total=False): auth: httpx.Auth # for user input files if TYPE_CHECKING: Base64FileInput = Union[IO[bytes], PathLike[str]] FileContent = Union[IO[bytes], bytes, PathLike[str]] else: Base64FileInput = Union[IO[bytes], PathLike] FileContent = Union[IO[bytes], bytes, PathLike] FileTypes = Union[ # file (or bytes) FileContent, # (filename, file (or bytes)) Tuple[Optional[str], FileContent], # (filename, file (or bytes), content_type) Tuple[Optional[str], FileContent, Optional[str]], # (filename, file (or bytes), content_type, headers) Tuple[Optional[str], FileContent, Optional[str], Mapping[str, str]], ] RequestFiles = Union[Mapping[str, FileTypes], Sequence[Tuple[str, FileTypes]]] # duplicate of the above but without our custom file support HttpxFileContent = Union[bytes, IO[bytes]] HttpxFileTypes = Union[ # file (or bytes) HttpxFileContent, # (filename, file (or bytes)) Tuple[Optional[str], HttpxFileContent], # (filename, file (or bytes), content_type) Tuple[Optional[str], HttpxFileContent, Optional[str]], # (filename, file (or bytes), content_type, headers) Tuple[Optional[str], HttpxFileContent, Optional[str], Mapping[str, str]], ] HttpxRequestFiles = Union[Mapping[str, HttpxFileTypes], Sequence[Tuple[str, HttpxFileTypes]]] ================================================ FILE: zhipuai/core/_constants.py ================================================ import httpx RAW_RESPONSE_HEADER = "X-Stainless-Raw-Response" # 通过 `Timeout` 控制接口`connect` 和 `read` 超时时间，默认为`timeout=300.0, connect=8.0` ZHIPUAI_DEFAULT_TIMEOUT = httpx.Timeout(timeout=300.0, connect=8.0) # 通过 `retry` 参数控制重试次数，默认为3次 ZHIPUAI_DEFAULT_MAX_RETRIES = 3 # 通过 `Limits` 控制最大连接数和保持连接数，默认为`max_connections=50, max_keepalive_connections=10` ZHIPUAI_DEFAULT_LIMITS = httpx.Limits(max_connections=50, max_keepalive_connections=10) INITIAL_RETRY_DELAY = 0.5 MAX_RETRY_DELAY = 8.0 ================================================ FILE: zhipuai/core/_errors.py ================================================ from __future__ import annotations import httpx __all__ = [ "ZhipuAIError", "APIStatusError", "APIRequestFailedError", "APIAuthenticationError", "APIReachLimitError", "APIInternalError", "APIServerFlowExceedError", "APIResponseError", "APIResponseValidationError", "APITimeoutError", "APIConnectionError", ] class ZhipuAIError(Exception): def __init__(self, message: str, ) -> None: super().__init__(message) class APIStatusError(ZhipuAIError): response: httpx.Response status_code: int def __init__(self, message: str, *, response: httpx.Response) -> None: super().__init__(message) self.response = response self.status_code = response.status_code class APIRequestFailedError(APIStatusError): ... class APIAuthenticationError(APIStatusError): ... class APIReachLimitError(APIStatusError): ... class APIInternalError(APIStatusError): ... class APIServerFlowExceedError(APIStatusError): ... class APIResponseError(ZhipuAIError): message: str request: httpx.Request json_data: object def __init__(self, message: str, request: httpx.Request, json_data: object): self.message = message self.request = request self.json_data = json_data super().__init__(message) class APIResponseValidationError(APIResponseError): status_code: int response: httpx.Response def __init__( self, response: httpx.Response, json_data: object | None, *, message: str | None = None ) -> None: super().__init__( message=message or "Data returned by API invalid for expected schema.", request=response.request, json_data=json_data ) self.response = response self.status_code = response.status_code class APIConnectionError(APIResponseError): def __init__(self, *, message: str = "Connection error.", request: httpx.Request) -> None: super().__init__(message, request, json_data=None) class APITimeoutError(APIConnectionError): def __init__(self, request: httpx.Request) -> None: super().__init__(message="Request timed out.", request=request) ================================================ FILE: zhipuai/core/_files.py ================================================ from __future__ import annotations import io import os import pathlib from typing import Mapping, Sequence, overload from typing_extensions import TypeGuard from ._base_type import ( FileTypes, HttpxFileTypes, HttpxRequestFiles, RequestFiles, Base64FileInput, FileContent, HttpxFileContent, ) from ._utils import is_tuple_t, is_mapping_t, is_sequence_t def is_base64_file_input(obj: object) -> TypeGuard[Base64FileInput]: return isinstance(obj, io.IOBase) or isinstance(obj, os.PathLike) def is_file_content(obj: object) -> TypeGuard[FileContent]: return ( isinstance(obj, bytes) or isinstance(obj, tuple) or isinstance(obj, io.IOBase) or isinstance(obj, os.PathLike) ) def assert_is_file_content(obj: object, *, key: str | None = None) -> None: if not is_file_content(obj): prefix = f"Expected entry at `{key}`" if key is not None else f"Expected file input `{obj!r}`" raise RuntimeError( f"{prefix} to be bytes, an io.IOBase instance, PathLike or a tuple but received {type(obj)} instead. See https://github.com/openai/openai-python/tree/main#file-uploads" ) from None @overload def to_httpx_files(files: None) -> None: ... @overload def to_httpx_files(files: RequestFiles) -> HttpxRequestFiles: ... def to_httpx_files(files: RequestFiles | None) -> HttpxRequestFiles | None: if files is None: return None if is_mapping_t(files): files = {key: _transform_file(file) for key, file in files.items()} elif is_sequence_t(files): files = [(key, _transform_file(file)) for key, file in files] else: raise TypeError(f"Unexpected file type input {type(files)}, expected mapping or sequence") return files def _transform_file(file: FileTypes) -> HttpxFileTypes: if is_file_content(file): if isinstance(file, os.PathLike): path = pathlib.Path(file) return (path.name, path.read_bytes()) return file if is_tuple_t(file): return (file[0], _read_file_content(file[1]), *file[2:]) raise TypeError(f"Expected file types input to be a FileContent type or to be a tuple") def _read_file_content(file: FileContent) -> HttpxFileContent: if isinstance(file, os.PathLike): return pathlib.Path(file).read_bytes() return file ================================================ FILE: zhipuai/core/_http_client.py ================================================ # -*- coding:utf-8 -*- from __future__ import annotations import inspect import warnings from typing import ( Any, Type, Union, cast, Mapping, TypeVar, Dict, overload, Optional, Literal, Generic, Iterator, TYPE_CHECKING ) from random import random import time import httpx import pydantic from httpx import URL, Timeout from . import _errors, get_origin from ._base_compat import model_copy from ._base_type import ( NotGiven, ResponseT, Body, Headers, NOT_GIVEN, RequestFiles, Query, Data, Omit, AnyMapping, ModelBuilderProtocol, HttpxSendArgs, PostParser, ) from ._constants import ZHIPUAI_DEFAULT_MAX_RETRIES, ZHIPUAI_DEFAULT_LIMITS, ZHIPUAI_DEFAULT_TIMEOUT, \ INITIAL_RETRY_DELAY, MAX_RETRY_DELAY, RAW_RESPONSE_HEADER from ._errors import APIResponseValidationError, APIStatusError, APITimeoutError, APIConnectionError from ._files import to_httpx_files from ._legacy_response import LegacyAPIResponse from ._request_opt import FinalRequestOptions, UserRequestInput from ._response import BaseAPIResponse, APIResponse, extract_response_type from ._sse_client import StreamResponse from ._utils import flatten, is_mapping, is_given from ._base_models import construct_type, GenericModel, validate_type import logging log: logging.Logger = logging.getLogger(__name__) # TODO: make base page type vars covariant SyncPageT = TypeVar("SyncPageT", bound="BaseSyncPage[Any]") # AsyncPageT = TypeVar("AsyncPageT", bound="BaseAsyncPage[Any]") _T = TypeVar("_T") _T_co = TypeVar("_T_co", covariant=True) if TYPE_CHECKING: from httpx._config import DEFAULT_TIMEOUT_CONFIG as HTTPX_DEFAULT_TIMEOUT else: try: from httpx._config import DEFAULT_TIMEOUT_CONFIG as HTTPX_DEFAULT_TIMEOUT except ImportError: # taken from https://github.com/encode/httpx/blob/3ba5fe0d7ac70222590e759c31442b1cab263791/httpx/_config.py#L366 HTTPX_DEFAULT_TIMEOUT = Timeout(5.0) headers = { "Accept": "application/json", "Content-Type": "application/json; charset=UTF-8", } class PageInfo: """Stores the necessary information to build the request to retrieve the next page. Either `url` or `params` must be set. """ url: URL | NotGiven params: Query | NotGiven @overload def __init__( self, *, url: URL, ) -> None: ... @overload def __init__( self, *, params: Query, ) -> None: ... def __init__( self, *, url: URL | NotGiven = NOT_GIVEN, params: Query | NotGiven = NOT_GIVEN, ) -> None: self.url = url self.params = params class BasePage(GenericModel, Generic[_T]): """ Defines the core interface for pagination. Type Args: ModelT: The pydantic model that represents an item in the response. Methods: has_next_page(): Check if there is another page available next_page_info(): Get the necessary information to make a request for the next page """ _options: FinalRequestOptions = pydantic.PrivateAttr() _model: Type[_T] = pydantic.PrivateAttr() def has_next_page(self) -> bool: items = self._get_page_items() if not items: return False return self.next_page_info() is not None def next_page_info(self) -> Optional[PageInfo]: ... def _get_page_items(self) -> Iterable[_T]: # type: ignore[empty-body] ... def _params_from_url(self, url: URL) -> httpx.QueryParams: # TODO: do we have to preprocess params here? return httpx.QueryParams(cast(Any, self._options.params)).merge(url.params) def _info_to_options(self, info: PageInfo) -> FinalRequestOptions: options = model_copy(self._options) options._strip_raw_response_header() if not isinstance(info.params, NotGiven): options.params = {**options.params, **info.params} return options if not isinstance(info.url, NotGiven): params = self._params_from_url(info.url) url = info.url.copy_with(params=params) options.params = dict(url.params) options.url = str(url) return options raise ValueError("Unexpected PageInfo state") class BaseSyncPage(BasePage[_T], Generic[_T]): _client: HttpClient = pydantic.PrivateAttr() def _set_private_attributes( self, client: HttpClient, model: Type[_T], options: FinalRequestOptions, ) -> None: self._model = model self._client = client self._options = options # Pydantic uses a custom `__iter__` method to support casting BaseModels # to dictionaries. e.g. dict(model). # As we want to support `for item in page`, this is inherently incompatible # with the default pydantic behaviour. It is not possible to support both # use cases at once. Fortunately, this is not a big deal as all other pydantic # methods should continue to work as expected as there is an alternative method # to cast a model to a dictionary, model.dict(), which is used internally # by pydantic. def __iter__(self) -> Iterator[_T]: # type: ignore for page in self.iter_pages(): for item in page._get_page_items(): yield item def iter_pages(self: SyncPageT) -> Iterator[SyncPageT]: page = self while True: yield page if page.has_next_page(): page = page.get_next_page() else: return def get_next_page(self: SyncPageT) -> SyncPageT: info = self.next_page_info() if not info: raise RuntimeError( "No next page expected; please check `.has_next_page()` before calling `.get_next_page()`." ) options = self._info_to_options(info) return self._client._request_api_list(self._model, page=self.__class__, options=options) class HttpClient: _client: httpx.Client _version: str _base_url: URL max_retries: int timeout: Union[float, Timeout, None] _limits: httpx.Limits _has_custom_http_client: bool _default_stream_cls: Type[StreamResponse[Any]] | None = None _strict_response_validation: bool def __init__( self, *, version: str, base_url: URL, _strict_response_validation: bool, max_retries: int = ZHIPUAI_DEFAULT_MAX_RETRIES, timeout: Union[float, Timeout, None], limits: httpx.Limits | None = None, custom_httpx_client: httpx.Client | None = None, custom_headers: Mapping[str, str] | None = None, ) -> None: if limits is not None: warnings.warn( "The `connection_pool_limits` argument is deprecated. The `http_client` argument should be passed instead", category=DeprecationWarning, stacklevel=3, ) if custom_httpx_client is not None: raise ValueError("The `http_client` argument is mutually exclusive with `connection_pool_limits`") else: limits = ZHIPUAI_DEFAULT_LIMITS if not is_given(timeout): if custom_httpx_client and custom_httpx_client.timeout != HTTPX_DEFAULT_TIMEOUT: timeout = custom_httpx_client.timeout else: timeout = ZHIPUAI_DEFAULT_TIMEOUT self.max_retries = max_retries self.timeout = timeout self._limits = limits self._has_custom_http_client = bool(custom_httpx_client) self._client = custom_httpx_client or httpx.Client( base_url=base_url, timeout=self.timeout, limits=limits, ) self._version = version url = URL(url=base_url) if not url.raw_path.endswith(b"/"): url = url.copy_with(raw_path=url.raw_path + b"/") self._base_url = url self._custom_headers = custom_headers or {} self._strict_response_validation = _strict_response_validation def _prepare_url(self, url: str) -> URL: sub_url = URL(url) if sub_url.is_relative_url: request_raw_url = self._base_url.raw_path + sub_url.raw_path.lstrip(b"/") return self._base_url.copy_with(raw_path=request_raw_url) return sub_url @property def _default_headers(self): return \ { "Accept": "application/json", "Content-Type": "application/json; charset=UTF-8", "ZhipuAI-SDK-Ver": self._version, "source_type": "zhipu-sdk-python", "x-request-sdk": "zhipu-sdk-python", **self.auth_headers, **self._custom_headers, } @property def custom_auth(self) -> httpx.Auth | None: return None @property def auth_headers(self): return {} def _prepare_headers(self, options: FinalRequestOptions) -> httpx.Headers: custom_headers = options.headers or {} headers_dict = _merge_mappings(self._default_headers, custom_headers) httpx_headers = httpx.Headers(headers_dict) return httpx_headers def _remaining_retries( self, remaining_retries: Optional[int], options: FinalRequestOptions, ) -> int: return remaining_retries if remaining_retries is not None else options.get_max_retries(self.max_retries) def _calculate_retry_timeout( self, remaining_retries: int, options: FinalRequestOptions, response_headers: Optional[httpx.Headers] = None, ) -> float: max_retries = options.get_max_retries(self.max_retries) # If the API asks us to wait a certain amount of time (and it's a reasonable amount), just do what it says. # retry_after = self._parse_retry_after_header(response_headers) # if retry_after is not None and 0 < retry_after <= 60: # return retry_after nb_retries = max_retries - remaining_retries # Apply exponential backoff, but not more than the max. sleep_seconds = min(INITIAL_RETRY_DELAY * pow(2.0, nb_retries), MAX_RETRY_DELAY) # Apply some jitter, plus-or-minus half a second. jitter = 1 - 0.25 * random() timeout = sleep_seconds * jitter return timeout if timeout >= 0 else 0 def _build_request( self, options: FinalRequestOptions ) -> httpx.Request: kwargs: dict[str, Any] = {} headers = self._prepare_headers(options) url = self._prepare_url(options.url) json_data = options.json_data if options.extra_json is not None: if json_data is None: json_data = cast(Body, options.extra_json) elif is_mapping(json_data): json_data = _merge_mappings(json_data, options.extra_json) else: raise RuntimeError(f"Unexpected JSON data type, {type(json_data)}, cannot merge with `extra_body`") content_type = headers.get("Content-Type") # multipart/form-data; boundary=---abc-- if headers.get("Content-Type") == "multipart/form-data": if "boundary" not in content_type: # only remove the header if the boundary hasn't been explicitly set # as the caller doesn't want httpx to come up with their own boundary headers.pop("Content-Type") if json_data: kwargs["data"] = self._make_multipartform(json_data) return self._client.build_request( headers=headers, timeout=self.timeout if isinstance(options.timeout, NotGiven) else options.timeout, method=options.method, url=url, json=json_data, files=options.files, params=options.params, **kwargs, ) def _object_to_formfata(self, key: str, value: Data | Mapping[object, object]) -> list[tuple[str, str]]: items = [] if isinstance(value, Mapping): for k, v in value.items(): items.extend(self._object_to_formfata(f"{key}[{k}]", v)) return items if isinstance(value, (list, tuple)): for v in value: items.extend(self._object_to_formfata(key + "[]", v)) return items def _primitive_value_to_str(val) -> str: # copied from httpx if val is True: return "true" elif val is False: return "false" elif val is None: return "" return str(val) str_data = _primitive_value_to_str(value) if not str_data: return [] return [(key, str_data)] def _make_multipartform(self, data: Mapping[object, object]) -> dict[str, object]: items = flatten([self._object_to_formfata(k, v) for k, v in data.items()]) serialized: dict[str, object] = {} for key, value in items: if key in serialized: raise ValueError(f"存在重复的键: {key};") serialized[key] = value return serialized def _process_response_data( self, *, data: object, cast_type: Type[ResponseT], response: httpx.Response, ) -> ResponseT: if data is None: return cast(ResponseT, None) if cast_type is object: return cast(ResponseT, data) try: if inspect.isclass(cast_type) and issubclass(cast_type, ModelBuilderProtocol): return cast(ResponseT, cast_type.build(response=response, data=data)) if self._strict_response_validation: return cast(ResponseT, validate_type(type_=cast_type, value=data)) return cast(ResponseT, construct_type(type_=cast_type, value=data)) except pydantic.ValidationError as err: raise APIResponseValidationError(response=response, json_data=data) from err def _should_stream_response_body(self, request: httpx.Request) -> bool: return request.headers.get(RAW_RESPONSE_HEADER) == "stream" # type: ignore[no-any-return] def _should_retry(self, response: httpx.Response) -> bool: # Note: this is not a standard header should_retry_header = response.headers.get("x-should-retry") # If the server explicitly says whether or not to retry, obey. if should_retry_header == "true": log.debug("Retrying as header `x-should-retry` is set to `true`") return True if should_retry_header == "false": log.debug("Not