SYMBOL INDEX (329 symbols across 28 files)

FILE: examples/batch_dry_run_example.py
  function main (line 21) | def main() -> int:

FILE: examples/batch_processing_example.py
  function create_sample_documents (line 31) | def create_sample_documents():
  function demonstrate_basic_batch_processing (line 109) | def demonstrate_basic_batch_processing():
  function demonstrate_async_batch_processing (line 188) | async def demonstrate_async_batch_processing():
  function demonstrate_rag_integration (line 235) | async def demonstrate_rag_integration():
  function demonstrate_directory_processing (line 317) | def demonstrate_directory_processing():
  function demonstrate_error_handling (line 400) | def demonstrate_error_handling():
  function main (line 487) | async def main():

FILE: examples/enhanced_markdown_example.py
  function create_sample_markdown_content (line 29) | def create_sample_markdown_content():
  function demonstrate_basic_conversion (line 372) | def demonstrate_basic_conversion():
  function demonstrate_backend_comparison (line 420) | def demonstrate_backend_comparison():
  function demonstrate_custom_styling (line 500) | def demonstrate_custom_styling():
  function demonstrate_content_conversion (line 717) | def demonstrate_content_conversion():
  function demonstrate_error_handling (line 808) | def demonstrate_error_handling():
  function main (line 955) | def main():

FILE: examples/image_format_test.py
  function check_pillow_installation (line 23) | def check_pillow_installation():
  function get_image_info (line 38) | def get_image_info(image_path: Path):
  function test_image_format_parsing (line 55) | async def test_image_format_parsing(file_path: str):
  function main (line 194) | def main():

FILE: examples/insert_content_list_example.py
  function configure_logging (line 34) | def configure_logging():
  function create_sample_content_list (line 92) | def create_sample_content_list():
  function demo_insert_content_list (line 177) | async def demo_insert_content_list(
  function main (line 378) | def main():

FILE: examples/lmstudio_integration_example.py
  function lmstudio_llm_model_func (line 45) | async def lmstudio_llm_model_func(
  function lmstudio_embedding_async (line 63) | async def lmstudio_embedding_async(texts: List[str]) -> List[List[float]]:
  class LMStudioRAGIntegration (line 76) | class LMStudioRAGIntegration:
    method __init__ (line 79) | def __init__(self):
    method test_connection (line 102) | async def test_connection(self) -> bool:
    method test_chat_completion (line 134) | async def test_chat_completion(self) -> bool:
    method embedding_func_factory (line 167) | def embedding_func_factory(self):
    method initialize_rag (line 175) | async def initialize_rag(self):
    method process_document_example (line 199) | async def process_document_example(self, file_path: str):
    method query_examples (line 217) | async def query_examples(self):
    method simple_query_example (line 239) | async def simple_query_example(self):
  function main (line 292) | async def main():

FILE: examples/modalprocessors_example.py
  function get_llm_model_func (line 22) | def get_llm_model_func(api_key: str, base_url: str = None):
  function get_vision_model_func (line 39) | def get_vision_model_func(api_key: str, base_url: str = None):
  function process_image_example (line 84) | async def process_image_example(lightrag: LightRAG, vision_model_func):
  function process_table_example (line 111) | async def process_table_example(lightrag: LightRAG, llm_model_func):
  function process_equation_example (line 143) | async def process_equation_example(lightrag: LightRAG, llm_model_func):
  function initialize_rag (line 166) | async def initialize_rag(api_key: str, base_url: str = None):
  function main (line 205) | def main():
  function main_async (line 220) | async def main_async(api_key: str, base_url: str = None):

FILE: examples/office_document_test.py
  function check_libreoffice_installation (line 23) | def check_libreoffice_installation():
  function test_office_document_parsing (line 49) | async def test_office_document_parsing(file_path: str):
  function main (line 156) | def main():

FILE: examples/raganything_example.py
  function configure_logging (line 33) | def configure_logging():
  function process_with_rag (line 89) | async def process_with_rag(
  function main (line 269) | def main():

