jn'dZddlZddlZddlmZddlmZmZmZm Z m Z ddl Z ddl Z ddl mZddlmZddlmZddlmZmZdd lmZdd lmZdd lmZmZeZe dd ed eeefde ede ede e e e jBfde ede eeefdefdZ"e dd ed eeefde ede ede e e e jBfde ede eeefde eeeeefffdZ#y)z Main OCR function for LiteLLM. N)partial)Any CoroutineDictOptionalUnion)verbose_logger)request_timeout)Logging) BaseOCRConfig OCRResponse)BaseLLMHTTPHandler)GenericLiteLLMParams)ProviderConfigManagerclientmodeldocumentapi_keyapi_basetimeoutcustom_llm_provider extra_headersreturnc Kt} tj} d|d<|tj||\} }} } t t f|||||||d|} tj} t | j| } | jd| d{}tj|r |d{}n|}|td||S787#t$r}tj|||||d}~wwxYww)a Async OCR function. Args: model: Model name (e.g., "mistral/mistral-ocr-latest") document: Document to process in Mistral format: {"type": "document_url", "document_url": "https://..."} for PDFs/docs or {"type": "image_url", "image_url": "https://..."} for images api_key: Optional API key api_base: Optional API base URL timeout: Optional timeout custom_llm_provider: Optional custom LLM provider extra_headers: Optional extra headers **kwargs: Additional parameters (e.g., include_image_base64, pages, image_limit) Returns: OCRResponse in Mistral OCR format with pages, model, usage_info, etc. Example: ```python import litellm # OCR with PDF response = await litellm.aocr( model="mistral/mistral-ocr-latest", document={ "type": "document_url", "document_url": "https://arxiv.org/pdf/2201.04234" }, include_image_base64=True ) # OCR with image response = await litellm.aocr( model="mistral/mistral-ocr-latest", document={ "type": "image_url", "image_url": "https://example.com/image.png" } ) # OCR with base64 encoded PDF response = await litellm.aocr( model="mistral/mistral-ocr-latest", document={ "type": "document_url", "document_url": f"data:application/pdf;base64,{base64_pdf}" } ) ``` TaocrN)rr)rrrrrrrz2Got an unexpected None response from the OCR API: rroriginal_exceptioncompletion_kwargs extra_kwargs)localsasyncioget_event_looplitellmget_llm_providerrocr contextvars copy_contextrunrun_in_executor iscoroutine ValueError Exceptionexception_type)rrrrrrrkwargs local_varsloop_funcctxfunc_with_context init_responseresponsees i/Users/manta/Documents/Projects/TheRoad-I1/backend/.venv/lib/python3.12/site-packages/litellm/ocr/main.pyrrs;|J, %%'v  &+2+C+Ch, (A"Aq    3'    &&(#CGGT2"2249JKK   } -**H$H  DXJO L+  $$ 3 (    sM DBCCC;C<CDCC D"C<<DDc t} |jd} |jdd} |jdddu} t|tst dt ||jd} | d vrt d | d tj|||| \}}} }| r| }|r|}tj|tj| }|t d|tjd|d|tdi|}|j|}i}|D]}||vs|j|||<|j!|i|}tjd|| j#||| |d|t$j'||||xst(| |||| ||t | }|S#t*$r}tj,|||||d}~wwxYw)a Synchronous OCR function. Args: model: Model name (e.g., "mistral/mistral-ocr-latest") document: Document to process in Mistral format: {"type": "document_url", "document_url": "https://..."} for PDFs/docs or {"type": "image_url", "image_url": "https://..."} for images api_key: Optional API key api_base: Optional API base URL timeout: Optional timeout custom_llm_provider: Optional custom LLM provider extra_headers: Optional extra headers **kwargs: Additional parameters (e.g., include_image_base64, pages, image_limit) Returns: OCRResponse in Mistral OCR format with pages, model, usage_info, etc. Example: ```python import litellm # OCR with PDF response = litellm.ocr( model="mistral/mistral-ocr-latest", document={ "type": "document_url", "document_url": "https://arxiv.org/pdf/2201.04234" }, include_image_base64=True ) # OCR with image response = litellm.ocr( model="mistral/mistral-ocr-latest", document={ "type": "image_url", "image_url": "https://example.com/image.png" } ) # OCR with base64 encoded PDF response = litellm.ocr( model="mistral/mistral-ocr-latest", document={ "type": "document_url", "document_url": f"data:application/pdf;base64,{base64_pdf}" } ) # Access pages for page in response.pages: print(f"Page {page.index}: {page.markdown}") ``` litellm_logging_objlitellm_call_idNrFTz7document must be a dict with 'type' and URL field, got type) document_url image_urlzInvalid document type: z'. Must be 'document_url' or 'image_url')rrrr)rproviderz#OCR is not supported for provider: zOCR call - model: z , provider: )r)non_default_paramsoptional_paramsrz#OCR optional_params after mapping: )r;r)rrAlitellm_paramsr) rrrAr logging_objrrrrheadersprovider_configrBr)r popget isinstancedictr+r<r#r$rget_provider_ocr_config LlmProvidersr debugrget_supported_ocr_paramsmap_ocr_paramsupdate_environment_variablesbase_llm_http_handlerr%r r,r-)rrrrrrrr.r/r:r; _is_asyncdoc_typedynamic_api_keydynamic_api_baseocr_provider_configrBsupported_paramsr@paramrAr6r7s r8r%r%svDJc 17ris88 +-SOI57+,""59)-.2j j 38nj c]j sm j eE5==01 2 j "# j DcN+j j j Z""59)-.2e e 38ne c]e sm e eE5==01 2 e "# e DcN+e  ; #sK"78 89e e rh