retrying as header `x-should-retry` is set to `false`") return False # Retry on request timeouts. if response.status_code == 408: log.debug("Retrying due to status code %i", response.status_code) return True # Retry on lock timeouts. if response.status_code == 409: log.debug("Retrying due to status code %i", response.status_code) return True # Retry on rate limits. if response.status_code == 429: log.debug("Retrying due to status code %i", response.status_code) return True # Retry internal errors. if response.status_code >= 500: log.debug("Retrying due to status code %i", response.status_code) return True log.debug("Not retrying") return False def is_closed(self) -> bool: return self._client.is_closed def close(self): self._client.close() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() def request( self, cast_type: Type[ResponseT], options: FinalRequestOptions, remaining_retries: Optional[int] = None, *, stream: bool = False, stream_cls: Type[StreamResponse] | None = None, ) -> ResponseT | StreamResponse: return self._request( cast_type=cast_type, options=options, stream=stream, stream_cls=stream_cls, remaining_retries=remaining_retries, ) def _request( self, *, cast_type: Type[ResponseT], options: FinalRequestOptions, remaining_retries: int | None, stream: bool, stream_cls: Type[StreamResponse] | None, ) -> ResponseT | StreamResponse: retries = self._remaining_retries(remaining_retries, options) request = self._build_request(options) kwargs: HttpxSendArgs = {} if self.custom_auth is not None: kwargs["auth"] = self.custom_auth try: response = self._client.send( request, stream=stream or self._should_stream_response_body(request=request), **kwargs, ) except httpx.TimeoutException as err: log.debug("Encountered httpx.TimeoutException", exc_info=True) if retries > 0: return self._retry_request( options, cast_type, retries, stream=stream, stream_cls=stream_cls, response_headers=None, ) log.debug("Raising timeout error") raise APITimeoutError(request=request) from err except Exception as err: log.debug("Encountered Exception", exc_info=True) if retries > 0: return self._retry_request( options, cast_type, retries, stream=stream, stream_cls=stream_cls, response_headers=None, ) log.debug("Raising connection error") raise APIConnectionError(request=request) from err log.debug( 'HTTP Request: %s %s "%i %s"', request.method, request.url, response.status_code, response.reason_phrase ) try: response.raise_for_status() except httpx.HTTPStatusError as err: # thrown on 4xx and 5xx status code log.debug("Encountered httpx.HTTPStatusError", exc_info=True) if retries > 0 and self._should_retry(err.response): err.response.close() return self._retry_request( options, cast_type, retries, err.response.headers, stream=stream, stream_cls=stream_cls, ) # If the response is streamed then we need to explicitly read the response # to completion before attempting to access the response text. if not err.response.is_closed: err.response.read() log.debug("Re-raising status error") raise self._make_status_error(err.response) from None # return self._parse_response( # cast_type=cast_type, # options=options, # response=response, # stream=stream, # stream_cls=stream_cls, # ) return self._process_response( cast_type=cast_type, options=options, response=response, stream=stream, stream_cls=stream_cls, ) def _retry_request( self, options: FinalRequestOptions, cast_type: Type[ResponseT], remaining_retries: int, response_headers: httpx.Headers | None, *, stream: bool, stream_cls: Type[StreamResponse] | None, ) -> ResponseT | StreamResponse: remaining = remaining_retries - 1 if remaining == 1: log.debug("1 retry left") else: log.debug("%i retries left", remaining) timeout = self._calculate_retry_timeout(remaining, options, response_headers) log.info("Retrying request to %s in %f seconds", options.url, timeout) # In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a # different thread if necessary. time.sleep(timeout) return self._request( options=options, cast_type=cast_type, remaining_retries=remaining, stream=stream, stream_cls=stream_cls, ) def _process_response( self, *, cast_type: Type[ResponseT], options: FinalRequestOptions, response: httpx.Response, stream: bool, stream_cls: Type[StreamResponse] | None, ) -> ResponseT: # _legacy_response with raw_response_header to paser method if response.request.headers.get(RAW_RESPONSE_HEADER) == "true": return cast( ResponseT, LegacyAPIResponse( raw=response, client=self, cast_type=cast_type, stream=stream, stream_cls=stream_cls, options=options, ), ) origin = get_origin(cast_type) or cast_type if inspect.isclass(origin) and issubclass(origin, BaseAPIResponse): if not issubclass(origin, APIResponse): raise TypeError(f"API Response types must subclass {APIResponse}; Received {origin}") response_cls = cast("type[BaseAPIResponse[Any]]", cast_type) return cast( ResponseT, response_cls( raw=response, client=self, cast_type=extract_response_type(response_cls), stream=stream, stream_cls=stream_cls, options=options, ), ) if cast_type == httpx.Response: return cast(ResponseT, response) api_response = APIResponse( raw=response, client=self, cast_type=cast("type[ResponseT]", cast_type), # pyright: ignore[reportUnnecessaryCast] stream=stream, stream_cls=stream_cls, options=options, ) if bool(response.request.headers.get(RAW_RESPONSE_HEADER)): return cast(ResponseT, api_response) return api_response.parse() def _request_api_list( self, model: Type[object], page: Type[SyncPageT], options: FinalRequestOptions, ) -> SyncPageT: def _parser(resp: SyncPageT) -> SyncPageT: resp._set_private_attributes( client=self, model=model, options=options, ) return resp options.post_parser = _parser return self.request(page, options, stream=False) @overload def get( self, path: str, *, cast_type: Type[ResponseT], options: UserRequestInput = {}, stream: Literal[False] = False, ) -> ResponseT: ... @overload def get( self, path: str, *, cast_type: Type[ResponseT], options: UserRequestInput = {}, stream: Literal[True], stream_cls: Type[StreamResponse], ) -> StreamResponse: ... @overload def get( self, path: str, *, cast_type: Type[ResponseT], options: UserRequestInput = {}, stream: bool, stream_cls: Type[StreamResponse] | None = None, ) -> ResponseT | StreamResponse: ... def get( self, path: str, *, cast_type: Type[ResponseT], options: UserRequestInput = {}, stream: bool = False, stream_cls: Type[StreamResponse] | None = None, ) -> ResponseT: opts = FinalRequestOptions.construct(method="get", url=path, **options) return cast(ResponseT, self.request(cast_type, opts, stream=stream, stream_cls=stream_cls)) @overload def post( self, path: str, *, cast_type: Type[ResponseT], body: Body | None = None, options: UserRequestInput = {}, files: RequestFiles | None = None, stream: Literal[False] = False, ) -> ResponseT: ... @overload def post( self, path: str, *, cast_type: Type[ResponseT], body: Body | None = None, options: UserRequestInput = {}, files: RequestFiles | None = None, stream: Literal[True], stream_cls: Type[StreamResponse], ) -> StreamResponse: ... @overload def post( self, path: str, *, cast_type: Type[ResponseT], body: Body | None = None, options: UserRequestInput = {}, files: RequestFiles | None = None, stream: bool, stream_cls: Type[StreamResponse] | None = None, ) -> ResponseT | StreamResponse: ... def post( self, path: str, *, cast_type: Type[ResponseT], body: Body | None = None, options: UserRequestInput = {}, files: RequestFiles | None = None, stream: bool = False, stream_cls: Type[StreamResponse[Any]] | None = None, ) -> ResponseT | StreamResponse: opts = FinalRequestOptions.construct( method="post", url=path, json_data=body, files=to_httpx_files(files), **options ) return cast(ResponseT, self.request(cast_type, opts, stream=stream, stream_cls=stream_cls)) def patch( self, path: str, *, cast_type: Type[ResponseT], body: Body | None = None, options: UserRequestInput = {}, ) -> ResponseT: opts = FinalRequestOptions.construct(method="patch", url=path, json_data=body, **options) return self.request( cast_type=cast_type, options=opts, ) def put( self, path: str, *, cast_type: Type[ResponseT], body: Body | None = None, options: UserRequestInput = {}, files: RequestFiles | None = None, ) -> ResponseT | StreamResponse: opts = FinalRequestOptions.construct(method="put", url=path, json_data=body, files=to_httpx_files(files), **options) return self.request( cast_type=cast_type, options=opts, ) def delete( self, path: str, *, cast_type: Type[ResponseT], body: Body | None = None, options: UserRequestInput = {}, ) -> ResponseT | StreamResponse: opts = FinalRequestOptions.construct(method="delete", url=path, json_data=body, **options) return self.request( cast_type=cast_type, options=opts, ) def get_api_list( self, path: str, *, model: Type[object], page: Type[SyncPageT], body: Body | None = None, options: UserRequestInput = {}, method: str = "get", ) -> SyncPageT: opts = FinalRequestOptions.construct(method=method, url=path, json_data=body, **options) return self._request_api_list(model, page, opts) def _make_status_error(self, response) -> APIStatusError: response_text = response.text.strip() status_code = response.status_code error_msg = f"Error code: {status_code}, with error text {response_text}" if status_code == 400: return _errors.APIRequestFailedError(message=error_msg, response=response) elif status_code == 401: return _errors.APIAuthenticationError(message=error_msg, response=response) elif status_code == 429: return _errors.APIReachLimitError(message=error_msg, response=response) elif status_code == 500: return _errors.APIInternalError(message=error_msg, response=response) elif status_code == 503: return _errors.APIServerFlowExceedError(message=error_msg, response=response) return APIStatusError(message=error_msg, response=response) def make_request_options( *, query: Query | None = None, extra_headers: Headers | None = None, extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, post_parser: PostParser | NotGiven = NOT_GIVEN, ) -> UserRequestInput: """Create a dict of type RequestOptions without keys of NotGiven values.""" options: UserRequestInput = {} if extra_headers is not None: options["headers"] = extra_headers if extra_body is not None: options["extra_json"] = cast(AnyMapping, extra_body) if query is not None: options["params"] = query if extra_query is not None: options["params"] = {**options.get("params", {}), **extra_query} if not isinstance(timeout, NotGiven): options["timeout"] = timeout if is_given(post_parser): # internal options["post_parser"] = post_parser # type: ignore return options def _merge_mappings( obj1: Mapping[_T_co, Union[_T, Omit]], obj2: Mapping[_T_co, Union[_T, Omit]], ) -> Dict[_T_co, _T]: """Merge two mappings of the same type, removing any values that are instances of `Omit`. In cases with duplicate keys the second mapping takes precedence. """ merged = {**obj1, **obj2} return {key: value for key, value in merged.items() if not isinstance(value, Omit)} ================================================ FILE: zhipuai/core/_jwt_token.py ================================================ # -*- coding:utf-8 -*- import time import cachetools.func import jwt # 缓存时间 3分钟 CACHE_TTL_SECONDS = 3 * 60 # token 有效期比缓存时间 多30秒 API_TOKEN_TTL_SECONDS = CACHE_TTL_SECONDS + 30 @cachetools.func.ttl_cache(maxsize=10, ttl=CACHE_TTL_SECONDS) def generate_token(apikey: str): try: api_key, secret = apikey.split(".") except Exception as e: raise Exception("invalid api_key", e) payload = { "api_key": api_key, "exp": int(round(time.time() * 1000)) + API_TOKEN_TTL_SECONDS * 1000, "timestamp": int(round(time.time() * 1000)), } ret = jwt.encode( payload, secret, algorithm="HS256", headers={"alg": "HS256", "sign_type": "SIGN"}, ) return ret ================================================ FILE: zhipuai/core/_legacy_binary_response.py ================================================ from __future__ import annotations import httpx import os from typing import Iterator, AsyncIterator, Any class HttpxResponseContent: @property def content(self) -> bytes: raise NotImplementedError("This method is not implemented for this class.") @property def text(self) -> str: raise NotImplementedError("This method is not implemented for this class.") @property def encoding(self) -> str | None: raise NotImplementedError("This method is not implemented for this class.") @property def charset_encoding(self) -> str | None: raise NotImplementedError("This method is not implemented for this class.") def json(self, **kwargs: Any) -> Any: raise NotImplementedError("This method is not implemented for this class.") def read(self) -> bytes: raise NotImplementedError("This method is not implemented for this class.") def iter_bytes(self, chunk_size: int | None = None) -> Iterator[bytes]: raise NotImplementedError("This method is not implemented for this class.") def iter_text(self, chunk_size: int | None = None) -> Iterator[str]: raise NotImplementedError("This method is not implemented for this class.") def iter_lines(self) -> Iterator[str]: raise NotImplementedError("This method is not implemented for this class.") def iter_raw(self, chunk_size: int | None = None) -> Iterator[bytes]: raise NotImplementedError("This method is not implemented for this class.") def write_to_file( self, file: str | os.PathLike[str], ) -> None: raise NotImplementedError("This method is not implemented for this class.") def stream_to_file( self, file: str | os.PathLike[str], *, chunk_size: int | None = None, ) -> None: raise NotImplementedError("This method is not implemented for this class.") def close(self) -> None: raise NotImplementedError("This method is not implemented for this class.") async def aread(self) -> bytes: raise NotImplementedError("This method is not implemented for this class.") async def aiter_bytes(self, chunk_size: int | None = None) -> AsyncIterator[bytes]: raise NotImplementedError("This method is not implemented for this class.") async def aiter_text(self, chunk_size: int | None = None) -> AsyncIterator[str]: raise NotImplementedError("This method is not implemented for this class.") async def aiter_lines(self) -> AsyncIterator[str]: raise NotImplementedError("This method is not implemented for this class.") async def aiter_raw(self, chunk_size: int | None = None) -> AsyncIterator[bytes]: raise NotImplementedError("This method is not implemented for this class.") async def astream_to_file( self, file: str | os.PathLike[str], *, chunk_size: int | None = None, ) -> None: raise NotImplementedError("This method is not implemented for this class.") async def aclose(self) -> None: raise NotImplementedError("This method is not implemented for this class.") class HttpxBinaryResponseContent(HttpxResponseContent): response: httpx.Response def __init__(self, response: httpx.Response) -> None: self.response = response @property def content(self) -> bytes: return self.response.content @property def encoding(self) -> str | None: return self.response.encoding @property def charset_encoding(self) -> str | None: return self.response.charset_encoding def read(self) -> bytes: return self.response.read() def text(self) -> str: raise NotImplementedError("Not implemented for binary response content") def json(self, **kwargs: Any) -> Any: raise NotImplementedError("Not implemented for binary response content") def iter_text(self, chunk_size: int | None = None) -> Iterator[str]: raise NotImplementedError("Not implemented for binary response content") def iter_lines(self) -> Iterator[str]: raise NotImplementedError("Not implemented for binary response content") async def aiter_text(self, chunk_size: int | None = None) -> AsyncIterator[str]: raise NotImplementedError("Not implemented for binary response content") async def aiter_lines(self) -> AsyncIterator[str]: raise NotImplementedError("Not implemented for binary response content") def iter_bytes(self, chunk_size: int | None = None) -> Iterator[bytes]: return self.response.iter_bytes(chunk_size) def iter_raw(self, chunk_size: int | None = None) -> Iterator[bytes]: return self.response.iter_raw(chunk_size) def write_to_file( self, file: str | os.PathLike[str], ) -> None: """Write the output to the given file. Accepts a filename or any path-like object, e.g. pathlib.Path Note: if you want to stream the data to the file instead of writing all at once then you should use `.with_streaming_response` when making the API request, e.g. `client.with_streaming_response.foo().stream_to_file('my_filename.txt')` """ with open(file, mode="wb") as f: for data in self.response.iter_bytes(): f.write(data) def stream_to_file( self, file: str | os.PathLike[str], *, chunk_size: int | None = None, ) -> None: with open(file, mode="wb") as f: for data in self.response.iter_bytes(chunk_size): f.write(data) def close(self) -> None: return self.response.close() async def aread(self) -> bytes: return await self.response.aread() async def aiter_bytes(self, chunk_size: int | None = None) -> AsyncIterator[bytes]: return self.response.aiter_bytes(chunk_size) async def aiter_raw(self, chunk_size: int | None = None) -> AsyncIterator[bytes]: return self.response.aiter_raw(chunk_size) async def astream_to_file( self, file: str | os.PathLike[str], *, chunk_size: int | None = None, ) -> None: path = anyio.Path(file) async with await path.open(mode="wb") as f: async for data in self.response.aiter_bytes(chunk_size): await f.write(data) async def aclose(self) -> None: return await self.response.aclose() class HttpxTextBinaryResponseContent(HttpxBinaryResponseContent): response: httpx.Response @property def text(self) -> str: return self.response.text def json(self, **kwargs: Any) -> Any: return self.response.json(**kwargs) def iter_text(self, chunk_size: int | None = None) -> Iterator[str]: return self.response.iter_text(chunk_size) def iter_lines(self) -> Iterator[str]: return self.response.iter_lines() async def aiter_text(self, chunk_size: int | None = None) -> AsyncIterator[str]: return self.response.aiter_text(chunk_size) async def aiter_lines(self) -> AsyncIterator[str]: return self.response.aiter_lines() ================================================ FILE: zhipuai/core/_legacy_response.py ================================================ from __future__ import annotations import os import inspect import logging import datetime import functools from collections.abc import Iterator from typing import TYPE_CHECKING, Any, Union, Generic, TypeVar, Callable, cast, overload, AsyncIterator from typing_extensions import Awaitable, ParamSpec, override, deprecated, get_origin import anyio import httpx import pydantic from ._base_type import NoneType from ._utils import is_given, extract_type_arg, is_annotated_type from ._base_models import BaseModel, is_basemodel from ._constants import RAW_RESPONSE_HEADER from ._sse_client import StreamResponse, is_stream_class_type, extract_stream_chunk_type from ._errors import APIResponseValidationError from ._legacy_binary_response import HttpxBinaryResponseContent, HttpxTextBinaryResponseContent, HttpxResponseContent if TYPE_CHECKING: from ._request_opt import FinalRequestOptions from ._http_client import HttpClient P = ParamSpec("P") R = TypeVar("R") _T = TypeVar("_T") log: logging.Logger = logging.getLogger(__name__) class LegacyAPIResponse(Generic[R]): """This is a legacy class as it will be replaced by `APIResponse` and `AsyncAPIResponse` in the `_response.py` file in the next major release. For the sync client this will mostly be the same with the exception of `content` & `text` will be methods instead of properties. In the async client, all methods will be async. A migration script will be provided & the migration in general should be smooth. """ _cast_type: type[R] _client: "HttpClient" _parsed_by_type: dict[type[Any], Any] _stream: bool _stream_cls: type[StreamResponse[Any]] | None _options: FinalRequestOptions http_response: httpx.Response def __init__( self, *, raw: httpx.Response, cast_type: type[R], client: "HttpClient", stream: bool, stream_cls: type[StreamResponse[Any]] | None, options: FinalRequestOptions, ) -> None: self._cast_type = cast_type self._client = client self._parsed_by_type = {} self._stream = stream self._stream_cls = stream_cls self._options = options self.http_response = raw @property def request_id(self) -> str | None: return self.http_response.headers.get("x-request-id") # type: ignore[no-any-return] @overload def parse(self, *, to: type[_T]) -> _T: ... @overload def parse(self) -> R: ... def parse(self, *, to: type[_T] | None = None) -> R | _T: """Returns the rich python representation of this response's data. NOTE: For the async client: this will become a coroutine in the next major version. For lower-level control, see `.read()`, `.json()`, `.iter_bytes()`. You can customise the type that the response is parsed into through the `to` argument, e.g. ```py from zhipuai import BaseModel class MyModel(BaseModel): foo: str obj = response.parse(to=MyModel) print(obj.foo) ``` We support parsing: - `BaseModel` - `dict` - `list` - `Union` - `str` - `int` - `float` - `httpx.Response` """ cache_key = to if to is not None else self._cast_type cached = self._parsed_by_type.get(cache_key) if cached is not None: return cached # type: ignore[no-any-return] parsed = self._parse(to=to) if is_given(self._options.post_parser): parsed = self._options.post_parser(parsed) self._parsed_by_type[cache_key] = parsed return parsed @property def headers(self) -> httpx.Headers: return self.http_response.headers @property def http_request(self) -> httpx.Request: return self.http_response.request @property def status_code(self) -> int: return self.http_response.status_code @property def url(self) -> httpx.URL: return self.http_response.url @property def method(self) -> str: return self.http_request.method @property def content(self) -> bytes: """Return the binary response content. NOTE: this will be removed in favour of `.read()` in the next major version. """ return self.http_response.content @property def text(self) -> str: """Return the decoded response content. NOTE: this will be turned into a method in the next major version. """ return self.http_response.text @property def http_version(self) -> str: return self.http_response.http_version @property def is_closed(self) -> bool: return self.http_response.is_closed @property def elapsed(self) -> datetime.timedelta: """The time taken for the complete request/response cycle to complete.""" return self.http_response.elapsed def _parse(self, *, to: type[_T] | None = None) -> R | _T: # unwrap `Annotated[T, ...]` -> `T` if to and is_annotated_type(to): to = extract_type_arg(to, 0) if self._stream: if to: if not is_stream_class_type(to): raise TypeError(f"Expected custom parse type to be a subclass of {StreamResponse}") return cast( _T, to( cast_type=extract_stream_chunk_type( to, failure_message="Expected custom stream type to be passed with a type argument, e.g. StreamResponse[ChunkType]", ), response=self.http_response, client=cast(Any, self._client), ), ) if self._stream_cls: return cast( R, self._stream_cls( cast_type=extract_stream_chunk_type(self._stream_cls), response=self.http_response, client=cast(Any, self._client), ), ) stream_cls = cast("type[StreamResponse[Any]] | None", self._client._default_stream_cls) if stream_cls is None: raise MissingStreamClassError() return cast( R, stream_cls( cast_type=self._cast_type, response=self.http_response, client=cast(Any, self._client), ), ) cast_type = to if to is not None else self._cast_type # unwrap `Annotated[T, ...]` -> `T` if is_annotated_type(cast_type): cast_type = extract_type_arg(cast_type, 0) if cast_type is NoneType: return cast(R, None) response = self.http_response if cast_type == str: return cast(R, response.text) if cast_type == int: return cast(R, int(response.text)) if cast_type == float: return cast(R, float(response.text)) origin = get_origin(cast_type) or cast_type if inspect.isclass(origin) and issubclass(origin, HttpxResponseContent): # in the response, e.g. mime file *_, filename = response.headers.get("content-disposition", "").split("filename=") # 判断文件类型是jsonl类型的使用HttpxTextBinaryResponseContent if filename and filename.endswith(".jsonl"): return cast(R, HttpxTextBinaryResponseContent(response)) elif filename and filename.endswith(".xlsx"): return cast(R, HttpxTextBinaryResponseContent(response)) else: return cast(R, cast_type(response)) # type: ignore if origin == LegacyAPIResponse: raise RuntimeError("Unexpected state - cast_type is `APIResponse`") if inspect.isclass(origin) and issubclass(origin, httpx.Response): # Because of the invariance of our ResponseT TypeVar, users can subclass httpx.Response # and pass that class to our request functions. We cannot change the variance to be either # covariant or contravariant as that makes our usage of ResponseT illegal. We could construct # the response class ourselves but that is something that should be supported directly in httpx # as it would be easy to incorrectly construct the Response object due to the multitude of arguments. if cast_type != httpx.Response: raise ValueError(f"Subclasses of httpx.Response cannot be passed to `cast_type`") return cast(R, response) if inspect.isclass(origin) and not issubclass(origin, BaseModel) and issubclass(origin, pydantic.BaseModel): raise TypeError("Pydantic models must subclass our base model type, e.g. `from openai import BaseModel`") if ( cast_type is not object and not origin is list and not origin is dict and not origin is Union and not issubclass(origin, BaseModel) ): raise RuntimeError( f"Unsupported type, expected {cast_type} to be a subclass of {BaseModel}, {dict}, {list}, {Union}, {NoneType}, {str} or {httpx.Response}." ) # split is required to handle cases where additional information is included # in the response, e.g. application/json; charset=utf-8 content_type, *_ = response.headers.get("content-type", "*").split(";") if content_type != "application/json": if is_basemodel(cast_type): try: data = response.json() except Exception as exc: log.debug("Could not read JSON from response data due to %s - %s", type(exc), exc) else: return self._client._process_response_data( data=data, cast_type=cast_type, # type: ignore response=response, ) if self._client._strict_response_validation: raise APIResponseValidationError( response=response, message=f"Expected Content-Type response header to be `application/json` but received `{content_type}` instead.", json_data=response.text, ) # If the API responds with content that isn't JSON then we just return # the (decoded) text without performing any parsing so that you can still # handle the response however you need to. return response.text # type: ignore data = response.json() return self._client._process_response_data( data=data, cast_type=cast_type, # type: ignore response=response, ) @override def __repr__(self) -> str: return f"" class MissingStreamClassError(TypeError): def __init__(self) -> None: super().__init__( "The `stream` argument was set to `True` but the `stream_cls` argument was not given. See `openai._streaming` for reference", ) def to_raw_response_wrapper(func: Callable[P, R]) -> Callable[P, LegacyAPIResponse[R]]: """Higher order function that takes one of our bound API methods and wraps it to support returning the raw `APIResponse` object directly. """ @functools.wraps(func) def wrapped(*args: P.args, **kwargs: P.kwargs) -> LegacyAPIResponse[R]: extra_headers: dict[str, str] = {**(cast(Any, kwargs.get("extra_headers")) or {})} extra_headers[RAW_RESPONSE_HEADER] = "true" kwargs["extra_headers"] = extra_headers return cast(LegacyAPIResponse[R], func(*args, **kwargs)) return wrapped ================================================ FILE: zhipuai/core/_request_opt.py ================================================ from __future__ import annotations from typing import Union, Any, cast, TYPE_CHECKING from ._constants import RAW_RESPONSE_HEADER from ._utils import is_given from ._base_compat import ConfigDict, PYDANTIC_V2 import pydantic.generics from httpx import Timeout from typing_extensions import ( final, Unpack, ClassVar, TypedDict, Required, Callable ) from ._base_type import Body, NotGiven, Headers, HttpxRequestFiles, Query, AnyMapping from ._utils import remove_notgiven_indict, strip_not_given class UserRequestInput(TypedDict, total=False): headers: Headers max_retries: int timeout: float | Timeout | None params: Query extra_json: AnyMapping class FinalRequestOptionsInput(TypedDict, total=False): method: Required[str] url: Required[str] params: Query headers: Headers max_retries: int timeout: float | Timeout | None files: HttpxRequestFiles | None json_data: Body extra_json: AnyMapping @final class FinalRequestOptions(pydantic.BaseModel): method: str url: str params: Query = {} headers: Union[Headers, NotGiven] = NotGiven() max_retries: Union[int, NotGiven] = NotGiven() timeout: Union[float, Timeout, None, NotGiven] = NotGiven() files: Union[HttpxRequestFiles, None] = None idempotency_key: Union[str, None] = None post_parser: Union[Callable[[Any], Any], NotGiven] = NotGiven() # It should be noted that we cannot use `json` here as that would override # a BaseModel method in an incompatible fashion. json_data: Union[Body, None] = None extra_json: Union[AnyMapping, None] = None if PYDANTIC_V2: model_config: ClassVar[ConfigDict] = ConfigDict(arbitrary_types_allowed=True) else: class Config(pydantic.BaseConfig): # pyright: ignore[reportDeprecated] arbitrary_types_allowed: bool = True def get_max_retries(self, max_retries: int) -> int: if isinstance(self.max_retries, NotGiven): return max_retries return self.max_retries def _strip_raw_response_header(self) -> None: if not is_given(self.headers): return if self.headers.get(RAW_RESPONSE_HEADER): self.headers = {**self.headers} self.headers.pop(RAW_RESPONSE_HEADER) # override the `construct` method so that we can run custom transformations. # this is necessary as we don't want to do any actual runtime type checking # (which means we can't use validators) but we do want to ensure that `NotGiven` # values are not present # # type ignore required because we're adding explicit types to `**values` @classmethod def construct( # type: ignore cls, _fields_set: set[str] | None = None, **values: Unpack[UserRequestInput], ) -> FinalRequestOptions: kwargs: dict[str, Any] = { # we unconditionally call `strip_not_given` on any value # as it will just ignore any non-mapping types key: strip_not_given(value) for key, value in values.items() } if PYDANTIC_V2: return super().model_construct(_fields_set, **kwargs) return cast(FinalRequestOptions, super().construct(_fields_set, **kwargs)) # pyright: ignore[reportDeprecated] if not TYPE_CHECKING: # type checkers incorrectly complain about this assignment model_construct = construct ================================================ FILE: zhipuai/core/_response.py ================================================ from __future__ import annotations import datetime import inspect from typing import TypeVar, Generic, cast, Any, TYPE_CHECKING, Iterator, Union, overload import httpx import logging import pydantic from typing_extensions import ParamSpec, get_origin, get_args, override from ._base_type import NoneType from ._sse_client import StreamResponse, is_stream_class_type, extract_stream_chunk_type from ._base_models import is_basemodel, BaseModel from ._utils import is_annotated_type, extract_type_arg, extract_type_var_from_base, is_given from ._errors import ZhipuAIError, APIResponseValidationError if TYPE_CHECKING: from ._request_opt import FinalRequestOptions from ._http_client import HttpClient P = ParamSpec("P") R = TypeVar("R") _T = TypeVar("_T") _APIResponseT = TypeVar("_APIResponseT", bound="APIResponse[Any]") log: logging.Logger = logging.getLogger(__name__) class BaseAPIResponse(Generic[R]): _cast_type: type[R] _client: "HttpClient" _parsed_by_type: dict[type[Any], Any] _is_sse_stream: bool _stream_cls: type[StreamResponse[Any]] _options: FinalRequestOptions http_response: httpx.Response def __init__( self, *, raw: httpx.Response, cast_type: type[R], client: "HttpClient", stream: bool, stream_cls: type[StreamResponse[Any]] | None = None, options: FinalRequestOptions, ) -> None: self._cast_type = cast_type self._client = client self._parsed_by_type = {} self._is_sse_stream = stream self._stream_cls = stream_cls self._options = options self.http_response = raw def _parse(self, *, to: type[_T] | None = None) -> R | _T: # unwrap `Annotated[T, ...]` -> `T` if to and is_annotated_type(to): to = extract_type_arg(to, 0) if self._is_sse_stream: if to: if not is_stream_class_type(to): raise TypeError(f"Expected custom parse type to be a subclass of {StreamResponse}") return cast( _T, to( cast_type=extract_stream_chunk_type( to, failure_message="Expected custom stream type to be passed with a type argument, e.g. StreamResponse[ChunkType]", ), response=self.http_response, client=cast(Any, self._client), ), ) if self._stream_cls: return cast( R, self._stream_cls( cast_type=extract_stream_chunk_type(self._stream_cls), response=self.http_response, client=cast(Any, self._client), ), ) stream_cls = cast("type[Stream[Any]] | None", self._client._default_stream_cls) if stream_cls is None: raise MissingStreamClassError() return cast( R, stream_cls( cast_type=self._cast_type, response=self.http_response, client=cast(Any, self._client), ), ) cast_type = to if to is not None else self._cast_type # unwrap `Annotated[T, ...]` -> `T` if is_annotated_type(cast_type): cast_type = extract_type_arg(cast_type, 0) if cast_type is NoneType: return cast(R, None) response = self.http_response if cast_type == str: return cast(R, response.text) if cast_type == bytes: return cast(R, response.content) if cast_type == int: return cast(R, int(response.text)) if cast_type == float: return cast(R, float(response.text)) origin = get_origin(cast_type) or cast_type # handle the legacy binary response case if inspect.isclass(cast_type) and cast_type.__name__ == "HttpxBinaryResponseContent": return cast(R, cast_type(response)) # type: ignore if origin == APIResponse: raise RuntimeError("Unexpected state - cast_type is `APIResponse`") if inspect.isclass(origin) and issubclass(origin, httpx.Response): # Because of the invariance of our ResponseT TypeVar, users can subclass httpx.Response # and pass that class to our request functions. We cannot change the variance to be either # covariant or contravariant as that makes our usage of ResponseT illegal. We could construct # the response class ourselves but that is something that should be supported directly in httpx # as it would be easy to incorrectly construct the Response object due to the multitude of arguments. if cast_type != httpx.Response: raise ValueError(f"Subclasses of httpx.Response cannot be passed to `cast_type`") return cast(R, response) if inspect.isclass(origin) and not issubclass(origin, BaseModel) and issubclass(origin, pydantic.BaseModel): raise TypeError("Pydantic models must subclass our base model type, e.g. `from openai import BaseModel`") if ( cast_type is not object and not origin is list and not origin is dict and not origin is Union and not issubclass(origin, BaseModel) ): raise RuntimeError( f"Unsupported type, expected {cast_type} to be a subclass of {BaseModel}, {dict}, {list}, {Union}, {NoneType}, {str} or {httpx.Response}." ) # split is required to handle cases where additional information is included # in the response, e.g. application/json; charset=utf-8 content_type, *_ = response.headers.get("content-type", "*").split(";") if content_type != "application/json": if is_basemodel(cast_type): try: data = response.json() except Exception as exc: log.debug("Could not read JSON from response data due to %s - %s", type(exc), exc) else: return self._client._process_response_data( data=data, cast_type=cast_type, # type: ignore response=response, ) if self._client._strict_response_validation: raise APIResponseValidationError( response=response, message=f"Expected Content-Type response header to be `application/json` but received `{content_type}` instead.", json_data=response.text, ) # If the API responds with content that isn't JSON then we just return # the (decoded) text without performing any parsing so that you can still # handle the response however you need to. return response.text # type: ignore data = response.json() return self._client._process_response_data( data=data, cast_type=cast_type, # type: ignore response=response, ) @property def headers(self) -> httpx.Headers: return self.http_response.headers @property def http_request(self) -> httpx.Request: """Returns the httpx Request instance associated with the current response.""" return self.http_response.request @property def status_code(self) -> int: return self.http_response.status_code @property def url(self) -> httpx.URL: """Returns the URL for which the request was made.""" return self.http_response.url @property def method(self) -> str: return self.http_request.method @property def http_version(self) -> str: return self.http_response.http_version @property def elapsed(self) -> datetime.timedelta: """The time taken for the complete request/response cycle to complete.""" return self.http_response.elapsed @property def is_closed(self) -> bool: """Whether or not the response body has been closed. If this is False then there is response data that has not been read yet. You must either fully consume the response body or call `.close()` before discarding the response to prevent resource leaks. """ return self.http_response.is_closed @override def __repr__(self) -> str: return ( f"<{self.