FILE: examples/text_format_test.py
  function check_reportlab_installation (line 23) | def check_reportlab_installation():
  function test_text_format_parsing (line 38) | async def test_text_format_parsing(file_path: str):
  function main (line 158) | def main():

FILE: examples/vllm_integration_example.py
  function vllm_llm_model_func (line 59) | async def vllm_llm_model_func(
  function vllm_embedding_async (line 80) | async def vllm_embedding_async(texts: List[str]) -> List[List[float]]:
  class VLLMRAGIntegration (line 96) | class VLLMRAGIntegration:
    method __init__ (line 99) | def __init__(self):
    method test_connection (line 124) | async def test_connection(self) -> bool:
    method test_chat_completion (line 157) | async def test_chat_completion(self) -> bool:
    method embedding_func_factory (line 188) | def embedding_func_factory(self):
    method initialize_rag (line 196) | async def initialize_rag(self):
    method process_document_example (line 219) | async def process_document_example(self, file_path: str):
    method query_examples (line 237) | async def query_examples(self):
    method simple_query_example (line 259) | async def simple_query_example(self):
  function main (line 314) | async def main():

FILE: raganything/__init__.py
  function get_version (line 114) | def get_version() -> str:

FILE: raganything/base.py
  class DocStatus (line 4) | class DocStatus(str, Enum):

FILE: raganything/batch.py
  class BatchMixin (line 19) | class BatchMixin:
    method _ensure_lightrag_initialized (line 27) | async def _ensure_lightrag_initialized(self) -> None: ...
    method process_document_complete (line 28) | async def process_document_complete(self, file_path: str, **kwargs) ->...
    method process_folder_complete (line 34) | async def process_folder_complete(
    method process_documents_batch (line 174) | def process_documents_batch(
    method process_documents_batch_async (line 226) | async def process_documents_batch_async(
    method get_supported_file_extensions (line 278) | def get_supported_file_extensions(self) -> List[str]:
    method filter_supported_files (line 283) | def filter_supported_files(
    method process_documents_with_rag_batch (line 302) | async def process_documents_with_rag_batch(

FILE: raganything/batch_parser.py
  class BatchProcessingResult (line 22) | class BatchProcessingResult:
    method success_rate (line 34) | def success_rate(self) -> float:
    method summary (line 40) | def summary(self) -> str:
  class BatchParser (line 53) | class BatchParser:
    method __init__ (line 61) | def __init__(
    method get_supported_extensions (line 101) | def get_supported_extensions(self) -> List[str]:
    method filter_supported_files (line 110) | def filter_supported_files(
    method process_single_file (line 158) | def process_single_file(
    method process_batch (line 203) | def process_batch(
    method process_batch_async (line 339) | async def process_batch_async(
  function main (line 376) | def main():

