o qmi@s"ddlZddlmZddlmZddlmZmZddlm Z m Z ddl m Z ddl mZdd lmZdd lmZdd lmZdd lmZdd lmZddlmZddlmZddlmZddlm Z ddl!m"Z"ddl#m$Z$ddl%m&Z&ddl'm(Z(e)ej*dZ+GdddZ,GdddZ-dS)N)JSONDecodeError)ApiError)AsyncClientWrapperSyncClientWrapper)AsyncHttpResponse HttpResponse)jsonable_encoder) parse_obj_as)RequestOptions)'convert_and_respect_annotation_metadata)BadRequestError)ForbiddenError)InternalServerError)ServiceUnavailableError)TooManyRequestsError)"DocDigitizationJobParametersParams)$DocDigitizationWebhookCallbackParams) DocDigitizationCreateJobResponse)$DocDigitizationDownloadFilesResponse) DocDigitizationJobStatusResponse)"DocDigitizationUploadFilesResponse.c @eZdZdefddZeedddejedeje deje d e e fd d Z dd d edejedeje d e efddZdd d edeje d e efddZdd d edeje d e efddZdd d edeje d e efddZdS)RawDocumentIntelligenceClientclient_wrappercC ||_dSN_client_wrapperselfrr!]/home/ubuntu/.local/lib/python3.10/site-packages/sarvamai/document_intelligence/raw_client.py__init__ z&RawDocumentIntelligenceClient.__init__Njob_parameterscallbackrequest_optionsr&r'r(returnc Cs |jjjd|jjdt|tddt|tdddddi|td}zd |j kr-d krBnnt t t t |d }t||d WS|j d krbtt|jt t jt jt t jt j|d d|j dkrtt|jt t jt jt t jt j|d d|j dkrtt|jt t jt jt t jt j|d d|j dkrtt|jt t jt jt t jt j|d d|j dkrtt|jt t jt jt t jt j|d d|}Wntyt|j t|j|jdwt|j t|j|d)a@ Creates a new Document Intelligence job. **Supported Languages (BCP-47 format):** - `hi-IN`: Hindi (default) - `en-IN`: English - `bn-IN`: Bengali - `gu-IN`: Gujarati - `kn-IN`: Kannada - `ml-IN`: Malayalam - `mr-IN`: Marathi - `or-IN`: Odia - `pa-IN`: Punjabi - `ta-IN`: Tamil - `te-IN`: Telugu - `ur-IN`: Urdu - `as-IN`: Assamese - `bodo-IN`: Bodo - `doi-IN`: Dogri - `ks-IN`: Kashmiri - `kok-IN`: Konkani - `mai-IN`: Maithili - `mni-IN`: Manipuri - `ne-IN`: Nepali - `sa-IN`: Sanskrit - `sat-IN`: Santali - `sd-IN`: Sindhi **Output Formats (delivered as ZIP file):** - `html`: Structured HTML files with layout preservation - `md`: Markdown files (default) - `json`: Structured JSON files for programmatic processing Parameters ---------- job_parameters : typing.Optional[DocDigitizationJobParametersParams] Configuration parameters for the Document Intelligence job including language and output format. Defaults to Hindi (hi-IN) and Markdown output if omitted. callback : typing.Optional[DocDigitizationWebhookCallbackParams] Optional webhook for completion notification request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DocDigitizationCreateJobResponse] Successful Response doc-digitization/job/v1POSTwriteobject_ annotation directionr&r' content-typeapplication/jsonbase_urlmethodjsonheadersr(omit,type_r.responsedatar8body status_coder8rC)r httpx_clientrequestget_environmentbaser rrOMITrItypingcastrr r7rr dictr8OptionalAnyrrrrrrtextr r&r'r( _response_data_response_jsonr!r!r" initialise!s8                  z(RawDocumentIntelligenceClient.initialiser(job_idfilesc Cs|jjjd|jjd||dddi|td}zd|jkr#dkr8nntt t t | d }t ||d WS|jd krXt t|jttjtjt tjtj| d d |jd krxtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d | }Wntyt|jt|j|jdwt|jt|j|d)a Returns presigned URLs for uploading input files. **File Constraints:** - Exactly one file required (PDF or ZIP) - PDF files: `.pdf` extension - ZIP files: `.zip` extension Parameters ---------- job_id : str Job identifier returned from Create Job files : typing.Sequence[str] List of filenames to upload (exactly 1 file: PDF or ZIP) request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DocDigitizationUploadFilesResponse] Successful Response $doc-digitization/job/v1/upload-filesr+r[r\r2r3r4r:r;r<r>rArBrDrErFrGrH)rrJrKrLrMrNrIrOrPrr r7rr rQr8rRrSrrrrrrrTr r[r\r(rVrWrXr!r!r"get_upload_linkss                 z.RawDocumentIntelligenceClient.get_upload_linksc