__class__.__name__} [{self.status_code} {self.http_response.reason_phrase}] type={self._cast_type}>" ) class APIResponse(BaseAPIResponse[R]): @property def request_id(self) -> str | None: return self.http_response.headers.get("x-request-id") # type: ignore[no-any-return] @overload def parse(self, *, to: type[_T]) -> _T: ... @overload def parse(self) -> R: ... def parse(self, *, to: type[_T] | None = None) -> R | _T: """Returns the rich python representation of this response's data. For lower-level control, see `.read()`, `.json()`, `.iter_bytes()`. You can customise the type that the response is parsed into through the `to` argument, e.g. ```py from openai import BaseModel class MyModel(BaseModel): foo: str obj = response.parse(to=MyModel) print(obj.foo) ``` We support parsing: - `BaseModel` - `dict` - `list` - `Union` - `str` - `int` - `float` - `httpx.Response` """ cache_key = to if to is not None else self._cast_type cached = self._parsed_by_type.get(cache_key) if cached is not None: return cached # type: ignore[no-any-return] if not self._is_sse_stream: self.read() parsed = self._parse(to=to) if is_given(self._options.post_parser): parsed = self._options.post_parser(parsed) self._parsed_by_type[cache_key] = parsed return parsed def read(self) -> bytes: """Read and return the binary response content.""" try: return self.http_response.read() except httpx.StreamConsumed as exc: # The default error raised by httpx isn't very # helpful in our case so we re-raise it with # a different error message. raise StreamAlreadyConsumed() from exc def text(self) -> str: """Read and decode the response content into a string.""" self.read() return self.http_response.text def json(self) -> object: """Read and decode the JSON response content.""" self.read() return self.http_response.json() def close(self) -> None: """Close the response and release the connection. Automatically called if the response body is read to completion. """ self.http_response.close() def iter_bytes(self, chunk_size: int | None = None) -> Iterator[bytes]: """ A byte-iterator over the decoded response content. This automatically handles gzip, deflate and brotli encoded responses. """ for chunk in self.http_response.iter_bytes(chunk_size): yield chunk def iter_text(self, chunk_size: int | None = None) -> Iterator[str]: """A str-iterator over the decoded response content that handles both gzip, deflate, etc but also detects the content's string encoding. """ for chunk in self.http_response.iter_text(chunk_size): yield chunk def iter_lines(self) -> Iterator[str]: """Like `iter_text()` but will only yield chunks for each line""" for chunk in self.http_response.iter_lines(): yield chunk class MissingStreamClassError(TypeError): def __init__(self) -> None: super().__init__( "The `stream` argument was set to `True` but the `stream_cls` argument was not given. See `openai._streaming` for reference", ) class StreamAlreadyConsumed(ZhipuAIError): """ Attempted to read or stream content, but the content has already been streamed. This can happen if you use a method like `.iter_lines()` and then attempt to read th entire response body afterwards, e.g. ```py response = await client.post(...) async for line in response.iter_lines(): ... # do something with `line` content = await response.read() # ^ error ``` If you want this behaviour you'll need to either manually accumulate the response content or call `await response.read()` before iterating over the stream. """ def __init__(self) -> None: message = ( "Attempted to read or stream some content, but the content has " "already been streamed. " "This could be due to attempting to stream the response " "content more than once." "\n\n" "You can fix this by manually accumulating the response content while streaming " "or by calling `.read()` before starting to stream." ) super().__init__(message) def extract_response_type(typ: type[BaseAPIResponse[Any]]) -> type: """Given a type like `APIResponse[T]`, returns the generic type variable `T`. This also handles the case where a concrete subclass is given, e.g. ```py class MyResponse(APIResponse[bytes]): ... extract_response_type(MyResponse) -> bytes ``` """ return extract_type_var_from_base( typ, generic_bases=cast("tuple[type, ...]", (BaseAPIResponse, APIResponse)), index=0, ) ================================================ FILE: zhipuai/core/_sse_client.py ================================================ # -*- coding:utf-8 -*- from __future__ import annotations import inspect import json from typing import TYPE_CHECKING, Generic, Iterator, Mapping, Type, cast import httpx from typing_extensions import TypeGuard from . import get_origin from ._base_type import ResponseT from ._errors import APIResponseError from ._utils import extract_type_var_from_base, is_mapping _FIELD_SEPARATOR = ':' if TYPE_CHECKING: from ._http_client import HttpClient class StreamResponse(Generic[ResponseT]): response: httpx.Response _cast_type: Type[ResponseT] def __init__( self, *, cast_type: Type[ResponseT], response: httpx.Response, client: HttpClient, ) -> None: self.response = response self._cast_type = cast_type self._data_process_func = client._process_response_data self._stream_chunks = self.__stream__() def __next__(self) -> ResponseT: return self._stream_chunks.__next__() def __iter__(self) -> Iterator[ResponseT]: for item in self._stream_chunks: yield item def __stream__(self) -> Iterator[ResponseT]: sse_line_parser = SSELineParser() iterator = sse_line_parser.iter_lines(self.response.iter_lines()) for sse in iterator: if sse.data.startswith('[DONE]'): break if sse.event is None: data = sse.json_data() if isinstance(data, Mapping) and data.get('agent_id'): yield self._data_process_func( data=data, cast_type=self._cast_type, response=self.response, ) continue if isinstance(data, Mapping) and data.get('error'): raise APIResponseError( message='An error occurred during streaming', request=self.response.request, json_data=data['error'], ) if sse.event is None: data = sse.json_data() if is_mapping(data) and data.get('error'): message = None error = data.get('error') if is_mapping(error): message = error.get('message') if not message or not isinstance(message, str): message = 'An error occurred during streaming' raise APIResponseError( message=message, request=self.response.request, json_data=data['error'], ) yield self._data_process_func( data=data, cast_type=self._cast_type, response=self.response ) else: data = sse.json_data() if ( sse.event == 'error' and is_mapping(data) and data.get('error') ): message = None error = data.get('error') if is_mapping(error): message = error.get('message') if not message or not isinstance(message, str): message = 'An error occurred during streaming' raise APIResponseError( message=message, request=self.response.request, json_data=data['error'], ) yield self._data_process_func( data=data, cast_type=self._cast_type, response=self.response ) for sse in iterator: pass class Event(object): def __init__( self, event: str | None = None, data: str | None = None, id: str | None = None, retry: int | None = None, ): self._event = event self._data = data self._id = id self._retry = retry def __repr__(self): data_len = len(self._data) if self._data else 0 return f'Event(event={self._event}, data={self._data} ,data_length={data_len}, id={self._id}, retry={self._retry}' @property def event(self): return self._event @property def data(self): return self._data def json_data(self): return json.loads(self._data) @property def id(self): return self._id @property def retry(self): return self._retry class SSELineParser: _data: list[str] _event: str | None _retry: int | None _id: str | None def __init__(self): self._event = None self._data = [] self._id = None self._retry = None def iter_lines(self, lines: Iterator[str]) -> Iterator[Event]: for line in lines: line = line.rstrip('\n') if not line: if ( self._event is None and not self._data and self._id is None and self._retry is None ): continue sse_event = Event( event=self._event, data='\n'.join(self._data), id=self._id, retry=self._retry, ) self._event = None self._data = [] self._id = None self._retry = None yield sse_event self.decode_line(line) def decode_line(self, line: str): if line.startswith(':') or not line: return field, _p, value = line.partition(':') if value.startswith(' '): value = value[1:] if field == 'data': self._data.append(value) elif field == 'event': self._event = value elif field == 'retry': try: self._retry = int(value) except (TypeError, ValueError): pass return def is_stream_class_type(typ: type) -> TypeGuard[type[StreamResponse[object]]]: """TypeGuard for determining whether or not the given type is a subclass of `Stream` / `AsyncStream`""" origin = get_origin(typ) or typ return inspect.isclass(origin) and issubclass(origin, StreamResponse) def extract_stream_chunk_type( stream_cls: type, *, failure_message: str | None = None, ) -> type: """Given a type like `StreamResponse[T]`, returns the generic type variable `T`. This also handles the case where a concrete subclass is given, e.g. ```py class MyStream(StreamResponse[bytes]): ... extract_stream_chunk_type(MyStream) -> bytes ``` """ return extract_type_var_from_base( stream_cls, index=0, generic_bases=cast('tuple[type, ...]', (StreamResponse,)), failure_message=failure_message, ) ================================================ FILE: zhipuai/core/_utils/__init__.py ================================================ from ._utils import ( remove_notgiven_indict as remove_notgiven_indict, flatten as flatten, is_dict as is_dict, is_list as is_list, is_given as is_given, is_tuple as is_tuple, is_mapping as is_mapping, is_tuple_t as is_tuple_t, parse_date as parse_date, is_iterable as is_iterable, is_sequence as is_sequence, coerce_float as coerce_float, is_mapping_t as is_mapping_t, removeprefix as removeprefix, removesuffix as removesuffix, extract_files as extract_files, is_sequence_t as is_sequence_t, required_args as required_args, coerce_boolean as coerce_boolean, coerce_integer as coerce_integer, file_from_path as file_from_path, parse_datetime as parse_datetime, strip_not_given as strip_not_given, deepcopy_minimal as deepcopy_minimal, get_async_library as get_async_library, maybe_coerce_float as maybe_coerce_float, get_required_header as get_required_header, maybe_coerce_boolean as maybe_coerce_boolean, maybe_coerce_integer as maybe_coerce_integer, drop_prefix_image_data as drop_prefix_image_data, ) from ._typing import ( is_list_type as is_list_type, is_union_type as is_union_type, extract_type_arg as extract_type_arg, is_iterable_type as is_iterable_type, is_required_type as is_required_type, is_annotated_type as is_annotated_type, strip_annotated_type as strip_annotated_type, extract_type_var_from_base as extract_type_var_from_base, ) from ._transform import ( PropertyInfo as PropertyInfo, transform as transform, async_transform as async_transform, maybe_transform as maybe_transform, async_maybe_transform as async_maybe_transform, ) ================================================ FILE: zhipuai/core/_utils/_transform.py ================================================ from __future__ import annotations import io import base64 import pathlib from typing import Any, Mapping, TypeVar, cast from datetime import date, datetime from typing_extensions import Literal, get_args, override, get_type_hints import anyio import pydantic from ._utils import ( is_list, is_mapping, is_iterable, ) from .._files import is_base64_file_input from ._typing import ( is_list_type, is_union_type, extract_type_arg, is_iterable_type, is_required_type, is_annotated_type, strip_annotated_type, ) from .._base_compat import model_dump, is_typeddict _T = TypeVar("_T") # TODO: support for drilling globals() and locals() # TODO: ensure works correctly with forward references in all cases PropertyFormat = Literal["iso8601", "base64", "custom"] class PropertyInfo: """Metadata class to be used in Annotated types to provide information about a given type. For example: class MyParams(TypedDict): account_holder_name: Annotated[str, PropertyInfo(alias='accountHolderName')] This means that {'account_holder_name': 'Robert'} will be transformed to {'accountHolderName': 'Robert'} before being sent to the API. """ alias: str | None format: PropertyFormat | None format_template: str | None discriminator: str | None def __init__( self, *, alias: str | None = None, format: PropertyFormat | None = None, format_template: str | None = None, discriminator: str | None = None, ) -> None: self.alias = alias self.format = format self.format_template = format_template self.discriminator = discriminator @override def __repr__(self) -> str: return f"{self.__class__.__name__}(alias='{self.alias}', format={self.format}, format_template='{self.format_template}', discriminator='{self.discriminator}')" def maybe_transform( data: object, expected_type: object, ) -> Any | None: """Wrapper over `transform()` that allows `None` to be passed. See `transform()` for more details. """ if data is None: return None return transform(data, expected_type) # Wrapper over _transform_recursive providing fake types def transform( data: _T, expected_type: object, ) -> _T: """Transform dictionaries based off of type information from the given type, for example: ```py class Params(TypedDict, total=False): card_id: Required[Annotated[str, PropertyInfo(alias="cardID")]] transformed = transform({"card_id": ""}, Params) # {'cardID': ''} ``` Any keys / data that does not have type information given will be included as is. It should be noted that the transformations that this function does are not represented in the type system. """ transformed = _transform_recursive(data, annotation=cast(type, expected_type)) return cast(_T, transformed) def _get_annotated_type(type_: type) -> type | None: """If the given type is an `Annotated` type then it is returned, if not `None` is returned. This also unwraps the type when applicable, e.g. `Required[Annotated[T, ...]]` """ if is_required_type(type_): # Unwrap `Required[Annotated[T, ...]]` to `Annotated[T, ...]` type_ = get_args(type_)[0] if is_annotated_type(type_): return type_ return None def _maybe_transform_key(key: str, type_: type) -> str: """Transform the given `data` based on the annotations provided in `type_`. Note: this function only looks at `Annotated` types that contain `PropertInfo` metadata. """ annotated_type = _get_annotated_type(type_) if annotated_type is None: # no `Annotated` definition for this type, no transformation needed return key # ignore the first argument as it is the actual type annotations = get_args(annotated_type)[1:] for annotation in annotations: if isinstance(annotation, PropertyInfo) and annotation.alias is not None: return annotation.alias return key def _transform_recursive( data: object, *, annotation: type, inner_type: type | None = None, ) -> object: """Transform the given data against the expected type. Args: annotation: The direct type annotation given to the particular piece of data. This may or may not be wrapped in metadata types, e.g. `Required[T]`, `Annotated[T, ...]