FILE: raganything/callbacks.py
  class ProcessingEvent (line 35) | class ProcessingEvent:
    method to_dict (line 47) | def to_dict(self) -> Dict[str, Any]:
  class ProcessingCallback (line 61) | class ProcessingCallback:
    method on_parse_start (line 72) | def on_parse_start(self, file_path: str, parser: str = "", **kwargs: A...
    method on_parse_complete (line 75) | def on_parse_complete(
    method on_parse_error (line 85) | def on_parse_error(
    method on_text_insert_start (line 91) | def on_text_insert_start(
    method on_text_insert_complete (line 96) | def on_text_insert_complete(
    method on_multimodal_start (line 102) | def on_multimodal_start(
    method on_multimodal_item_complete (line 107) | def on_multimodal_item_complete(
    method on_multimodal_complete (line 117) | def on_multimodal_complete(
    method on_query_start (line 127) | def on_query_start(self, query: str, mode: str = "", **kwargs: Any) ->...
    method on_query_complete (line 130) | def on_query_complete(
    method on_query_error (line 140) | def on_query_error(
    method on_document_complete (line 150) | def on_document_complete(
    method on_document_error (line 159) | def on_document_error(
    method on_batch_start (line 169) | def on_batch_start(self, file_count: int = 0, **kwargs: Any) -> None:
    method on_batch_complete (line 172) | def on_batch_complete(
  class MetricsCallback (line 183) | class MetricsCallback(ProcessingCallback):
    method __init__ (line 196) | def __init__(self) -> None:
    method on_parse_complete (line 210) | def on_parse_complete(
    method on_text_insert_complete (line 220) | def on_text_insert_complete(
    method on_multimodal_complete (line 225) | def on_multimodal_complete(
    method on_document_complete (line 235) | def on_document_complete(self, file_path: str, **kw: Any) -> None:
    method on_document_error (line 238) | def on_document_error(
    method on_query_complete (line 250) | def on_query_complete(
    method on_query_error (line 256) | def on_query_error(
    method summary (line 263) | def summary(self) -> str:
    method reset (line 285) | def reset(self) -> None:
  class CallbackManager (line 290) | class CallbackManager:
    method __init__ (line 298) | def __init__(self) -> None:
    method register (line 304) | def register(self, callback: ProcessingCallback) -> None:
    method unregister (line 320) | def unregister(self, callback: ProcessingCallback) -> None:
    method enable_event_log (line 325) | def enable_event_log(self, enabled: bool = True) -> None:
    method event_log (line 335) | def event_log(self) -> List[ProcessingEvent]:
    method clear_event_log (line 340) | def clear_event_log(self) -> None:
    method dispatch (line 345) | def dispatch(self, event_name: str, **kwargs: Any) -> None:

FILE: raganything/config.py
  class RAGAnythingConfig (line 13) | class RAGAnythingConfig:
    method __post_init__ (line 111) | def __post_init__(self):
    method mineru_parse_method (line 126) | def mineru_parse_method(self) -> str:
    method mineru_parse_method (line 143) | def mineru_parse_method(self, value: str):

FILE: raganything/enhanced_markdown.py
  class MarkdownConfig (line 46) | class MarkdownConfig:
  class EnhancedMarkdownConverter (line 72) | class EnhancedMarkdownConverter:
    method __init__ (line 82) | def __init__(self, config: Optional[MarkdownConfig] = None):
    method _check_backends (line 96) | def _check_backends(self) -> Dict[str, bool]:
    method _get_default_css (line 113) | def _get_default_css(self) -> str:
    method _process_markdown_content (line 228) | def _process_markdown_content(self, content: str) -> str:
    method convert_with_weasyprint (line 286) | def convert_with_weasyprint(self, markdown_content: str, output_path: ...
    method convert_with_pandoc (line 310) | def convert_with_pandoc(
    method convert_markdown_to_pdf (line 370) | def convert_markdown_to_pdf(
    method convert_file_to_pdf (line 403) | def convert_file_to_pdf(
    method get_backend_info (line 446) | def get_backend_info(self) -> Dict[str, Any]:
    method _get_recommended_backend (line 460) | def _get_recommended_backend(self) -> str:
  function main (line 470) | def main():