C|jjjdt|d|jjd|d}zd|jkr!dkr6nntt t t | d}t ||dWS|jd krVt t|jttjtjt tjtj| dd |jd krvtt|jttjtjt tjtj| dd |jd krtt|jttjtjt tjtj| dd |jd krtt|jttjtjt tjtj| dd |jdkrtt|jttjtjt tjtj| dd | }Wntyt|jt|j|jdwt|jt|j|d)a Validates the uploaded file and starts processing. **Validation Checks:** - File must be uploaded before starting - File size must not exceed 200 MB - PDF must be parseable by the PDF parser - ZIP must contain only JPEG/PNG images - ZIP must be flat (no nested folders beyond one level) - ZIP must contain at least one valid image - Page/image count must not exceed 500 - User must have sufficient credits **Processing:** Job runs asynchronously. Poll the status endpoint or use webhook callback for completion notification. Parameters ---------- job_id : str The unique identifier of the job request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DocDigitizationJobStatusResponse] Successful Response doc-digitization/job/v1//startr+r5r6r(r:r;r<r>rArBrDrErFrGrHrrJrKr rLrMrIrOrPrr r7rr rQr8rRrSrrrrrrrTr r[r(rVrWrXr!r!r"start s                  z#RawDocumentIntelligenceClient.startc Cra)a Returns the current status of a job with page-level metrics. **Job States:** - `Accepted`: Job created, awaiting file upload - `Pending`: File uploaded, waiting to start - `Running`: Processing in progress - `Completed`: All pages processed successfully - `PartiallyCompleted`: Some pages succeeded, some failed - `Failed`: All pages failed or job-level error **Page Metrics:** Response includes detailed progress: total pages, pages processed, succeeded, failed, and per-page errors. Parameters ---------- job_id : str The unique identifier of the job request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DocDigitizationJobStatusResponse] Successful Response rb/statusGETrdr:r;r<r>rArBrDrErFrGrHrerfr!r!r" get_statuss                 z(RawDocumentIntelligenceClient.get_statusc Cra)a  Returns presigned URLs for downloading output files. **Prerequisites:** - Job must be in `Completed` or `PartiallyCompleted` state - Failed jobs have no output available Parameters ---------- job_id : str The unique identifier of the job request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DocDigitizationDownloadFilesResponse] Successful Response rb/download-filesr+rdr:r;r<r>rArBrDrErFrGrH)rrJrKr rLrMrIrOrPrr r7rr rQr8rRrSrrrrrrrTrfr!r!r"get_download_linkss                 z0RawDocumentIntelligenceClient.get_download_links)__name__ __module__ __qualname__rr#rNrOrRrrr rrrYstrSequencerr`rrgrjrrlr!r!r!r"rb  p m krc @r)"AsyncRawDocumentIntelligenceClientrcCrrrrr!r!r"r#[r$z+AsyncRawDocumentIntelligenceClient.__init__Nr%r&r'r(r)c s|jjjd|jjdt|tddt|tdddddi|tdId H}zd |j kr1d krFnnt t t t |d }t||d WS|j dkrftt|jt t jt jt t jt j|d d|j dkrtt|jt t jt jt t jt j|d d|j dkrtt|jt t jt jt t jt j|d d|j dkrtt|jt t jt jt t jt j|d d|j dkrtt|jt t jt jt t jt j|d d|}Wntyt|j t|j|jdwt|j t|j|d)aE Creates a new Document Intelligence job. **Supported Languages (BCP-47 format):** - `hi-IN`: Hindi (default) - `en-IN`: English - `bn-IN`: Bengali - `gu-IN`: Gujarati - `kn-IN`: Kannada - `ml-IN`: Malayalam - `mr-IN`: Marathi - `or-IN`: Odia - `pa-IN`: Punjabi - `ta-IN`: Tamil - `te-IN`: Telugu - `ur-IN`: Urdu - `as-IN`: Assamese - `bodo-IN`: Bodo - `doi-IN`: Dogri - `ks-IN`: Kashmiri - `kok-IN`: Konkani - `mai-IN`: Maithili - `mni-IN`: Manipuri - `ne-IN`: Nepali - `sa-IN`: Sanskrit - `sat-IN`: Santali - `sd-IN`: Sindhi **Output Formats (delivered as ZIP file):** - `html`: Structured HTML files with layout preservation - `md`: Markdown files (default) - `json`: Structured JSON files for programmatic processing Parameters ---------- job_parameters : typing.Optional[DocDigitizationJobParametersParams] Configuration parameters for