o ưi$ @sJddlZddlmZmZmZmZddlZddlmZm Z m Z m Z m Z ddl mZddlmZddlmZmZddlTddlmZmZdd lmZeZd ed eed eed eeeffddZde d eeeffddZde d eeeffddZej de egedgdej de egedgde efde de defddZ!dS)N)AnyDictOptionalcast) APIRouterDependsRequestResponse UploadFile)ORJSONResponse)verbose_proxy_logger)%convert_file_document_to_url_document get_mime_type)*)UserAPIKeyAuthuser_api_key_auth)ProxyBaseLLMRequestProcessing file_contentfilename content_typereturncCsF|r |ddnd}|r|dkr|rt|}td||pddS)z Convert uploaded file bytes into a Mistral-format document dict with base64 data URI. Delegates to convert_file_document_to_url_document after resolving MIME type from the upload's content_type header or filename. ;rNzapplication/octet-streamfile)typer mime_type)splitstriprr )rrrrr\/home/app/Keep/.python/lib/python3.10/site-packages/litellm/proxy/ocr_endpoints/endpoints.py_build_document_from_uploads rrequestc sLz |IdH}Wnty }z tdt|dd}~ww|d}|dus4t|ts8t|ds8tdtt|}| dIdH| IdH}|sRtdt ||j |j d }d |i}|D],\}}|d vrlqct|trz t|||<Wqctjtfy|||<Yqcw|||<qctd |d d|dd|j |S)z Extract OCR data from a multipart form request. Uses the cached form if already parsed by auth middleware, otherwise parses the form from the request. Returns: A dict with 'document', 'model', and any other OCR params. Nz%Failed to parse multipart form data: u. When using curl with --form/-F, do NOT set the Content-Type header manually — curl will set it automatically with the required boundary.rreadzNMultipart OCR request must include a 'file' field with the document to processrzUploaded file is empty)rrrdocument)rr"z+OCR multipart form request parsed - model: modelz, document_type: rz , filename: )form Exception ValueErrorstrget isinstancer hasattrrseekr!rrritemsjsonloadsJSONDecodeErrorr debug) r r$eZ uploaded_filerr"data field_nameZ field_valuerrr_parse_multipart_form,s^      r4c s|jdd}d|vrt|IdHSz |IdH}Wn ty)d}Ynw|sDt|dddur@tdt|IdHSt dzt |}Wnt j y`}zt d |d d}~wwt |trk|d nd}t |tr}|d d kr}t d|S)a Parse an OCR request, supporting both JSON and multipart form data. JSON body (existing behavior): { "model": "mistral/mistral-ocr-latest", "document": {"type": "document_url", "document_url": "https://..."} } Multipart form data (new): - file: the uploaded file - model: model name (form field) - Any other OCR params as form fields (pages, include_image_base64, etc.) Returns: A dict suitable for passing to the OCR processing pipeline. z content-typezmultipart/form-dataNZ_formufOCR request body is empty but form data is available from middleware — processing as multipart form.zEmpty request body. For file uploads, use multipart/form-data content type with a file field. When using curl with --form/-F, do NOT set the Content-Type header manually.zInvalid JSON in request body: zy. Ensure the request body is valid JSON with Content-Type: application/json, or use multipart/form-data for file uploads.r"rrzdocument type 'file' is not supported through the JSON API. To upload a local file, use multipart/form-data with a 'file' field. For JSON requests, use 'document_url' or 'image_url' document types.)headersr(lowerr4body RuntimeErrorgetattrr r0r&orjsonr.r/r)dict)r rr9r2r1docrrr_parse_ocr_requestos@    r?z/v1/ocrocr) dependenciesresponse_classtagsz/ocrfastapi_responseuser_api_key_dictc sddlm}m}m}m}m}m}m} m} m } m } m } i}zFt |IdH}t |d}|jdid|d|d|dd d |d |d |d |d|ddd| d| d| d| d|d| IdHWSty}zt |d}|j|||| dIdHd}~ww)a OCR endpoint for extracting text from documents and images. Supports two input modes: **1. JSON body** (Mistral OCR API compatible): ```bash curl -X POST "http://localhost:4000/v1/ocr" -H "Authorization: Bearer sk-1234" -H "Content-Type: application/json" -d '{ "model": "mistral-ocr", "document": { "type": "document_url", "document_url": "https://arxiv.org/pdf/2201.04234" } }' ``` **2. Multipart form file upload**: ```bash curl -X POST "http://localhost:4000/v1/ocr" -H "Authorization: Bearer sk-1234" -F "model=mistral-ocr" -F "file=@document.pdf" ``` r) general_settings llm_router proxy_configproxy_logging_objselect_data_generator user_api_baseuser_max_tokens user_modeluser_request_timeoutuser_temperatureversionN)r2r rDrEZ route_typeZaocrrIrGrFrHrJr#rMrOrNrLrKrP)r1rErIrPr)Zlitellm.proxy.proxy_serverrFrGrHrIrJrKrLrMrNrOrPr?rZbase_process_llm_requestr%Z_handle_llm_api_exception)r rDrErFrGrHrIrJrKrLrMrNrOrPr2 processorr1rrrr@sb4,          )"r-typingrrrrr<Zfastapirrrr r Zfastapi.responsesr Zlitellm._loggingr Zlitellm.ocr.mainr rZlitellm.proxy._typesZ$litellm.proxy.auth.user_api_key_authrrZ'litellm.proxy.common_request_processingrZrouterbytesr'rr4r?postr@rrrrsT     CI