FILE: raganything/modalprocessors.py
  class ContextConfig (line 34) | class ContextConfig:
    method __post_init__ (line 44) | def __post_init__(self):
  class ContextExtractor (line 49) | class ContextExtractor:
    method __init__ (line 52) | def __init__(self, config: ContextConfig = None, tokenizer=None):
    method extract_context (line 62) | def extract_context(
    method _extract_from_content_list (line 114) | def _extract_from_content_list(
    method _extract_page_context (line 133) | def _extract_page_context(
    method _extract_chunk_context (line 173) | def _extract_chunk_context(
    method _extract_text_from_item (line 206) | def _extract_text_from_item(self, item: Dict) -> str:
    method _extract_from_dict_source (line 238) | def _extract_from_dict_source(
    method _extract_from_text_source (line 265) | def _extract_from_text_source(
    method _extract_from_text_chunks (line 279) | def _extract_from_text_chunks(
    method _truncate_context (line 308) | def _truncate_context(self, context: str) -> str:
  class BaseModalProcessor (line 360) | class BaseModalProcessor:
    method __init__ (line 363) | def __init__(
    method set_content_source (line 406) | def set_content_source(self, content_source: Any, content_format: str ...
    method _get_context_for_item (line 417) | def _get_context_for_item(self, item_info: Dict[str, Any]) -> str:
    method generate_description_only (line 442) | async def generate_description_only(
    method _create_entity_and_chunk (line 465) | async def _create_entity_and_chunk(
    method _robust_json_parse (line 547) | def _robust_json_parse(self, response: str) -> dict:
    method _extract_all_json_candidates (line 573) | def _extract_all_json_candidates(self, response: str) -> list:
    method _try_parse_json (line 618) | def _try_parse_json(self, json_str: str) -> dict:
    method _basic_json_cleanup (line 628) | def _basic_json_cleanup(self, json_str: str) -> str:
    method _progressive_quote_fix (line 642) | def _progressive_quote_fix(self, json_str: str) -> str:
    method _extract_fields_with_regex (line 657) | def _extract_fields_with_regex(self, response: str) -> dict:
    method _extract_json_from_response (line 690) | def _extract_json_from_response(self, response: str) -> str:
    method _fix_json_escapes (line 695) | def _fix_json_escapes(self, json_str: str) -> str:
    method _process_chunk_for_extraction (line 699) | async def _process_chunk_for_extraction(
  class ImageModalProcessor (line 796) | class ImageModalProcessor(BaseModalProcessor):
    method __init__ (line 799) | def __init__(
    method _encode_image_to_base64 (line 814) | def _encode_image_to_base64(self, image_path: str) -> str:
    method generate_description_only (line 824) | async def generate_description_only(
    method process_multimodal_content (line 930) | async def process_multimodal_content(
    method _parse_response (line 993) | def _parse_response(
  class TableModalProcessor (line 1032) | class TableModalProcessor(BaseModalProcessor):
    method generate_description_only (line 1035) | async def generate_description_only(
    method process_multimodal_content (line 1125) | async def process_multimodal_content(
    method _parse_table_response (line 1187) | def _parse_table_response(
  class EquationModalProcessor (line 1226) | class EquationModalProcessor(BaseModalProcessor):
    method generate_description_only (line 1229) | async def generate_description_only(
    method process_multimodal_content (line 1313) | async def process_multimodal_content(
    method _parse_equation_response (line 1371) | def _parse_equation_response(
  class GenericModalProcessor (line 1410) | class GenericModalProcessor(BaseModalProcessor):
    method generate_description_only (line 1413) | async def generate_description_only(
    method process_multimodal_content (line 1487) | async def process_multimodal_content(
    method _parse_generic_response (line 1533) | def _parse_generic_response(