the Document Intelligence job including language and output format. Defaults to Hindi (hi-IN) and Markdown output if omitted. callback : typing.Optional[DocDigitizationWebhookCallbackParams] Optional webhook for completion notification request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DocDigitizationCreateJobResponse] Successful Response r*r+r,r-r1r2r3r4Nr:r;r<r>rArBrDrErFrGrH)rrJrKrLrMr rrrNrIrOrPrr r7rr rQr8rRrSrrrrrrrTrUr!r!r"rY^s8                   z-AsyncRawDocumentIntelligenceClient.initialiserZr[r\c s|jjjd|jjd||dddi|tdIdH}zd|jkr'd krrArBrDrErFrGrH)rrJrKrLrMrNrIrOrPrr r7rr rQr8rRrSrrrrrrrTr_r!r!r"r`s                  z3AsyncRawDocumentIntelligenceClient.get_upload_linksc |jjjdt|d|jjd|dIdH}zd|jkr%dkr:nntt t t | d}t ||d WS|jd krZt t|jttjtjt tjtj| dd |jd krztt|jttjtjt tjtj| dd |jd krtt|jttjtjt tjtj| dd |jdkrtt|jttjtjt tjtj| dd |jdkrtt|jttjtjt tjtj| dd | }Wntyt|jt|j|jdwt|jt|j|d)a Validates the uploaded file and starts processing. **Validation Checks:** - File must be uploaded before starting - File size must not exceed 200 MB - PDF must be parseable by the PDF parser - ZIP must contain only JPEG/PNG images - ZIP must be flat (no nested folders beyond one level) - ZIP must contain at least one valid image - Page/image count must not exceed 500 - User must have sufficient credits **Processing:** Job runs asynchronously. Poll the status endpoint or use webhook callback for completion notification. Parameters ---------- job_id : str The unique identifier of the job request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DocDigitizationJobStatusResponse] Successful Response rbrcr+rdNr:r;r<r>rArBrDrErFrGrHrrJrKr rLrMrIrOrPrr r7rr rQr8rRrSrrrrrrrTrfr!r!r"rg]s                   z(AsyncRawDocumentIntelligenceClient.startc rt)a Returns the current status of a job with page-level metrics. **Job States:** - `Accepted`: Job created, awaiting file upload - `Pending`: File uploaded, waiting to start - `Running`: Processing in progress - `Completed`: All pages processed successfully - `PartiallyCompleted`: Some pages succeeded, some failed - `Failed`: All pages failed or job-level error **Page Metrics:** Response includes detailed progress: total pages, pages processed, succeeded, failed, and per-page errors. Parameters ---------- job_id : str The unique identifier of the job request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DocDigitizationJobStatusResponse] Successful Response rbrhrirdNr:r;r<r>rArBrDrErFrGrHrurfr!r!r"rjs                  z-AsyncRawDocumentIntelligenceClient.get_statusc rt)a% Returns presigned URLs for downloading output files. **Prerequisites:** - Job must be in `Completed` or `PartiallyCompleted` state - Failed jobs have no output available Parameters ---------- job_id : str The unique identifier of the job request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DocDigitizationDownloadFilesResponse] Successful Response rbrkr+rdNr:r;r<r>rArBrDrErFrGrH)rrJrKr rLrMrIrOrPrr r7rr rQr8rRrSrrrrrrrTrfr!r!r"rl3s                  z5AsyncRawDocumentIntelligenceClient.get_download_links)rmrnrorr#rNrOrRrrr rrrYrprqrr`rrgrjrrlr!r!r!r"rsZrrrs).rO json.decoderrcore.api_errorrcore.client_wrapperrrcore.http_responserrcore.jsonable_encoderr core.pydantic_utilitiesr core.request_optionsr core.serializationr errors.bad_request_errorr errors.forbidden_errorrerrors.internal_server_errorr errors.service_unavailable_errorrerrors.too_many_requests_errorr(requests.doc_digitization_job_parametersr*requests.doc_digitization_webhook_callbackr*types.doc_digitization_create_job_responser.types.doc_digitization_download_files_responser*types.doc_digitization_job_status_responser,types.doc_digitization_upload_files_responserrPrSrNrrsr!r!r!r"s6                 A