` etc inner_type: If applicable, this is the "inside" type. This is useful in certain cases where the outside type is a container type such as `List[T]`. In that case `inner_type` should be set to `T` so that each entry in the list can be transformed using the metadata from the container type. Defaults to the same value as the `annotation` argument. """ if inner_type is None: inner_type = annotation stripped_type = strip_annotated_type(inner_type) if is_typeddict(stripped_type) and is_mapping(data): return _transform_typeddict(data, stripped_type) if ( # List[T] (is_list_type(stripped_type) and is_list(data)) # Iterable[T] or (is_iterable_type(stripped_type) and is_iterable(data) and not isinstance(data, str)) ): inner_type = extract_type_arg(stripped_type, 0) return [_transform_recursive(d, annotation=annotation, inner_type=inner_type) for d in data] if is_union_type(stripped_type): # For union types we run the transformation against all subtypes to ensure that everything is transformed. # # TODO: there may be edge cases where the same normalized field name will transform to two different names # in different subtypes. for subtype in get_args(stripped_type): data = _transform_recursive(data, annotation=annotation, inner_type=subtype) return data if isinstance(data, pydantic.BaseModel): return model_dump(data, exclude_unset=True) annotated_type = _get_annotated_type(annotation) if annotated_type is None: return data # ignore the first argument as it is the actual type annotations = get_args(annotated_type)[1:] for annotation in annotations: if isinstance(annotation, PropertyInfo) and annotation.format is not None: return _format_data(data, annotation.format, annotation.format_template) return data def _format_data(data: object, format_: PropertyFormat, format_template: str | None) -> object: if isinstance(data, (date, datetime)): if format_ == "iso8601": return data.isoformat() if format_ == "custom" and format_template is not None: return data.strftime(format_template) if format_ == "base64" and is_base64_file_input(data): binary: str | bytes | None = None if isinstance(data, pathlib.Path): binary = data.read_bytes() elif isinstance(data, io.IOBase): binary = data.read() if isinstance(binary, str): # type: ignore[unreachable] binary = binary.encode() if not isinstance(binary, bytes): raise RuntimeError(f"Could not read bytes from {data}; Received {type(binary)}") return base64.b64encode(binary).decode("ascii") return data def _transform_typeddict( data: Mapping[str, object], expected_type: type, ) -> Mapping[str, object]: result: dict[str, object] = {} annotations = get_type_hints(expected_type, include_extras=True) for key, value in data.items(): type_ = annotations.get(key) if type_ is None: # we do not have a type annotation for this field, leave it as is result[key] = value else: result[_maybe_transform_key(key, type_)] = _transform_recursive(value, annotation=type_) return result async def async_maybe_transform( data: object, expected_type: object, ) -> Any | None: """Wrapper over `async_transform()` that allows `None` to be passed. See `async_transform()` for more details. """ if data is None: return None return await async_transform(data, expected_type) async def async_transform( data: _T, expected_type: object, ) -> _T: """Transform dictionaries based off of type information from the given type, for example: ```py class Params(TypedDict, total=False): card_id: Required[Annotated[str, PropertyInfo(alias="cardID")]] transformed = transform({"card_id": ""}, Params) # {'cardID': ''} ``` Any keys / data that does not have type information given will be included as is. It should be noted that the transformations that this function does are not represented in the type system. """ transformed = await _async_transform_recursive(data, annotation=cast(type, expected_type)) return cast(_T, transformed) async def _async_transform_recursive( data: object, *, annotation: type, inner_type: type | None = None, ) -> object: """Transform the given data against the expected type. Args: annotation: The direct type annotation given to the particular piece of data. This may or may not be wrapped in metadata types, e.g. `Required[T]`, `Annotated[T, ...]` etc inner_type: If applicable, this is the "inside" type. This is useful in certain cases where the outside type is a container type such as `List[T]`. In that case `inner_type` should be set to `T` so that each entry in the list can be transformed using the metadata from the container type. Defaults to the same value as the `annotation` argument. """ if inner_type is None: inner_type = annotation stripped_type = strip_annotated_type(inner_type) if is_typeddict(stripped_type) and is_mapping(data): return await _async_transform_typeddict(data, stripped_type) if ( # List[T] (is_list_type(stripped_type) and is_list(data)) # Iterable[T] or (is_iterable_type(stripped_type) and is_iterable(data) and not isinstance(data, str)) ): inner_type = extract_type_arg(stripped_type, 0) return [await _async_transform_recursive(d, annotation=annotation, inner_type=inner_type) for d in data] if is_union_type(stripped_type): # For union types we run the transformation against all subtypes to ensure that everything is transformed. # # TODO: there may be edge cases where the same normalized field name will transform to two different names # in different subtypes. for subtype in get_args(stripped_type): data = await _async_transform_recursive(data, annotation=annotation, inner_type=subtype) return data if isinstance(data, pydantic.BaseModel): return model_dump(data, exclude_unset=True) annotated_type = _get_annotated_type(annotation) if annotated_type is None: return data # ignore the first argument as it is the actual type annotations = get_args(annotated_type)[1:] for annotation in annotations: if isinstance(annotation, PropertyInfo) and annotation.format is not None: return await _async_format_data(data, annotation.format, annotation.format_template) return data async def _async_format_data(data: object, format_: PropertyFormat, format_template: str | None) -> object: if isinstance(data, (date, datetime)): if format_ == "iso8601": return data.isoformat() if format_ == "custom" and format_template is not None: return data.strftime(format_template) if format_ == "base64" and is_base64_file_input(data): binary: str | bytes | None = None if isinstance(data, pathlib.Path): binary = await anyio.Path(data).read_bytes() elif isinstance(data, io.IOBase): binary = data.read() if isinstance(binary, str): # type: ignore[unreachable] binary = binary.encode() if not isinstance(binary, bytes): raise RuntimeError(f"Could not read bytes from {data}; Received {type(binary)}") return base64.b64encode(binary).decode("ascii") return data async def _async_transform_typeddict( data: Mapping[str, object], expected_type: type, ) -> Mapping[str, object]: result: dict[str, object] = {} annotations = get_type_hints(expected_type, include_extras=True) for key, value in data.items(): type_ = annotations.get(key) if type_ is None: # we do not have a type annotation for this field, leave it as is result[key] = value else: result[_maybe_transform_key(key, type_)] = await _async_transform_recursive(value, annotation=type_) return result ================================================ FILE: zhipuai/core/_utils/_typing.py ================================================ from __future__ import annotations from typing import Any, TypeVar, Iterable, cast from collections import abc as _c_abc from typing_extensions import Required, Annotated, get_args, get_origin from .._base_type import InheritsGeneric from zhipuai.core._base_compat import is_union as _is_union def is_annotated_type(typ: type) -> bool: return get_origin(typ) == Annotated def is_list_type(typ: type) -> bool: return (get_origin(typ) or typ) == list def is_iterable_type(typ: type) -> bool: """If the given type is `typing.Iterable[T]`""" origin = get_origin(typ) or typ return origin == Iterable or origin == _c_abc.Iterable def is_union_type(typ: type) -> bool: return _is_union(get_origin(typ)) def is_required_type(typ: type) -> bool: return get_origin(typ) == Required def is_typevar(typ: type) -> bool: # type ignore is required because type checkers # think this expression will always return False return type(typ) == TypeVar # type: ignore # Extracts T from Annotated[T, ...] or from Required[Annotated[T, ...]] def strip_annotated_type(typ: type) -> type: if is_required_type(typ) or is_annotated_type(typ): return strip_annotated_type(cast(type, get_args(typ)[0])) return typ def extract_type_arg(typ: type, index: int) -> type: args = get_args(typ) try: return cast(type, args[index]) except IndexError as err: raise RuntimeError(f"Expected type {typ} to have a type argument at index {index} but it did not") from err def extract_type_var_from_base( typ: type, *, generic_bases: tuple[type, ...], index: int, failure_message: str | None = None, ) -> type: """Given a type like `Foo[T]`, returns the generic type variable `T`. This also handles the case where a concrete subclass is given, e.g. ```py class MyResponse(Foo[bytes]): ... extract_type_var(MyResponse, bases=(Foo,), index=0) -> bytes ``` And where a generic subclass is given: ```py _T = TypeVar('_T') class MyResponse(Foo[_T]): ... extract_type_var(MyResponse[bytes], bases=(Foo,), index=0) -> bytes ``` """ cls = cast(object, get_origin(typ) or typ) if cls in generic_bases: # we're given the class directly return extract_type_arg(typ, index) # if a subclass is given # --- # this is needed as __orig_bases__ is not present in the typeshed stubs # because it is intended to be for internal use only, however there does # not seem to be a way to resolve generic TypeVars for inherited subclasses # without using it. if isinstance(cls, InheritsGeneric): target_base_class: Any | None = None for base in cls.__orig_bases__: if base.__origin__ in generic_bases: target_base_class = base break if target_base_class is None: raise RuntimeError( "Could not find the generic base class;\n" "This should never happen;\n" f"Does {cls} inherit from one of {generic_bases} ?" ) extracted = extract_type_arg(target_base_class, index) if is_typevar(extracted): # If the extracted type argument is itself a type variable # then that means the subclass itself is generic, so we have # to resolve the type argument from the class itself, not # the base class. # # Note: if there is more than 1 type argument, the subclass could # change the ordering of the type arguments, this is not currently # supported. return extract_type_arg(typ, index) return extracted raise RuntimeError(failure_message or f"Could not resolve inner type variable at index {index} for {typ}") ================================================ FILE: zhipuai/core/_utils/_utils.py ================================================ from __future__ import annotations import os import re import inspect import functools from typing import ( Any, Tuple, Mapping, TypeVar, Callable, Iterable, Sequence, cast, overload, List, Union, ) from pathlib import Path from typing_extensions import TypeGuard import sniffio from .._base_type import Headers, NotGiven, FileTypes, NotGivenOr, HeadersLike from .._base_compat import parse_date as parse_date, parse_datetime as parse_datetime def remove_notgiven_indict(obj): if obj is None or (not isinstance(obj, Mapping)): return obj return {key: value for key, value in obj.items() if not isinstance(value, NotGiven)} _T = TypeVar("_T") _TupleT = TypeVar("_TupleT", bound=Tuple[object, ...]) _MappingT = TypeVar("_MappingT", bound=Mapping[str, object]) _SequenceT = TypeVar("_SequenceT", bound=Sequence[object]) CallableT = TypeVar("CallableT", bound=Callable[..., Any]) def flatten(t: Iterable[Iterable[_T]]) -> list[_T]: return [item for sublist in t for item in sublist] def extract_files( # TODO: this needs to take Dict but variance issues..... # create protocol type ? query: Mapping[str, object], *, paths: Sequence[Sequence[str]], ) -> list[tuple[str, FileTypes]]: """Recursively extract files from the given dictionary based on specified paths. A path may look like this ['foo', 'files', '', 'data']. Note: this mutates the given dictionary. """ files: list[tuple[str, FileTypes]] = [] for path in paths: files.extend(_extract_items(query, path, index=0, flattened_key=None)) return files def _extract_items( obj: object, path: Sequence[str], *, index: int, flattened_key: str | None, ) -> list[tuple[str, FileTypes]]: try: key = path[index] except IndexError: if isinstance(obj, NotGiven): # no value was provided - we can safely ignore return [] # cyclical import from .._files import assert_is_file_content # We have exhausted the path, return the entry we found. assert_is_file_content(obj, key=flattened_key) assert flattened_key is not None return [(flattened_key, cast(FileTypes, obj))] index += 1 if is_dict(obj): try: # We are at the last entry in the path so we must remove the field if (len(path)) == index: item = obj.pop(key) else: item = obj[key] except KeyError: # Key was not present in the dictionary, this is not indicative of an error # as the given path may not point to a required field. We also do not want # to enforce required fields as the API may differ from the spec in some cases. return [] if flattened_key is None: flattened_key = key else: flattened_key += f"[{key}]" return _extract_items( item, path, index=index, flattened_key=flattened_key, ) elif is_list(obj): if key != "": return [] return flatten( [ _extract_items( item, path, index=index, flattened_key=flattened_key + "[]" if flattened_key is not None else "[]", ) for item in obj ] ) # Something unexpected was passed, just ignore it. return [] def is_given(obj: NotGivenOr[_T]) -> TypeGuard[_T]: return not isinstance(obj, NotGiven) # Type safe methods for narrowing types with TypeVars. # The default narrowing for isinstance(obj, dict) is dict[unknown, unknown], # however this cause Pyright to rightfully report errors. As we know we don't # care about the contained types we can safely use `object` in it's place. # # There are two separate functions defined, `is_*` and `is_*_t` for different use cases. # `is_*` is for when you're dealing with an unknown input # `is_*_t` is for when you're narrowing a known union type to a specific subset def is_tuple(obj: object) -> TypeGuard[tuple[object, ...]]: return isinstance(obj, tuple) def is_tuple_t(obj: _TupleT | object) -> TypeGuard[_TupleT]: return isinstance(obj, tuple) def is_sequence(obj: object) -> TypeGuard[Sequence[object]]: return isinstance(obj, Sequence) def is_sequence_t(obj: _SequenceT | object) -> TypeGuard[_SequenceT]: return isinstance(obj, Sequence) def is_mapping(obj: object) -> TypeGuard[Mapping[str, object]]: return isinstance(obj, Mapping) def is_mapping_t(obj: _MappingT | object) -> TypeGuard[_MappingT]: return isinstance(obj, Mapping) def is_dict(obj: object) -> TypeGuard[dict[object, object]]: return isinstance(obj, dict) def is_list(obj: object) -> TypeGuard[list[object]]: return isinstance(obj, list) def is_iterable(obj: object) -> TypeGuard[Iterable[object]]: return isinstance(obj, Iterable) def deepcopy_minimal(item: _T) -> _T: """Minimal reimplementation of copy.deepcopy() that will only copy certain object types: - mappings, e.g. `dict` - list This is done for performance reasons. """ if is_mapping(item): return cast(_T, {k: deepcopy_minimal(v) for k, v in item.items()}) if is_list(item): return cast(_T, [deepcopy_minimal(entry) for entry in item]) return item # copied from https://github.com/Rapptz/RoboDanny def human_join(seq: Sequence[str], *, delim: str = ", ", final: str = "or") -> str: size = len(seq) if size == 0: return "" if size == 1: return seq[0] if size == 2: return f"{seq[0]} {final} {seq[1]}" return delim.join(seq[:-1]) + f" {final} {seq[-1]}" def quote(string: str) -> str: """Add single quotation marks around the given string. Does *not* do any escaping.""" return f"'{string}'" def required_args(*variants: Sequence[str]) -> Callable[[CallableT], CallableT]: """Decorator to enforce a given set of arguments or variants of arguments are passed to the decorated function. Useful for enforcing runtime validation of overloaded functions. Example usage: ```py @overload def foo(*, a: str) -> str: ... @overload def foo(*, b: bool) -> str: ... # This enforces the same constraints that a static type checker would # i.e. that either a or b must be passed to the function @required_args(["a"], ["b"]) def foo(*, a: str | None = None, b: bool | None = None) -> str: ... ``` """ def inner(func: CallableT) -> CallableT: params = inspect.signature(func).parameters positional = [ name for name, param in params.items() if param.kind in { param.POSITIONAL_ONLY, param.POSITIONAL_OR_KEYWORD, } ] @functools.wraps(func) def wrapper(*args: object, **kwargs: object) -> object: given_params: set[str] = set() for i, _ in enumerate(args): try: given_params.add(positional[i]) except IndexError: raise TypeError( f"{func.__name__}() takes {len(positional)} argument(s) but {len(args)} were given" ) from None for key in kwargs.keys(): given_params.add(key) for variant in variants: matches = all((param in given_params for param in variant)) if matches: break else: # no break if len(variants) > 1: variations = human_join( ["(" + human_join([quote(arg) for arg in variant], final="and") + ")" for variant in variants] ) msg = f"Missing required arguments; Expected either {variations} arguments to be given" else: # TODO: this error message is not deterministic missing = list(set(variants[0]) - given_params) if len(missing) > 1: msg = f"Missing required arguments: {human_join([quote(arg) for arg in missing])}" else: msg = f"Missing required argument: {quote(missing[0])}" raise TypeError(msg) return func(*args, **kwargs) return wrapper # type: ignore return inner _K = TypeVar("_K") _V = TypeVar("_V") @overload def strip_not_given(obj: None) -> None: ... @overload def strip_not_given(obj: Mapping[_K, _V | NotGiven]) -> dict[_K, _V]: ... @overload def strip_not_given(obj: object) -> object: ... def strip_not_given(obj: object | None) -> object: """Remove all top-level keys where their values are instances of `NotGiven`""" if obj is None: return None if not is_mapping(obj): return obj return {key: value for key, value in obj.items() if not isinstance(value, NotGiven)} def coerce_integer(val: str) -> int: return int(val, base=10) def coerce_float(val: str) -> float: return float(val) def coerce_boolean(val: str) -> bool: return val == "true" or val == "1" or val == "on" def maybe_coerce_integer(val: str | None) -> int | None: if val is None: return None return coerce_integer(val) def maybe_coerce_float(val: str | None) -> float | None: if val is None: return None return coerce_float(val) def maybe_coerce_boolean(val: str | None) -> bool | None: if val is None: return None return coerce_boolean(val) def removeprefix(string: str, prefix: str) -> str: """Remove a prefix from a string. Backport of `str.removeprefix` for Python < 3.9 """ if string.startswith(prefix): return string[len(prefix):] return string def removesuffix(string: str, suffix: str) -> str: """Remove a suffix from a string. Backport of `str.removesuffix` for Python < 3.9 """ if string.endswith(suffix): return string[: -len(suffix)] return string def file_from_path(path: str) -> FileTypes: contents = Path(path).read_bytes() file_name = os.path.basename(path) return (file_name, contents) def get_required_header(headers: HeadersLike, header: str) -> str: lower_header = header.lower() if isinstance(headers, Mapping): headers = cast(Headers, headers) for k, v in headers.items(): if k.lower() == lower_header and isinstance(v, str): return v """ to deal with the case where the header looks like Stainless-Event-Id """ intercaps_header = re.sub(r"([^\w])(\w)", lambda pat: pat.group(1) + pat.group(2).upper(), header.capitalize()) for normalized_header in [header, lower_header, header.upper(), intercaps_header]: value = headers.get(normalized_header) if value: return value raise ValueError(f"Could not find {header} header") def get_async_library() -> str: try: return sniffio.current_async_library() except Exception: return "false" def drop_prefix_image_data(content: Union[str, List[dict]]) -> Union[str, List[dict]]: """ 删除 ;base64, 前缀 :param image_data: :return: """ if isinstance(content, List): for data in content: if data.get('type') == 'image_url': image_data = data.get("image_url").get("url") if image_data.startswith("data:image/"): image_data = image_data.split("base64,")[-1] data["image_url"]["url"] = image_data return content ================================================ FILE: zhipuai/core/logs.py ================================================ import logging import os import time logger = logging.getLogger(__name__) class LoggerNameFilter(logging.Filter): def filter(self, record): # return record.name.startswith("loom_core") or record.name in "ERROR" or ( # record.name.startswith("uvicorn.error") # and record.getMessage().startswith("Uvicorn running on") # ) return True def get_log_file(log_path: str, sub_dir: str): """ sub_dir should contain a timestamp. """ log_dir = os.path.join(log_path, sub_dir) # Here should be creating a new directory each time, so `exist_ok=False` os.makedirs(log_dir, exist_ok=False) return os.path.join(log_dir, "zhipuai.log") def get_config_dict( log_level: str, log_file_path: str, log_backup_count: int, log_max_bytes: int ) -> dict: # for windows, the path should be a raw string. log_file_path = ( log_file_path.encode("unicode-escape").decode() if os.name == "nt" else log_file_path ) log_level = log_level.upper() config_dict = { "version": 1, "disable_existing_loggers": False, "formatters": { "formatter": { "format": ( "%(asctime)s %(name)-12s %(process)d %(levelname)-8s %(message)s" ) }, }, "filters": { "logger_name_filter": { "()": __name__ + ".LoggerNameFilter", }, }, "handlers": { "stream_handler": { "class": "logging.StreamHandler", "formatter": "formatter", "level": log_level, # "stream": "ext://sys.stdout", # "filters": ["logger_name_filter"], }, "file_handler": { "class": "logging.handlers.RotatingFileHandler", "formatter": "formatter", "level": log_level, "filename": log_file_path, "mode": "a", "maxBytes": log_max_bytes, "backupCount": log_backup_count, "encoding": "utf8", }, }, "loggers": { "loom_core": { "handlers": ["stream_handler", "file_handler"], "level": log_level, "propagate": False, } }, "root": { "level": log_level, "handlers": ["stream_handler", "file_handler"], }, } return config_dict def get_timestamp_ms(): t = time.time() return int(round(t * 1000)) ================================================ FILE: zhipuai/core/pagination.py ================================================ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. from typing import Any, List, Generic, TypeVar, Optional, cast from typing_extensions import Protocol, override, runtime_checkable from ._http_client import BasePage, PageInfo, BaseSyncPage __all__ = ["SyncPage", "SyncCursorPage"] _T = TypeVar("_T") @runtime_checkable class CursorPageItem(Protocol): id: Optional[str] class SyncPage(BaseSyncPage[_T], BasePage[_T], Generic[_T]): """Note: no pagination actually occurs yet, this is for forwards-compatibility.""" data: List[_T] object: str @override def _get_page_items(self) -> List[_T]: data = self.data if not data: return [] return data @override def next_page_info(self) -> None: """ This page represents a response that isn't actually paginated at the API level so there will never be a next page. """ return None class SyncCursorPage(BaseSyncPage[_T], BasePage[_T], Generic[_T]): data: List[_T] @override def _get_page_items(self) -> List[_T]: data = self.data if not data: return [] return data @override def next_page_info(self) -> Optional[PageInfo]: data = self.data if not data: return None item = cast(Any, data[-1]) if not isinstance(item, CursorPageItem) or item.id is None: # TODO emit warning log return None return PageInfo(params={"after": item.id}) ================================================ FILE: zhipuai/types/__init__.py ================================================ ================================================ FILE: zhipuai/types/agents/__init__.py ================================================ ================================================ FILE: zhipuai/types/agents/agents_completion.py ================================================ from typing import List, Optional from ...core import BaseModel __all__ = ["AgentsCompletion", "AgentsCompletionUsage"] class AgentsCompletionMessage(BaseModel): content: Optional[object] = None role: str class AgentsCompletionUsage(BaseModel): prompt_tokens: int completion_tokens: int total_tokens: int class AgentsCompletionChoice(BaseModel): index: int finish_reason: str message: AgentsCompletionMessage class AgentsError(BaseModel): code: Optional[str] = None message: Optional[str] = None class AgentsCompletion(BaseModel): agent_id: Optional[str] = None conversation_id: Optional[str] = None status: Optional[str] = None choices: List[AgentsCompletionChoice] request_id: Optional[str] = None id: Optional[str] = None usage: Optional[AgentsCompletionUsage] = None error: Optional[AgentsError] = None ================================================ FILE: zhipuai/types/agents/agents_completion_chunk.py ================================================ from typing import List, Optional, Dict, Any from ...core import BaseModel __all__ = [ "AgentsCompletionUsage", "AgentsCompletionChunk", "AgentsChoice", "AgentsChoiceDelta" ] class AgentsChoiceDelta(BaseModel): content: Optional[object] = None role: Optional[str] = None class AgentsChoice(BaseModel): delta: AgentsChoiceDelta finish_reason: Optional[str] = None index: int class AgentsCompletionUsage(BaseModel): prompt_tokens: int completion_tokens: int total_tokens: int class AgentsError(BaseModel): code: Optional[str] = None message: Optional[str] = None class AgentsCompletionChunk(BaseModel): agent_id: Optional[str] = None conversation_id: Optional[str] = None id: Optional[str] = None choices: List[AgentsChoice] usage: Optional[AgentsCompletionUsage] = None error: Optional[AgentsError] = None ================================================ FILE: zhipuai/types/agents/chat_completions_create_param.py ================================================ from typing import Optional from typing_extensions import TypedDict class Reference(TypedDict, total=False): enable: Optional[bool] search_query: Optional[str] ================================================ FILE: zhipuai/types/assistant/__init__.py ================================================ from .assistant_completion import AssistantCompletion __all__ = [ 'AssistantCompletion', ] ================================================ FILE: zhipuai/types/assistant/assistant_completion.py ================================================ from typing import List, Optional, Dict, Any from .message import MessageContent from ...core import BaseModel __all__ = ["AssistantCompletion", "CompletionUsage"] class ErrorInfo(BaseModel): code: str # 错误码 message: str # 错误信息 class AssistantChoice(BaseModel): index: int # 结果下标 delta: MessageContent # 当前会话输出消息体 finish_reason: str """ # 推理结束原因 stop代表推理自然结束或触发停止词。 sensitive 代表模型推理内容被安全审核接口拦截。请注意，针对此类内容，请用户自行判断并决定是否撤回已公开的内容。 # network_error 代表模型推理服务异常。 """ metadata: dict # 元信息，拓展字段 class CompletionUsage(BaseModel): prompt_tokens: int # 输入的 tokens 数量 completion_tokens: int # 输出的 tokens 数量 total_tokens: int # 总 tokens 数量 class AssistantCompletion(BaseModel): id: str # 请求 ID conversation_id: str # 会话 ID assistant_id: str # 智能体 ID created: int # 请求创建时间，Unix 时间戳 status: str # 返回状态，包括：`completed` 表示生成结束`in_progress`表示生成中 `failed` 表示生成异常 last_error: Optional[ErrorInfo] # 异常信息 choices: List[AssistantChoice] # 增量返回的信息 metadata: Optional[Dict[str, Any]] # 元信息，拓展字段 usage: Optional[CompletionUsage] # tokens 数量统计 ================================================ FILE: zhipuai/types/assistant/assistant_conversation_params.py ================================================ from typing import TypedDict, List, Optional, Union class ConversationParameters(TypedDict, total=False): assistant_id: str # 智能体 ID page: int # 当前分页 page_size: int # 分页数量 ================================================ FILE: zhipuai/types/assistant/assistant_conversation_resp.py ================================================ from typing import List, Optional, Dict, Any from ...core import BaseModel __all__ = [ "ConversationUsageListResp" ] class Usage(BaseModel): prompt_tokens: int # 用户输入的 tokens 数量 completion_tokens: int # 模型输入的 tokens 数量 total_tokens: int # 总 tokens 数量 class ConversationUsage(BaseModel): id: str # 会话 id assistant_id: str # 智能体Assistant id create_time: int # 创建时间 update_time: int # 更新时间 usage: Usage # 会话中 tokens 数量统计 class ConversationUsageList(BaseModel): assistant_id: str # 智能体id has_more: bool # 是否还有更多页 conversation_list: List[ConversationUsage] # 返回的 class ConversationUsageListResp(BaseModel): code: int msg: str data: ConversationUsageList ================================================ FILE: zhipuai/types/assistant/assistant_create_params.py ================================================ from typing import TypedDict, List, Optional, Union class AssistantAttachments: file_id: str class MessageTextContent: type: str # 目前支持 type = text text: str MessageContent = Union[MessageTextContent] class ConversationMessage(TypedDict): """会话消息体""" role: str # 用户的输入角色，例如 'user' content: List[MessageContent] # 会话消息体的内容 class AssistantParameters(TypedDict, total=False): """智能体参数类""" assistant_id: str # 智能体 ID conversation_id: Optional[str] # 会话 ID，不传则创建新会话 model: str # 模型名称，默认为 'GLM-4-Assistant' stream: bool # 是否支持流式 SSE，需要传入 True messages: List[ConversationMessage] # 会话消息体 attachments: Optional[List[AssistantAttachments]] # 会话指定的文件，非必填 metadata: Optional[dict] # 元信息，拓展字段，非必填 class TranslateParameters(TypedDict, total=False): from_language: str to_language: str class ExtraParameters(TypedDict, total=False): translate: TranslateParameters ================================================ FILE: zhipuai/types/assistant/assistant_support_resp.py ================================================ from typing import List, Optional, Dict, Any from .message import MessageContent from ...core import BaseModel __all__ = [ "AssistantSupportResp" ] class AssistantSupport(BaseModel): assistant_id: str # 智能体的 Assistant id，用于智能体会话 created_at: int # 创建时间 updated_at: int # 更新时间 name: str # 智能体名称 avatar: str # 智能体头像 description: str # 智能体描述 status: str # 智能体状态，目前只有 publish tools: List[str] # 智能体支持的工具名 starter_prompts: List[str] # 智能体启动推荐的 prompt class AssistantSupportResp(BaseModel): code: int msg: str data: List[AssistantSupport] # 智能体列表 ================================================ FILE: zhipuai/types/assistant/message/__init__.py ================================================ from .message_content import MessageContent __all__ = [ "MessageContent" ] ================================================ FILE: zhipuai/types/assistant/message/message_content.py ================================================ from typing import Union from typing_extensions import Annotated, TypeAlias from ....core._utils import PropertyInfo from .tools_delta_block import ToolsDeltaBlock from .text_content_block import TextContentBlock __all__ = ["MessageContent"] MessageContent: TypeAlias = Annotated[ Union[ToolsDeltaBlock, TextContentBlock], PropertyInfo(discriminator="type"), ] ================================================ FILE: zhipuai/types/assistant/message/text_content_block.py ================================================ from typing_extensions import Literal from ....core import BaseModel __all__ = ["TextContentBlock"] class TextContentBlock(BaseModel): content: str role: str = "assistant" type: Literal["content"] = "content" """Always `content`.""" ================================================ FILE: zhipuai/types/assistant/message/tools/code_interpreter_delta_block.py ================================================ from typing import List from typing_extensions import Literal __all__ = ["CodeInterpreterToolBlock"] from .....core import BaseModel class CodeInterpreterToolOutput(BaseModel): """代码工具输出结果""" type: str # 代码执行日志，目前只有 logs logs: str # 代码执行的日志结果 error_msg: str # 错误信息 class CodeInterpreter(BaseModel): """代码解释器""" input: str # 生成的代码片段，输入给代码沙盒 outputs: List[CodeInterpreterToolOutput] # 代码执行后的输出结果 class CodeInterpreterToolBlock(BaseModel): """代码工具块""" code_interpreter: CodeInterpreter # 代码解释器对象 type: Literal["code_interpreter"] # 调用工具的类型，始终为 `code_interpreter` ================================================ FILE: zhipuai/types/assistant/message/tools/drawing_tool_delta_block.py ================================================ from typing import List from typing_extensions import Literal from .....core import BaseModel __all__ = ["DrawingToolBlock"] class DrawingToolOutput(BaseModel): image: str class DrawingTool(BaseModel): input: str outputs: List[DrawingToolOutput] class DrawingToolBlock(BaseModel): drawing_tool: DrawingTool type: Literal["drawing_tool"] """Always `drawing_tool`.""" ================================================ FILE: zhipuai/types/assistant/message/tools/function_delta_block.py ================================================ from typing import List, Union from typing_extensions import Literal __all__ = ["FunctionToolBlock"] from .....core import BaseModel class FunctionToolOutput(BaseModel): content: str class FunctionTool(BaseModel): name: str arguments: Union[str,dict] outputs: List[FunctionToolOutput] class FunctionToolBlock(BaseModel): function: FunctionTool type: Literal["function"] """Always `drawing_tool`.""" ================================================ FILE: zhipuai/types/assistant/message/tools/retrieval_delta_black.py ================================================ from typing import List from typing_extensions import Literal from .....core import BaseModel class RetrievalToolOutput(BaseModel): """ This class represents the output of a retrieval tool. Attributes: - text (str): The text snippet retrieved from the knowledge base. - document (str): The name of the document from which the text snippet was retrieved, returned only in intelligent configuration. """ text: str document: str class RetrievalTool(BaseModel): """ This class represents the outputs of a retrieval tool. Attributes: - outputs (List[RetrievalToolOutput]): A list of text snippets and their respective document names retrieved from the knowledge base. """ outputs: List[RetrievalToolOutput] class RetrievalToolBlock(BaseModel): """ This class represents a block for invoking the retrieval tool. Attributes: - retrieval (RetrievalTool): An instance of the RetrievalTool class containing the retrieval outputs. - type (Literal["retrieval"]): The type of tool being used, always set to "retrieval". """ retrieval: RetrievalTool type: Literal["retrieval"] """Always `retrieval`.""" ================================================ FILE: zhipuai/types/assistant/message/tools/tools_type.py ================================================ from typing import Union from typing_extensions import Annotated, TypeAlias from .code_interpreter_delta_block import CodeInterpreterToolBlock from .retrieval_delta_black import RetrievalToolBlock from .web_browser_delta_block import WebBrowserToolBlock from .....core._utils import PropertyInfo from .drawing_tool_delta_block import DrawingToolBlock from .function_delta_block import FunctionToolBlock __all__ = ["ToolsType"] ToolsType: TypeAlias = Annotated[ Union[DrawingToolBlock, CodeInterpreterToolBlock, WebBrowserToolBlock, RetrievalToolBlock, FunctionToolBlock], PropertyInfo(discriminator="type"), ] ================================================ FILE: zhipuai/types/assistant/message/tools/web_browser_delta_block.py ================================================ from typing import List from typing_extensions import Literal from .....core import BaseModel __all__ = ["WebBrowserToolBlock"] class WebBrowserOutput(BaseModel): """ This class represents the output of a web browser search result. Attributes: - title (str): The title of the search result. - link (str): The URL link to the search result's webpage. - content (str): The textual content extracted from the search result. - error_msg (str): Any error message encountered during the search or retrieval process. """ title: str link: str content: str error_msg: str class WebBrowser(BaseModel): """ This class represents the input and outputs of a web browser search. Attributes: - input (str): The input query for the web browser search. - outputs (List[WebBrowserOutput]): A list of search results returned by the web browser. """ input: str outputs: List[WebBrowserOutput] class WebBrowserToolBlock(BaseModel): """ This class represents a block for invoking the web browser tool. Attributes: - web_browser (WebBrowser): An instance of the WebBrowser class containing the search input and outputs. - type (Literal["web_browser"]): The type of tool being used, always set to "web_browser". """ web_browser: WebBrowser type: Literal["web_browser"] ================================================ FILE: zhipuai/types/assistant/message/tools_delta_block.py ================================================ from typing import Optional, List from typing_extensions import Literal from .tools.tools_type import ToolsType from ....core import BaseModel __all__ = ["ToolsDeltaBlock"] class ToolsDeltaBlock(BaseModel): tool_calls: List[ToolsType] """The index of the content part in the message.""" role: str = "tool" type: Literal["tool_calls"] = "tool_calls" """Always `tool_calls`.""" ================================================ FILE: zhipuai/types/audio/__init__.py ================================================ from .audio_speech_params import( AudioSpeechParams ) from .audio_customization_param import( AudioCustomizationParam ) from .transcriptions_create_param import( TranscriptionsParam ) __all__ = ["AudioSpeechParams","AudioCustomizationParam","TranscriptionsParam"] ================================================ FILE: zhipuai/types/audio/audio_customization_param.py ================================================ from __future__ import annotations from typing import List, Optional from typing_extensions