FILE: raganything/parser.py
  class MineruExecutionError (line 50) | class MineruExecutionError(Exception):
    method __init__ (line 53) | def __init__(self, return_code, error_msg):
  class Parser (line 61) | class Parser:
    method __init__ (line 76) | def __init__(self) -> None:
    method _unique_output_dir (line 81) | def _unique_output_dir(
    method convert_office_to_pdf (line 103) | def convert_office_to_pdf(
    method convert_text_to_pdf (line 243) | def convert_text_to_pdf(
    method _process_inline_markdown (line 480) | def _process_inline_markdown(cls, text: str) -> str:
    method parse_pdf (line 523) | def parse_pdf(
    method parse_image (line 547) | def parse_image(
    method parse_document (line 572) | def parse_document(
    method check_installation (line 596) | def check_installation(self) -> bool:
  class MineruParser (line 609) | class MineruParser(Parser):
    method __init__ (line 624) | def __init__(self) -> None:
    method _run_mineru_command (line 629) | def _run_mineru_command(
    method _read_output_files (line 860) | def _read_output_files(
    method parse_pdf (line 976) | def parse_pdf(
    method parse_image (line 1049) | def parse_image(
    method parse_office_doc (line 1200) | def parse_office_doc(
    method parse_text_file (line 1237) | def parse_text_file(
    method parse_document (line 1271) | def parse_document(
    method check_installation (line 1321) | def check_installation(self) -> bool:
  class DoclingParser (line 1355) | class DoclingParser(Parser):
    method __init__ (line 1366) | def __init__(self) -> None:
    method parse_pdf (line 1370) | def parse_pdf(
    method parse_document (line 1426) | def parse_document(
    method _run_docling_command (line 1469) | def _run_docling_command(
    method _read_output_files (line 1549) | def _read_output_files(
    method read_from_block_recursive (line 1599) | def read_from_block_recursive(
    method read_from_block (line 1637) | def read_from_block(
    method parse_office_doc (line 1697) | def parse_office_doc(
    method parse_html (line 1756) | def parse_html(
    method check_installation (line 1815) | def check_installation(self) -> bool:
  class PaddleOCRParser (line 1849) | class PaddleOCRParser(Parser):
    method __init__ (line 1852) | def __init__(self, default_lang: str = "en") -> None:
    method _require_paddleocr (line 1857) | def _require_paddleocr(self):
    method _get_ocr (line 1870) | def _get_ocr(self, lang: Optional[str] = None):
    method _extract_text_lines (line 1896) | def _extract_text_lines(self, result: Any) -> List[str]:
    method _ocr_input (line 1982) | def _ocr_input(
    method _extract_pdf_page_inputs (line 2002) | def _extract_pdf_page_inputs(self, pdf_path: Path) -> Iterator[Tuple[i...
    method _ocr_rendered_page (line 2034) | def _ocr_rendered_page(
    method parse_pdf (line 2055) | def parse_pdf(
    method parse_image (line 2087) | def parse_image(
    method parse_office_doc (line 2114) | def parse_office_doc(
    method parse_text_file (line 2126) | def parse_text_file(
    method parse_document (line 2138) | def parse_document(
    method check_installation (line 2166) | def check_installation(self) -> bool:
  function _normalize_parser_name (line 2174) | def _normalize_parser_name(name: str) -> str:
  function register_parser (line 2190) | def register_parser(name: str, parser_class: type) -> None:
  function unregister_parser (line 2247) | def unregister_parser(name: str) -> None:
  function list_parsers (line 2265) | def list_parsers() -> Dict[str, str]:
  function get_supported_parsers (line 2285) | def get_supported_parsers() -> tuple:
  function get_parser (line 2290) | def get_parser(parser_type: str) -> Parser:
  function main (line 2322) | def main():

FILE: raganything/processor.py
  class ProcessorMixin (line 26) | class ProcessorMixin:
    method _get_file_reference (line 29) | def _get_file_reference(self, file_path: str) -> str:
    method _generate_cache_key (line 44) | def _generate_cache_key(
    method _generate_content_based_doc_id (line 94) | def _generate_content_based_doc_id(self, content_list: List[Dict[str, ...
    method _get_cached_result (line 133) | async def _get_cached_result(
    method _store_cached_result (line 212) | async def _store_cached_result(
    method parse_document (line 280) | async def parse_document(
    method _process_multimodal_content (line 501) | async def _process_multimodal_content(
    method _process_multimodal_content_individual (line 614) | async def _process_multimodal_content_individual(
    method _process_multimodal_content_batch_type_aware (line 769) | async def _process_multimodal_content_batch_type_aware(
    method _convert_to_lightrag_chunks_type_aware (line 946) | def _convert_to_lightrag_chunks_type_aware(
    method _apply_chunk_template (line 994) | def _apply_chunk_template(
    method _store_chunks_to_lightrag_storage_type_aware (line 1069) | async def _store_chunks_to_lightrag_storage_type_aware(
    method _store_multimodal_main_entities (line 1086) | async def _store_multimodal_main_entities(
    method _store_multimodal_entities_to_full_entities (line 1180) | async def _store_multimodal_entities_to_full_entities(
    method _batch_extract_entities_lightrag_style_type_aware (line 1239) | async def _batch_extract_entities_lightrag_style_type_aware(
    method _batch_add_belongs_to_relations_type_aware (line 1268) | async def _batch_add_belongs_to_relations_type_aware(
    method _batch_merge_lightrag_style_type_aware (line 1332) | async def _batch_merge_lightrag_style_type_aware(
    method _update_doc_status_with_chunks_type_aware (line 1367) | async def _update_doc_status_with_chunks_type_aware(
    method _mark_multimodal_processing_complete (line 1408) | async def _mark_multimodal_processing_complete(self, doc_id: str):
    method is_document_fully_processed (line 1431) | async def is_document_fully_processed(self, doc_id: str) -> bool:
    method get_document_processing_status (line 1457) | async def get_document_processing_status(self, doc_id: str) -> Dict[st...
    method process_document_complete (line 1507) | async def process_document_complete(
    method process_document_complete_lightrag_api (line 1642) | async def process_document_complete_lightrag_api(
    method insert_content_list (line 1867) | async def insert_content_list(

FILE: raganything/query.py
  class QueryMixin (line 23) | class QueryMixin:
    method _generate_multimodal_cache_key (line 26) | def _generate_multimodal_cache_key(
    method aquery (line 101) | async def aquery(
    method aquery_with_multimodal (line 194) | async def aquery_with_multimodal(
    method aquery_vlm_enhanced (line 334) | async def aquery_vlm_enhanced(
    method _process_multimodal_query_content (line 403) | async def _process_multimodal_query_content(
    method _generate_query_content_description (line 456) | async def _generate_query_content_description(
    method _describe_image_for_query (line 486) | async def _describe_image_for_query(
    method _describe_table_for_query (line 517) | async def _describe_table_for_query(
    method _describe_equation_for_query (line 534) | async def _describe_equation_for_query(
    method _describe_generic_for_query (line 551) | async def _describe_generic_for_query(
    method _process_image_paths_for_vlm (line 570) | async def _process_image_paths_for_vlm(
    method _build_vlm_messages_with_images (line 689) | def _build_vlm_messages_with_images(
    method _call_vlm_with_multimodal_content (line 773) | async def _call_vlm_with_multimodal_content(self, messages: List[Dict]...
    method query (line 807) | def query(self, query: str, mode: str = "mix", **kwargs) -> str:
    method query_with_multimodal (line 825) | def query_with_multimodal(

FILE: raganything/raganything.py
  class RAGAnything (line 51) | class RAGAnything(QueryMixin, ProcessorMixin, BatchMixin):
    method __post_init__ (line 105) | def __post_init__(self):
    method close (line 140) | def close(self):
    method _create_context_config (line 158) | def _create_context_config(self) -> ContextConfig:
    method _create_context_extractor (line 169) | def _create_context_extractor(self) -> ContextExtractor:
    method _initialize_processors (line 181) | def _initialize_processors(self):
    method update_config (line 226) | def update_config(self, **kwargs):
    method _ensure_lightrag_initialized (line 235) | async def _ensure_lightrag_initialized(self):
    method finalize_storages (line 375) | async def finalize_storages(self):
    method check_parser_installation (line 421) | def check_parser_installation(self) -> bool:
    method verify_parser_installation_once (line 430) | def verify_parser_installation_once(self) -> bool:
    method get_config_info (line 441) | def get_config_info(self) -> Dict[str, Any]:
    method set_content_source_for_context (line 497) | def set_content_source_for_context(
    method update_context_config (line 525) | def update_context_config(self, **context_kwargs):
    method get_processor_info (line 557) | def get_processor_info(self) -> Dict[str, Any]:

FILE: raganything/utils.py
  function separate_content (line 13) | def separate_content(
  function encode_image_to_base64 (line 59) | def encode_image_to_base64(image_path: str) -> str:
  function validate_image_file (line 78) | def validate_image_file(image_path: str, max_size_mb: int = 50) -> bool:
  function insert_text_content (line 146) | async def insert_text_content(
  function insert_text_content_with_multimodal_content (line 181) | async def insert_text_content_with_multimodal_content(
  function get_processor_for_type (line 228) | def get_processor_for_type(modal_processors: Dict[str, Any], content_typ...
  function get_processor_supports (line 251) | def get_processor_supports(proc_type: str) -> List[str]:

FILE: setup.py
  function read_long_description (line 6) | def read_long_description():
  function retrieve_metadata (line 14) | def retrieve_metadata():
  function read_requirements (line 43) | def read_requirements():

FILE: tests/testpaddleocr_parser.py
  function test_supported_parsers_include_paddleocr (line 10) | def test_supported_parsers_include_paddleocr():
  function test_get_parser_returns_paddleocr_parser (line 14) | def test_get_parser_returns_paddleocr_parser():
  function test_get_parser_rejects_unknown_parser (line 19) | def test_get_parser_rejects_unknown_parser():
  function test_parser_module_import_does_not_import_paddleocr (line 24) | def test_parser_module_import_does_not_import_paddleocr():
  function test_check_installation_false_when_dependency_missing (line 30) | def test_check_installation_false_when_dependency_missing(monkeypatch):
  function test_check_installation_true_when_pdf_renderer_missing (line 40) | def test_check_installation_true_when_pdf_renderer_missing(monkeypatch):
  function test_parse_pdf_raises_import_error_when_pdf_renderer_missing (line 59) | def test_parse_pdf_raises_import_error_when_pdf_renderer_missing(monkeyp...
  function test_parse_image_raises_import_error_with_install_hint (line 81) | def test_parse_image_raises_import_error_with_install_hint(monkeypatch, ...
  function test_parse_image_returns_content_list_schema (line 95) | def test_parse_image_returns_content_list_schema(monkeypatch, tmp_path):
  function test_parse_image_preserves_repeated_ocr_lines (line 119) | def test_parse_image_preserves_repeated_ocr_lines(monkeypatch, tmp_path):
  function test_parse_pdf_assigns_page_index (line 143) | def test_parse_pdf_assigns_page_index(monkeypatch, tmp_path):

FILE: tests/testparser_kwargs.py
  function mineru_parser (line 25) | def mineru_parser():
  function docling_parser (line 30) | def docling_parser():
  function dummy_path (line 35) | def dummy_path():
  function test_mineru_env_propagation (line 42) | def test_mineru_env_propagation(
  function test_docling_env_propagation (line 68) | def test_docling_env_propagation(mock_run, docling_parser, dummy_path):
  function test_mineru_unknown_kwargs (line 82) | def test_mineru_unknown_kwargs(mineru_parser, dummy_path):
  function test_docling_unknown_kwargs (line 90) | def test_docling_unknown_kwargs(mock_run, docling_parser, dummy_path):
  function test_invalid_env_type (line 97) | def test_invalid_env_type(mineru_parser, docling_parser, dummy_path):
  function test_invalid_env_contents (line 106) | def test_invalid_env_contents(mineru_parser, docling_parser, dummy_path):

FILE: tests/testparser_wiring.py
  function test_batch_parser_uses_paddleocr_parser (line 6) | def test_batch_parser_uses_paddleocr_parser():
  function test_raganything_initializes_selected_parser (line 15) | def test_raganything_initializes_selected_parser(monkeypatch, tmp_path):
  function test_processor_parse_document_uses_selected_parser (line 45) | async def test_processor_parse_document_uses_selected_parser(monkeypatch...