import Literal, Required, TypedDict __all__ = ["AudioCustomizationParam"] from ..sensitive_word_check import SensitiveWordCheckRequest class AudioCustomizationParam(TypedDict, total=False): model: str """模型编码""" input: str """需要生成语音的文本""" voice_text: str """需要生成语音的音色""" response_format: str """需要生成语音文件的格式""" sensitive_word_check: Optional[SensitiveWordCheckRequest] request_id: str """由用户端传参，需保证唯一性；用于区分每次请求的唯一标识，用户端不传时平台会默认生成。""" user_id: str """用户端。""" ================================================ FILE: zhipuai/types/audio/audio_speech_chunk.py ================================================ from typing import List, Optional, Dict, Any from ...core import BaseModel __all__ = [ "AudioSpeechChunk", "AudioError", "AudioSpeechChoice", "AudioSpeechDelta" ] class AudioSpeechDelta(BaseModel): content: Optional[str] = None role: Optional[str] = None class AudioSpeechChoice(BaseModel): delta: AudioSpeechDelta finish_reason: Optional[str] = None index: int class AudioError(BaseModel): code: Optional[str] = None message: Optional[str] = None class AudioSpeechChunk(BaseModel): choices: List[AudioSpeechChoice] request_id: Optional[str] = None created: Optional[int] = None error: Optional[AudioError] = None ================================================ FILE: zhipuai/types/audio/audio_speech_params.py ================================================ from __future__ import annotations from typing import List, Optional from typing_extensions import Literal, Required, TypedDict __all__ = ["AudioSpeechParams"] from ..sensitive_word_check import SensitiveWordCheckRequest class AudioSpeechParams(TypedDict, total=False): model: str """模型编码""" input: str """需要生成语音的文本""" voice: str """需要生成语音的音色""" response_format: str """需要生成语音文件的格式""" sensitive_word_check: Optional[SensitiveWordCheckRequest] request_id: str """由用户端传参，需保证唯一性；用于区分每次请求的唯一标识，用户端不传时平台会默认生成。""" user_id: str """用户端。""" ================================================ FILE: zhipuai/types/audio/transcriptions_create_param.py ================================================ from __future__ import annotations from typing import List, Optional from typing_extensions import Literal, Required, TypedDict __all__ = ["TranscriptionsParam"] from ..sensitive_word_check import SensitiveWordCheckRequest class TranscriptionsParam(TypedDict, total=False): model: str """模型编码""" temperature:float """采样温度""" stream: bool """是否流式输出""" sensitive_word_check: Optional[SensitiveWordCheckRequest] request_id: str """由用户端传参，需保证唯一性；用于区分每次请求的唯一标识，用户端不传时平台会默认生成。""" user_id: str """用户端。""" ================================================ FILE: zhipuai/types/batch.py ================================================ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. import builtins from typing import List, Optional from typing_extensions import Literal from ..core import BaseModel from .batch_error import BatchError from .batch_request_counts import BatchRequestCounts __all__ = ["Batch", "Errors"] class Errors(BaseModel): data: Optional[List[BatchError]] = None object: Optional[str] = None """这个类型，一直是`list`。""" class Batch(BaseModel): id: str completion_window: str """用于执行请求的地址信息。""" created_at: int """这是 Unix timestamp (in seconds) 表示的创建时间。""" endpoint: str """这是ZhipuAI endpoint的地址。""" input_file_id: str """标记为batch的输入文件的ID。""" object: Literal["batch"] """这个类型，一直是`batch`.""" status: Literal[ "validating", "failed", "in_progress", "finalizing", "completed", "expired", "cancelling", "cancelled" ] """batch 的状态。""" cancelled_at: Optional[int] = None """Unix timestamp (in seconds) 表示的取消时间。""" cancelling_at: Optional[int] = None """Unix timestamp (in seconds) 表示发起取消的请求时间 """ completed_at: Optional[int] = None """Unix timestamp (in seconds) 表示的完成时间。""" error_file_id: Optional[str] = None """这个文件id包含了执行请求失败的请求的输出。""" errors: Optional[Errors] = None expired_at: Optional[int] = None """Unix timestamp (in seconds) 表示的将在过期时间。""" expires_at: Optional[int] = None """Unix timestamp (in seconds) 触发过期""" failed_at: Optional[int] = None """Unix timestamp (in seconds) 表示的失败时间。""" finalizing_at: Optional[int] = None """Unix timestamp (in seconds) 表示的最终时间。""" in_progress_at: Optional[int] = None """Unix timestamp (in seconds) 表示的开始处理时间。""" metadata: Optional[builtins.object] = None """ key:value形式的元数据，以便将信息存储 结构化格式。键的长度是64个字符，值最长512个字符 """ output_file_id: Optional[str] = None """完成请求的输出文件的ID。""" request_counts: Optional[BatchRequestCounts] = None """批次中不同状态的请求计数""" ================================================ FILE: zhipuai/types/batch_create_params.py ================================================ from __future__ import annotations from typing import Dict, Optional from typing_extensions import Literal, Required, TypedDict __all__ = ["BatchCreateParams"] class BatchCreateParams(TypedDict, total=False): completion_window: Required[str] """The time frame within which the batch should be processed. Currently only `24h` is supported. """ endpoint: Required[Literal["/v1/chat/completions", "/v1/embeddings"]] """The endpoint to be used for all requests in the batch. Currently `/v1/chat/completions` and `/v1/embeddings` are supported. """ input_file_id: Required[str] """The ID of an uploaded file that contains requests for the new batch. See [upload file](https://platform.openai.com/docs/api-reference/files/create) for how to upload a file. 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`. """ metadata: Optional[Dict[str, str]] """Optional custom metadata for the batch.""" auto_delete_input_file: Optional[bool] ================================================ FILE: zhipuai/types/batch_error.py ================================================ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. from typing import Optional from ..core import BaseModel __all__ = ["BatchError"] class BatchError(BaseModel): code: Optional[str] = None """定义的业务错误码""" line: Optional[int] = None """文件中的行号""" message: Optional[str] = None """关于对话文件中的错误的描述""" param: Optional[str] = None """参数名称，如果有的话""" ================================================ FILE: zhipuai/types/batch_list_params.py ================================================ from __future__ import annotations from typing_extensions import TypedDict __all__ = ["BatchListParams"] class BatchListParams(TypedDict, total=False): after: str """分页的游标，用于获取下一页的数据。 `after` 是一个指向当前页面的游标，用于获取下一页的数据。如果没有提供 `after`，则返回第一页的数据。 list. """ limit: int """这个参数用于限制返回的结果数量。 Limit 用于限制返回的结果数量。默认值为 10 """ ================================================ FILE: zhipuai/types/batch_request_counts.py ================================================ from ..core import BaseModel __all__ = ["BatchRequestCounts"] class BatchRequestCounts(BaseModel): completed: int """这个数字表示已经完成的请求。""" failed: int """这个数字表示失败的请求。""" total: int """这个数字表示总的请求。""" ================================================ FILE: zhipuai/types/chat/__init__.py ================================================ ================================================ FILE: zhipuai/types/chat/async_chat_completion.py ================================================ from typing import List, Optional from ...core import BaseModel from .chat_completion import CompletionChoice, CompletionUsage __all__ = ["AsyncTaskStatus", "AsyncCompletion"] class AsyncTaskStatus(BaseModel): id: Optional[str] = None request_id: Optional[str] = None model: Optional[str] = None task_status: Optional[str] = None class AsyncCompletion(BaseModel): id: Optional[str] = None request_id: Optional[str] = None model: Optional[str] = None task_status: str choices: List[CompletionChoice] usage: CompletionUsage ================================================ FILE: zhipuai/types/chat/chat_completion.py ================================================ from typing import List, Optional from ...core import BaseModel __all__ = ["Completion", "CompletionUsage"] class Function(BaseModel): arguments: str name: str class CompletionMessageToolCall(BaseModel): id: str function: Function type: str class CompletionMessage(BaseModel): content: Optional[str] = None role: str reasoning_content: Optional[str] = None tool_calls: Optional[List[CompletionMessageToolCall]] = None class CompletionUsage(BaseModel): prompt_tokens: int completion_tokens: int total_tokens: int class CompletionChoice(BaseModel): index: int finish_reason: str message: CompletionMessage class Completion(BaseModel): model: Optional[str] = None created: Optional[int] = None choices: List[CompletionChoice] request_id: Optional[str] = None id: Optional[str] = None usage: CompletionUsage ================================================ FILE: zhipuai/types/chat/chat_completion_chunk.py ================================================ from typing import List, Optional, Dict, Any from ...core import BaseModel __all__ = [ "CompletionUsage", "ChatCompletionChunk", "Choice", "ChoiceDelta", "ChoiceDeltaFunctionCall", "ChoiceDeltaToolCall", "ChoiceDeltaToolCallFunction", "AudioCompletionChunk" ] class ChoiceDeltaFunctionCall(BaseModel): arguments: Optional[str] = None name: Optional[str] = None class ChoiceDeltaToolCallFunction(BaseModel): arguments: Optional[str] = None name: Optional[str] = None class ChoiceDeltaToolCall(BaseModel): index: int id: Optional[str] = None function: Optional[ChoiceDeltaToolCallFunction] = None type: Optional[str] = None class AudioCompletionChunk(BaseModel): id: Optional[str] = None data: Optional[str] = None expires_at: Optional[int] = None class ChoiceDelta(BaseModel): content: Optional[str] = None role: Optional[str] = None reasoning_content: Optional[str] = None tool_calls: Optional[List[ChoiceDeltaToolCall]] = None audio: Optional[AudioCompletionChunk] = None class Choice(BaseModel): delta: ChoiceDelta finish_reason: Optional[str] = None index: int class PromptTokensDetails(BaseModel): cached_tokens: int class CompletionTokensDetails(BaseModel): reasoning_tokens: int class CompletionUsage(BaseModel): prompt_tokens: int prompt_tokens_details: Optional[PromptTokensDetails] = None completion_tokens: int completion_tokens_details: Optional[CompletionTokensDetails] = None total_tokens: int class ChatCompletionChunk(BaseModel): id: Optional[str] = None choices: List[Choice] created: Optional[int] = None model: Optional[str] = None usage: Optional[CompletionUsage] = None extra_json: Dict[str, Any] ================================================ FILE: zhipuai/types/chat/chat_completions_create_param.py ================================================ from typing import Optional from typing_extensions import TypedDict class Reference(TypedDict, total=False): enable: Optional[bool] search_query: Optional[str] ================================================ FILE: zhipuai/types/chat/code_geex/code_geex_params.py ================================================ from typing import List, Optional from typing_extensions import Literal, Required, TypedDict __all__ = [ "CodeGeexTarget", "CodeGeexContext", "CodeGeexExtra", ] class CodeGeexTarget(TypedDict, total=False): """补全的内容参数""" path: Optional[str] """文件路径""" language: Required[Literal[ "c", "c++", "cpp", "c#", "csharp", "c-sharp", "css", "cuda", "dart", "lua", "objectivec", "objective-c", "objective-c++", "python", "perl", "prolog", "swift", "lisp", "java", "scala", "tex", "jsx", "tsx", "vue", "markdown", "html", "php", "js", "javascript", "typescript", "go", "shell", "rust", "sql", "kotlin", "vb", "ruby", "pascal", "r", "fortran", "lean", "matlab", "delphi", "scheme", "basic", "assembly", "groovy", "abap", "gdscript", "haskell", "julia", "elixir", "excel", "clojure", "actionscript", "solidity", "powershell", "erlang", "cobol", "alloy", "awk", "thrift", "sparql", "augeas", "cmake", "f-sharp", "stan", "isabelle", "dockerfile", "rmarkdown", "literate-agda", "tcl", "glsl", "antlr", "verilog", "racket", "standard-ml", "elm", "yaml", "smalltalk", "ocaml", "idris", "visual-basic", "protocol-buffer", "bluespec", "applescript", "makefile", "tcsh", "maple", "systemverilog", "literate-coffeescript", "vhdl", "restructuredtext", "sas", "literate-haskell", "java-server-pages", "coffeescript", "emacs-lisp", "mathematica", "xslt", "zig", "common-lisp", "stata", "agda", "ada" ]] """代码语言类型，如python""" code_prefix: Required[str] """补全位置的前文""" code_suffix: Required[str] """补全位置的后文""" class CodeGeexContext(TypedDict, total=False): """附加代码""" path: Required[str] """附加代码文件的路径""" code: Required[str] """附加的代码内容""" class CodeGeexExtra(TypedDict, total=False): target: Required[CodeGeexTarget] """补全的内容参数""" contexts: Optional[List[CodeGeexContext]] """附加代码""" ================================================ FILE: zhipuai/types/embeddings.py ================================================ from __future__ import annotations from typing import Optional, List from ..core import BaseModel from .chat.chat_completion import CompletionUsage __all__ = ["Embedding", "EmbeddingsResponded"] class Embedding(BaseModel): object: str index: Optional[int] = None embedding: List[float] class EmbeddingsResponded(BaseModel): object: str data: List[Embedding] model: str usage: CompletionUsage ================================================ FILE: zhipuai/types/file_parser/__init__.py ================================================ ================================================ FILE: zhipuai/types/file_parser/file_parser_create_params.py ================================================ from __future__ import annotations from typing_extensions import Literal, Required, TypedDict from ...core import NOT_GIVEN, Body, Headers, NotGiven, FileTypes __all__ = ["FileParserCreateParams", "FileParserDownloadParams"] class FileParserCreateParams(TypedDict): file: FileTypes """上传的文件""" file_type: str """文件类型""" tool_type: Literal["simple", "doc2x", "tencent", "zhipu-pro"] """工具类型""" class FileParserDownloadParams(TypedDict): task_id: str """解析任务id""" format_type: Literal["text", "download_link"] """结果返回类型""" ================================================ FILE: zhipuai/types/file_parser/file_parser_resp.py ================================================ from typing import List, Optional from zhipuai.core import BaseModel __all__ = [ "FileParserTaskCreateResp" ] class FileParserTaskCreateResp(BaseModel): task_id: str # 任务id message: str # message success: bool # 是否成功 ================================================ FILE: zhipuai/types/files/__init__.py ================================================ from .file_object import FileObject, ListOfFileObject from .upload_detail import UploadDetail from .file_deleted import FileDeleted __all__ = [ "FileObject", "ListOfFileObject", "UploadDetail", "FileDeleted" ] ================================================ FILE: zhipuai/types/files/file_create_params.py ================================================ from __future__ import annotations from typing import List, Optional from typing_extensions import Literal, Required, TypedDict __all__ = ["FileCreateParams"] from . import UploadDetail from ...core import FileTypes class FileCreateParams(TypedDict, total=False): file: FileTypes """file和 upload_detail二选一必填""" upload_detail: List[UploadDetail] """file和 upload_detail二选一必填""" purpose: Required[Literal["fine-tune", "retrieval", "batch"]] """ 上传文件的用途，支持 "fine-tune和 "retrieval" retrieval支持上传Doc、Docx、PDF、Xlsx、URL类型文件，且单个文件的大小不超过 5MB。 fine-tune支持上传.jsonl文件且当前单个文件的大小最大可为 100 MB ，文件中语料格式需满足微调指南中所描述的格式。 """ custom_separator: Optional[List[str]] """ 当 purpose 为 retrieval 且文件类型为 pdf, url, docx 时上传，切片规则默认为 `\n`。 """ knowledge_id: str """ 当文件上传目的为 retrieval 时，需要指定知识库ID进行上传。 """ sentence_size: int """ 当文件上传目的为 retrieval 时，需要指定知识库ID进行上传。 """ ================================================ FILE: zhipuai/types/files/file_deleted.py ================================================ from typing_extensions import Literal from ...core import BaseModel __all__ = ["FileDeleted"] class FileDeleted(BaseModel): id: str deleted: bool object: Literal["file"] ================================================ FILE: zhipuai/types/files/file_object.py ================================================ from typing import Optional, List from ...core import BaseModel __all__ = ["FileObject", "ListOfFileObject"] class FileObject(BaseModel): id: Optional[str] = None bytes: Optional[int] = None created_at: Optional[int] = None filename: Optional[str] = None object: Optional[str] = None purpose: Optional[str] = None status: Optional[str] = None status_details: Optional[str] = None class ListOfFileObject(BaseModel): object: Optional[str] = None data: List[FileObject] has_more: Optional[bool] = None ================================================ FILE: zhipuai/types/files/upload_detail.py ================================================ from typing import Optional, List, Dict from ...core import BaseModel class UploadDetail(BaseModel): url: str knowledge_type: int file_name: Optional[str] = None sentence_size: Optional[int] = None custom_separator: Optional[List[str]] = None callback_url: Optional[str] = None callback_header: Optional[Dict[str,str]] = None ================================================ FILE: zhipuai/types/fine_tuning/__init__.py ================================================ from __future__ import annotations from .fine_tuning_job import FineTuningJob as FineTuningJob from .fine_tuning_job import ListOfFineTuningJob as ListOfFineTuningJob from .fine_tuning_job_event import FineTuningJobEvent as FineTuningJobEvent ================================================ FILE: zhipuai/types/fine_tuning/fine_tuning_job.py ================================================ from typing import List, Union, Optional, Dict, Any from ...core import BaseModel __all__ = ["FineTuningJob", "Error", "Hyperparameters", "ListOfFineTuningJob" ] class Error(BaseModel): code: str message: str param: Optional[str] = None class Hyperparameters(BaseModel): n_epochs: Union[str, int, None] = None class FineTuningJob(BaseModel): id: Optional[str] = None request_id: Optional[str] = None created_at: Optional[int] = None error: Optional[Error] = None fine_tuned_model: Optional[str] = None finished_at: Optional[int] = None hyperparameters: Optional[Hyperparameters] = None model: Optional[str] = None object: Optional[str] = None result_files: List[str] status: str trained_tokens: Optional[int] = None training_file: str validation_file: Optional[str] = None class ListOfFineTuningJob(BaseModel): object: Optional[str] = None data: List[FineTuningJob] has_more: Optional[bool] = None ================================================ FILE: zhipuai/types/fine_tuning/fine_tuning_job_event.py ================================================ from typing import List, Union, Optional from ...core import BaseModel __all__ = ["FineTuningJobEvent", "Metric", "JobEvent"] class Metric(BaseModel): epoch: Optional[Union[str, int, float]] = None current_steps: Optional[int] = None total_steps: Optional[int] = None elapsed_time: Optional[str] = None remaining_time: Optional[str] = None trained_tokens: Optional[int] = None loss: Optional[Union[str, int, float]] = None eval_loss: Optional[Union[str, int, float]] = None acc: Optional[Union[str, int, float]] = None eval_acc: Optional[Union[str, int, float]] = None learning_rate: Optional[Union[str, int, float]] = None class JobEvent(BaseModel): object: Optional[str] = None id: Optional[str] = None type: Optional[str] = None created_at: Optional[int] = None level: Optional[str] = None message: Optional[str] = None data: Optional[Metric] = None class FineTuningJobEvent(BaseModel): object: Optional[str] = None data: List[JobEvent] has_more: Optional[bool] = None ================================================ FILE: zhipuai/types/fine_tuning/job_create_params.py ================================================ from __future__ import annotations from typing import Union from typing_extensions import Literal, TypedDict __all__ = ["Hyperparameters"] class Hyperparameters(TypedDict, total=False): batch_size: Union[Literal["auto"], int] learning_rate_multiplier: Union[Literal["auto"], float] n_epochs: Union[Literal["auto"], int] ================================================ FILE: zhipuai/types/fine_tuning/models/__init__.py ================================================ from .fine_tuned_models import FineTunedModelsStatus ================================================ FILE: zhipuai/types/fine_tuning/models/fine_tuned_models.py ================================================ from typing import List, Union, Optional, ClassVar from ....core import BaseModel, PYDANTIC_V2, ConfigDict __all__ = ["FineTunedModelsStatus"] class FineTunedModelsStatus(BaseModel): if PYDANTIC_V2: model_config: ClassVar[ConfigDict] = ConfigDict(extra="allow", protected_namespaces=()) request_id: str #请求id model_name: str #模型名称 delete_status: str #删除状态 deleting（删除中）, deleted （已删除） ================================================ FILE: zhipuai/types/image.py ================================================ from __future__ import annotations from typing import Optional, List from ..core import BaseModel __all__ = ["GeneratedImage", "ImagesResponded"] class GeneratedImage(BaseModel): b64_json: Optional[str] = None url: Optional[str] = None revised_prompt: Optional[str] = None class ImagesResponded(BaseModel): created: int data: List[GeneratedImage] ================================================ FILE: zhipuai/types/knowledge/__init__.py ================================================ from .knowledge import KnowledgeInfo from .knowledge_used import KnowledgeStatistics, KnowledgeUsed __all__ = [ 'KnowledgeInfo', "KnowledgeStatistics", "KnowledgeUsed", ] ================================================ FILE: zhipuai/types/knowledge/document/__init__.py ================================================ from .document import DocumentData, DocumentObject, DocumentSuccessinfo, DocumentFailedInfo __all__ = [ "DocumentData", "DocumentObject", "DocumentSuccessinfo", "DocumentFailedInfo", ] ================================================ FILE: zhipuai/types/knowledge/document/document.py ================================================ from typing import Optional, List from ....core import BaseModel __all__ = ["DocumentData", "DocumentObject", "DocumentSuccessinfo", "DocumentFailedInfo"] class DocumentSuccessinfo(BaseModel): documentId: Optional[str] = None """文件id""" filename: Optional[str] = None """文件名称""" class DocumentFailedInfo(BaseModel): failReason: Optional[str] = None """上传失败的原因，包括：文件格式不支持、文件大小超出限制、知识库容量已满、容量上限为 50 万字。""" filename: Optional[str] = None """文件名称""" documentId: Optional[str] = None """知识库id""" class DocumentObject(BaseModel): """文档信息""" successInfos: Optional[List[DocumentSuccessinfo]] = None """上传成功的文件信息""" failedInfos: Optional[List[DocumentFailedInfo]] = None """上传失败的文件信息""" class DocumentDataFailInfo(BaseModel): """失败原因""" embedding_code: Optional[int] = None # 失败码 10001：知识不可用，知识库空间已达上限 10002：知识不可用，知识库空间已达上限(字数超出限制) embedding_msg: Optional[str] = None # 失败原因 class DocumentData(BaseModel): id: str = None # 知识唯一id custom_separator: List[str] = None # 切片规则 sentence_size: str = None # 切片大小 length: int = None # 文件大小（字节） word_num: int = None # 文件字数 name: str = None # 文件名 url: str = None # 文件下载链接 embedding_stat: int = None # 0:向量化中 1:向量化完成 2:向量化失败 failInfo: Optional[DocumentDataFailInfo] = None # 失败原因 向量化失败embedding_stat=2的时候 会有此值 ================================================ FILE: zhipuai/types/knowledge/document/document_edit_params.py ================================================ from typing import Optional, List, Literal, TypedDict, Dict __all__ = ["DocumentEditParams"] class DocumentEditParams(TypedDict): """ 知识参数类型定义 Attributes: id (str): 知识ID knowledge_type (int): 知识类型: 1:文章知识: 支持pdf,url,docx 2.问答知识-文档: 支持pdf,url,docx 3.问答知识-表格: 支持xlsx 4.商品库-表格: 支持xlsx 5.自定义: 支持pdf,url,docx custom_separator (Optional[List[str]]): 当前知识类型为自定义(knowledge_type=5)时的切片规则，默认\n sentence_size (Optional[int]): 当前知识类型为自定义(knowledge_type=5)时的切片字数，取值范围: 20-2000，默认300 callback_url (Optional[str]): 回调地址 callback_header (Optional[dict]): 回调时携带的header """ id: str knowledge_type: int custom_separator: Optional[List[str]] sentence_size: Optional[int] callback_url: Optional[str] callback_header: Optional[Dict[str, str]] ================================================ FILE: zhipuai/types/knowledge/document/document_list_params.py ================================================ from __future__ import annotations from typing import Dict, Optional from typing_extensions import Literal, Required, TypedDict class DocumentListParams(TypedDict, total=False): """ 文件查询参数类型定义 Attributes: purpose (Optional[str]): 文件用途 knowledge_id (Optional[str]): 当文件用途为 retrieval 时，需要提供查询的知识库ID page (Optional[int]): 页，默认1 limit (Optional[int]): 查询文件列表数，默认10 after (Optional[str]): 查询指定fileID之后的文件列表（当文件用途为 fine-tune 时需要） order (Optional[str]): 排序规则，可选值['desc', 'asc']，默认desc（当文件用途为 fine-tune 时需要） """ purpose: Optional[str] knowledge_id: Optional[str] page: Optional[int] limit: Optional[int] after: Optional[str] order: Optional[str] ================================================ FILE: zhipuai/types/knowledge/document/document_list_resp.py ================================================ from __future__ import annotations from typing import Dict, Optional, List from . import DocumentData from ....core import BaseModel __all__ = [ "DocumentPage" ] class DocumentPage(BaseModel): list: List[DocumentData] object: str ================================================ FILE: zhipuai/types/knowledge/knowledge.py ================================================ from typing import Optional from ...core import BaseModel __all__ = ["KnowledgeInfo"] class KnowledgeInfo(BaseModel): id: Optional[str] = None """知识库唯一 id""" embedding_id: Optional[str] = None # 知识库绑定的向量化模型 见模型列表 [内部服务开放接口文档](https://lslfd0slxc.feishu.cn/docx/YauWdbBiMopV0FxB7KncPWCEn8f#H15NduiQZo3ugmxnWQFcfAHpnQ4) name: Optional[str] = None # 知识库名称 100字限制 customer_identifier: Optional[str] = None # 用户标识 长度32位以内 description: Optional[str] = None # 知识库描述 500字限制 background: Optional[str] = None # 背景颜色（给枚举）'blue', 'red', 'orange', 'purple', 'sky' icon: Optional[str] = None # 知识库图标（给枚举） question: 问号、book: 书籍、seal: 印章、wrench: 扳手、tag: 标签、horn: 喇叭、house: 房子 bucket_id: Optional[str] = None # 桶id 限制32位 ================================================ FILE: zhipuai/types/knowledge/knowledge_create_params.py ================================================ from __future__ import annotations from typing import Dict, Optional from typing_extensions import Literal, Required, TypedDict __all__ = ["KnowledgeBaseParams"] class KnowledgeBaseParams(TypedDict): """ 知识库参数类型定义 Attributes: embedding_id (int): 知识库绑定的向量化模型ID name (str): 知识库名称，限制100字 customer_identifier (Optional[str]): 用户标识，长度32位以内 description (Optional[str]): 知识库描述，限制500字 background (Optional[Literal['blue', 'red', 'orange', 'purple', 'sky']]): 背景颜色 icon (Optional[Literal['question', 'book', 'seal', 'wrench', 'tag', 'horn', 'house']]): 知识库图标 bucket_id (Optional[str]): 桶ID，限制32位 """ embedding_id: int name: str customer_identifier: Optional[str] description: Optional[str] background: Optional[Literal['blue', 'red', 'orange', 'purple', 'sky']] = None icon: Optional[Literal['question', 'book', 'seal', 'wrench', 'tag', 'horn', 'house']] = None bucket_id: Optional[str] ================================================ FILE: zhipuai/types/knowledge/knowledge_list_params.py ================================================ from __future__ import annotations from typing import Dict, Optional from typing_extensions import Literal, Required, TypedDict __all__ = ["KnowledgeListParams"] class KnowledgeListParams(TypedDict, total=False): page: int = 1 """ 页码，默认 1，第一页 """ size: int = 10 """每页数量 默认10 """ ================================================ FILE: zhipuai/types/knowledge/knowledge_list_resp.py ================================================ from __future__ import annotations from typing import Dict, Optional, List from . import KnowledgeInfo from ...core import BaseModel __all__ = [ "KnowledgePage" ] class KnowledgePage(BaseModel): list: List[KnowledgeInfo] object: str ================================================ FILE: zhipuai/types/knowledge/knowledge_used.py ================================================ from typing import Optional from ...core import BaseModel __all__ = [ "KnowledgeStatistics", "KnowledgeUsed" ] class KnowledgeStatistics(BaseModel): """ 使用量统计 """ word_num: Optional[int] = None length: Optional[int] = None class KnowledgeUsed(BaseModel): used: Optional[KnowledgeStatistics] = None """已使用量""" total: Optional[KnowledgeStatistics] = None """知识库总量""" ================================================ FILE: zhipuai/types/moderation/__init__.py ================================================ ================================================ FILE: zhipuai/types/moderation/moderation_completion.py ================================================ from typing import List, Optional, Union, Dict from ...core import BaseModel __all__ = ["Completion"] class Completion(BaseModel): model: Optional[str] = None input: Optional[Union[str, List[str], Dict]] = None # 新增 input 字段 ================================================ FILE: zhipuai/types/sensitive_word_check/__init__.py ================================================ from .sensitive_word_check import SensitiveWordCheckRequest __all__ = [ "SensitiveWordCheckRequest" ] ================================================ FILE: zhipuai/types/sensitive_word_check/sensitive_word_check.py ================================================ from typing import Optional from typing_extensions import TypedDict class SensitiveWordCheckRequest(TypedDict, total=False): type: Optional[str] """敏感词类型，当前仅支持ALL""" status: Optional[str] """敏感词启用禁用状态 启用：ENABLE 禁用：DISABLE 备注：默认开启敏感词校验，如果要关闭敏感词校验，需联系商务获取对应权限，否则敏感词禁用不生效。 """ ================================================ FILE: zhipuai/types/tools/__init__.py ================================================ from .web_search import ( WebSearch, SearchIntent, SearchResult, SearchRecommend, ) from .web_search_chunk import ( WebSearchChunk ) __all__ = [ 'WebSearch', 'SearchIntent', 'SearchResult', 'SearchRecommend', 'WebSearchChunk' ] ================================================ FILE: zhipuai/types/tools/tools_web_search_params.py ================================================ from __future__ import annotations from typing import Union, Optional, List from typing_extensions import Literal, Required, TypedDict __all__ = ["WebSearchParams"] class WebSearchParams(TypedDict): """ 工具名：web-search-pro参数类型定义 Attributes: :param model: str, 模型名称 :param request_id: Optional[str], 请求ID :param stream: Optional[bool], 是否流式 :param messages: Union[str, List[str], List[int], object, None], 包含历史对话上下文的内容，按照 {"role": "user", "content": "你好"} 的json 数组形式进行传参 当前版本仅支持 User Message 单轮对话，工具会理解User Message并进行搜索， 请尽可能传入不带指令格式的用户原始提问，以提高搜索准确率。 :param scope: Optional[str], 指定搜索范围，全网、学术等，默认全网 :param location: Optional[str], 指定搜索用户地区 location 提高相关性 :param recent_days: Optional[int],支持指定返回 N 天（1-30）更新的搜索结果 """ model: str request_id: Optional[str] stream: Optional[bool] messages: Union[str, List[str], List[int], object, None] scope: Optional[str] = None location: Optional[str] = None recent_days: Optional[int] = None ================================================ FILE: zhipuai/types/tools/web_search.py ================================================ from typing import List, Optional from ..chat.chat_completion import Function from ...core import BaseModel __all__ = [ "WebSearch", "SearchIntent", "SearchResult", "SearchRecommend", ] class SearchIntent(BaseModel): index: int # 搜索轮次，默认为 0 query: str # 搜索优化 query intent: str # 判断的意图类型 keywords: str # 搜索关键词 class SearchResult(BaseModel): index: int # 搜索轮次，默认为 0 title: str # 标题 link: str # 链接 content: str # 内容 icon: str # 图标 media: str # 来源媒体 refer: str # 角标序号 [ref_1] class SearchRecommend(BaseModel): index: int # 搜索轮次，默认为 0 query: str # 推荐query class WebSearchMessageToolCall(BaseModel): id: str search_intent: Optional[SearchIntent] search_result: Optional[SearchResult] search_recommend: Optional[SearchRecommend] type: str class WebSearchMessage(BaseModel): role: str tool_calls: Optional[List[WebSearchMessageToolCall]] = None class WebSearchChoice(BaseModel): index: int finish_reason: str message: WebSearchMessage class WebSearch(BaseModel): created: Optional[int] = None choices: List[WebSearchChoice] request_id: Optional[str] = None id: Optional[str] = None ================================================ FILE: zhipuai/types/tools/web_search_chunk.py ================================================ from typing import List, Optional, Dict, Any from .web_search import SearchIntent, SearchResult, SearchRecommend from ...core import BaseModel __all__ = [ "WebSearchChunk" ] class ChoiceDeltaToolCall(BaseModel): index: int id: Optional[str] = None search_intent: Optional[SearchIntent] = None search_result: Optional[SearchResult] = None search_recommend: Optional[SearchRecommend] = None type: Optional[str] = None class ChoiceDelta(BaseModel): role: Optional[str] = None tool_calls: Optional[List[ChoiceDeltaToolCall]] = None class Choice(BaseModel): delta: ChoiceDelta finish_reason: Optional[str] = None index: int class WebSearchChunk(BaseModel): id: Optional[str] = None choices: List[Choice] created: Optional[int] = None ================================================ FILE: zhipuai/types/video/__init__.py ================================================ from .video_object import ( VideoObject, VideoResult ) __all__ = ["VideoObject", "VideoResult"] ================================================ FILE: zhipuai/types/video/video_create_params.py ================================================ from __future__ import annotations from typing import List, Optional from typing_extensions import Literal, Required, TypedDict __all__ = ["VideoCreateParams"] from ..sensitive_word_check import SensitiveWordCheckRequest class VideoCreateParams(TypedDict, total=False): model: str """模型编码""" prompt: str """所需视频的文本描述""" image_url: str """所需视频的文本描述""" sensitive_word_check: Optional[SensitiveWordCheckRequest] """支持 URL 或者 Base64、传入 image 奖进行图生视频 * 图片格式： * 图片大小：""" request_id: str """由用户端传参，需保证唯一性；用于区分每次请求的唯一标识，用户端不传时平台会默认生成。""" user_id: str """用户端。""" ================================================ FILE: zhipuai/types/video/video_object.py ================================================ from typing import Optional, List from ...core import BaseModel __all__ = ["VideoObject", "VideoResult"] class VideoResult(BaseModel): url: str """视频url""" cover_image_url: str """预览图""" class VideoObject(BaseModel): id: Optional[str] = None """智谱 AI 开放平台生成的任务订单号，调用请求结果接口时请使用此订单号""" model: str """模型名称""" video_result: List[VideoResult] """视频生成结果""" task_status: str """处理状态，PROCESSING（处理中），SUCCESS（成功），FAIL（失败） 注：处理中状态需通过查询获取结果""" request_id: str """用户在客户端请求时提交的任务编号或者平台生成的任务编号""" ================================================ FILE: zhipuai/types/web_search/__init__.py ================================================ from .web_search_create_params import ( WebSearchCreatParams ) __all__ = ["WebSearchCreatParams"] ================================================ FILE: zhipuai/types/web_search/web_search_create_params.py ================================================ from __future__ import annotations from typing import Union, Optional, List from typing_extensions import Literal, Required, TypedDict from ...types.sensitive_word_check import SensitiveWordCheckRequest __all__ = ["WebSearchCreatParams"] class WebSearchCreatParams(TypedDict): search_engine: str """搜索引擎""" search_query: str """搜索query文本""" request_id: str """由用户端传参，需保证唯一性；用于区分每次请求的唯一标识，用户端不传时平台会默认生成。""" user_id: str """用户端。""" sensitive_word_check: Optional[SensitiveWordCheckRequest] ================================================ FILE: zhipuai/types/web_search/web_search_resp.py ================================================ from typing import List, Optional from ...core import BaseModel __all__ = [ "SearchIntentResp", "SearchResultResp", ] class SearchIntentResp(BaseModel): query: str # 搜索优化 query intent: str # 判断的意图类型 keywords: str # 搜索关键词 class SearchResultResp(BaseModel): title: str # 标题 link: str # 链接 content: str # 内容 icon: str # 图标 media: str # 来源媒体 refer: str # 角标序号 [ref_1] publish_date: str # 发布时间 class WebSearchResp(BaseModel): created: Optional[int] = None request_id: Optional[str] = None id: Optional[str] = None search_intent: Optional[SearchIntentResp] search_result: Optional[SearchResultResp]