sarvamai 0.1.23a6__py3-none-any.whl → 0.1.23a7__py3-none-any.whl

sarvamai/__init__.py

@@ -33,6 +33,21 @@ from .types import (
     CreateChatCompletionResponse,
     DiarizedEntry,
     DiarizedTranscript,
+    DocDigitizationCreateJobResponse,
+    DocDigitizationDownloadFilesResponse,
+    DocDigitizationErrorCode,
+    DocDigitizationErrorDetails,
+    DocDigitizationErrorMessage,
+    DocDigitizationJobDetail,
+    DocDigitizationJobDetailState,
+    DocDigitizationJobParameters,
+    DocDigitizationJobState,
+    DocDigitizationJobStatusResponse,
+    DocDigitizationOutputFormat,
+    DocDigitizationPageError,
+    DocDigitizationSupportedLanguage,
+    DocDigitizationUploadFilesResponse,
+    DocDigitizationWebhookCallback,
     ErrorCode,
     ErrorData,
     ErrorDetails,
@@ -112,6 +127,7 @@ from .errors import (
 )
 from . import (
     chat,
+    doc_digitization_job,
     speech_to_text,
     speech_to_text_job,
     speech_to_text_streaming,
@@ -147,6 +163,16 @@ from .requests import (
     CreateChatCompletionResponseParams,
     DiarizedEntryParams,
     DiarizedTranscriptParams,
+    DocDigitizationCreateJobResponseParams,
+    DocDigitizationDownloadFilesResponseParams,
+    DocDigitizationErrorDetailsParams,
+    DocDigitizationErrorMessageParams,
+    DocDigitizationJobDetailParams,
+    DocDigitizationJobParametersParams,
+    DocDigitizationJobStatusResponseParams,
+    DocDigitizationPageErrorParams,
+    DocDigitizationUploadFilesResponseParams,
+    DocDigitizationWebhookCallbackParams,
     ErrorDataParams,
     ErrorDetailsParams,
     ErrorMessageParams,
@@ -259,6 +285,31 @@ __all__ = [
     "DiarizedEntryParams",
     "DiarizedTranscript",
     "DiarizedTranscriptParams",
+    "DocDigitizationCreateJobResponse",
+    "DocDigitizationCreateJobResponseParams",
+    "DocDigitizationDownloadFilesResponse",
+    "DocDigitizationDownloadFilesResponseParams",
+    "DocDigitizationErrorCode",
+    "DocDigitizationErrorDetails",
+    "DocDigitizationErrorDetailsParams",
+    "DocDigitizationErrorMessage",
+    "DocDigitizationErrorMessageParams",
+    "DocDigitizationJobDetail",
+    "DocDigitizationJobDetailParams",
+    "DocDigitizationJobDetailState",
+    "DocDigitizationJobParameters",
+    "DocDigitizationJobParametersParams",
+    "DocDigitizationJobState",
+    "DocDigitizationJobStatusResponse",
+    "DocDigitizationJobStatusResponseParams",
+    "DocDigitizationOutputFormat",
+    "DocDigitizationPageError",
+    "DocDigitizationPageErrorParams",
+    "DocDigitizationSupportedLanguage",
+    "DocDigitizationUploadFilesResponse",
+    "DocDigitizationUploadFilesResponseParams",
+    "DocDigitizationWebhookCallback",
+    "DocDigitizationWebhookCallbackParams",
     "ErrorCode",
     "ErrorData",
     "ErrorDataParams",
@@ -386,6 +437,7 @@ __all__ = [
     "UnprocessableEntityError",
     "__version__",
     "chat",
+    "doc_digitization_job",
     "speech_to_text",
     "speech_to_text_job",
     "speech_to_text_streaming",

sarvamai/client.py

@@ -7,6 +7,7 @@ import httpx
 from .chat.client import AsyncChatClient, ChatClient
 from .core.api_error import ApiError
 from .core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
+from .doc_digitization_job.client import AsyncDocDigitizationJobClient, DocDigitizationJobClient
 from .environment import SarvamAIEnvironment
 from .speech_to_text.client import AsyncSpeechToTextClient, SpeechToTextClient
 from .speech_to_text_job.client import AsyncSpeechToTextJobClient, SpeechToTextJobClient
@@ -92,6 +93,7 @@ class SarvamAI:
         self.chat = ChatClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_job = SpeechToTextJobClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_job = SpeechToTextTranslateJobClient(client_wrapper=self._client_wrapper)
+        self.doc_digitization_job = DocDigitizationJobClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_streaming = SpeechToTextStreamingClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_streaming = SpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper
@@ -170,6 +172,7 @@ class AsyncSarvamAI:
         self.chat = AsyncChatClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_job = AsyncSpeechToTextJobClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_job = AsyncSpeechToTextTranslateJobClient(client_wrapper=self._client_wrapper)
+        self.doc_digitization_job = AsyncDocDigitizationJobClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_streaming = AsyncSpeechToTextStreamingClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_streaming = AsyncSpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper

sarvamai/core/client_wrapper.py

@@ -23,10 +23,10 @@ class BaseClientWrapper:
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "sarvamai/0.1.23a6",
+            "User-Agent": "sarvamai/0.1.23a7",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.23a6",
+            "X-Fern-SDK-Version": "0.1.23a7",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

sarvamai/doc_digitization_job/__init__.py

@@ -0,0 +1,4 @@
+# This file was auto-generated by Fern from our API Definition.
+
+# isort: skip_file
+

sarvamai/doc_digitization_job/client.py

@@ -0,0 +1,570 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
+from ..core.request_options import RequestOptions
+from ..requests.doc_digitization_job_parameters import DocDigitizationJobParametersParams
+from ..requests.doc_digitization_webhook_callback import DocDigitizationWebhookCallbackParams
+from ..types.doc_digitization_create_job_response import DocDigitizationCreateJobResponse
+from ..types.doc_digitization_download_files_response import DocDigitizationDownloadFilesResponse
+from ..types.doc_digitization_job_status_response import DocDigitizationJobStatusResponse
+from ..types.doc_digitization_upload_files_response import DocDigitizationUploadFilesResponse
+from .raw_client import AsyncRawDocDigitizationJobClient, RawDocDigitizationJobClient
+
+# this is used as the default value for optional parameters
+OMIT = typing.cast(typing.Any, ...)
+
+
+class DocDigitizationJobClient:
+    def __init__(self, *, client_wrapper: SyncClientWrapper):
+        self._raw_client = RawDocDigitizationJobClient(client_wrapper=client_wrapper)
+
+    @property
+    def with_raw_response(self) -> RawDocDigitizationJobClient:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        RawDocDigitizationJobClient
+        """
+        return self._raw_client
+
+    def initialise(
+        self,
+        *,
+        job_parameters: typing.Optional[DocDigitizationJobParametersParams] = OMIT,
+        callback: typing.Optional[DocDigitizationWebhookCallbackParams] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> DocDigitizationCreateJobResponse:
+        """
+        Creates a new document digitization job.
+
+        **Supported Languages:**
+        - `hi`: Hindi
+        - `en`: English
+        - `bn`: Bengali
+        - `gu`: Gujarati
+        - `kn`: Kannada
+        - `ml`: Malayalam
+        - `mr`: Marathi
+        - `or`: Odia
+        - `pa`: Punjabi
+        - `ta`: Tamil
+        - `te`: Telugu
+        - `ur`: Urdu
+        - `as`: Assamese
+        - `bodo`: Bodo
+        - `doi`: Dogri
+        - `ks`: Kashmiri
+        - `kok`: Konkani
+        - `mai`: Maithili
+        - `mni`: Manipuri
+        - `ne`: Nepali
+        - `sa`: Sanskrit
+        - `sat`: Santali
+        - `sd`: Sindhi
+
+        **Output Formats:**
+        - `html`: Structured HTML with layout preservation (default)
+        - `md`: Markdown format
+
+        **Webhook Callback:**
+        Optionally provide a callback URL to receive notification when processing completes.
+
+        Parameters
+        ----------
+        job_parameters : typing.Optional[DocDigitizationJobParametersParams]
+            Job configuration parameters. Omit the request body to use defaults.
+
+        callback : typing.Optional[DocDigitizationWebhookCallbackParams]
+            Optional webhook for completion notification
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        DocDigitizationCreateJobResponse
+            Successful Response
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+        client.doc_digitization_job.initialise()
+        """
+        _response = self._raw_client.initialise(
+            job_parameters=job_parameters, callback=callback, request_options=request_options
+        )
+        return _response.data
+
+    def get_upload_links(
+        self, *, job_id: str, files: typing.Sequence[str], request_options: typing.Optional[RequestOptions] = None
+    ) -> DocDigitizationUploadFilesResponse:
+        """
+        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
+        -------
+        DocDigitizationUploadFilesResponse
+            Successful Response
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+        client.doc_digitization_job.get_upload_links(
+            job_id="job_id",
+            files=["files"],
+        )
+        """
+        _response = self._raw_client.get_upload_links(job_id=job_id, files=files, request_options=request_options)
+        return _response.data
+
+    def start(
+        self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> DocDigitizationJobStatusResponse:
+        """
+        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
+        -------
+        DocDigitizationJobStatusResponse
+            Successful Response
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+        client.doc_digitization_job.start(
+            job_id="job_id",
+        )
+        """
+        _response = self._raw_client.start(job_id, request_options=request_options)
+        return _response.data
+
+    def get_status(
+        self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> DocDigitizationJobStatusResponse:
+        """
+        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
+        -------
+        DocDigitizationJobStatusResponse
+            Successful Response
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+        client.doc_digitization_job.get_status(
+            job_id="job_id",
+        )
+        """
+        _response = self._raw_client.get_status(job_id, request_options=request_options)
+        return _response.data
+
+    def get_download_links(
+        self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> DocDigitizationDownloadFilesResponse:
+        """
+        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
+        -------
+        DocDigitizationDownloadFilesResponse
+            Successful Response
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+        client.doc_digitization_job.get_download_links(
+            job_id="job_id",
+        )
+        """
+        _response = self._raw_client.get_download_links(job_id, request_options=request_options)
+        return _response.data
+
+
+class AsyncDocDigitizationJobClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._raw_client = AsyncRawDocDigitizationJobClient(client_wrapper=client_wrapper)
+
+    @property
+    def with_raw_response(self) -> AsyncRawDocDigitizationJobClient:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        AsyncRawDocDigitizationJobClient
+        """
+        return self._raw_client
+
+    async def initialise(
+        self,
+        *,
+        job_parameters: typing.Optional[DocDigitizationJobParametersParams] = OMIT,
+        callback: typing.Optional[DocDigitizationWebhookCallbackParams] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> DocDigitizationCreateJobResponse:
+        """
+        Creates a new document digitization job.
+
+        **Supported Languages:**
+        - `hi`: Hindi
+        - `en`: English
+        - `bn`: Bengali
+        - `gu`: Gujarati
+        - `kn`: Kannada
+        - `ml`: Malayalam
+        - `mr`: Marathi
+        - `or`: Odia
+        - `pa`: Punjabi
+        - `ta`: Tamil
+        - `te`: Telugu
+        - `ur`: Urdu
+        - `as`: Assamese
+        - `bodo`: Bodo
+        - `doi`: Dogri
+        - `ks`: Kashmiri
+        - `kok`: Konkani
+        - `mai`: Maithili
+        - `mni`: Manipuri
+        - `ne`: Nepali
+        - `sa`: Sanskrit
+        - `sat`: Santali
+        - `sd`: Sindhi
+
+        **Output Formats:**
+        - `html`: Structured HTML with layout preservation (default)
+        - `md`: Markdown format
+
+        **Webhook Callback:**
+        Optionally provide a callback URL to receive notification when processing completes.
+
+        Parameters
+        ----------
+        job_parameters : typing.Optional[DocDigitizationJobParametersParams]
+            Job configuration parameters. Omit the request body to use defaults.
+
+        callback : typing.Optional[DocDigitizationWebhookCallbackParams]
+            Optional webhook for completion notification
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        DocDigitizationCreateJobResponse
+            Successful Response
+
+        Examples
+        --------
+        import asyncio
+
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.doc_digitization_job.initialise()
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.initialise(
+            job_parameters=job_parameters, callback=callback, request_options=request_options
+        )
+        return _response.data
+
+    async def get_upload_links(
+        self, *, job_id: str, files: typing.Sequence[str], request_options: typing.Optional[RequestOptions] = None
+    ) -> DocDigitizationUploadFilesResponse:
+        """
+        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
+        -------
+        DocDigitizationUploadFilesResponse
+            Successful Response
+
+        Examples
+        --------
+        import asyncio
+
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.doc_digitization_job.get_upload_links(
+                job_id="job_id",
+                files=["files"],
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.get_upload_links(job_id=job_id, files=files, request_options=request_options)
+        return _response.data
+
+    async def start(
+        self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> DocDigitizationJobStatusResponse:
+        """
+        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
+        -------
+        DocDigitizationJobStatusResponse
+            Successful Response
+
+        Examples
+        --------
+        import asyncio
+
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.doc_digitization_job.start(
+                job_id="job_id",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.start(job_id, request_options=request_options)
+        return _response.data
+
+    async def get_status(
+        self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> DocDigitizationJobStatusResponse:
+        """
+        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
+        -------
+        DocDigitizationJobStatusResponse
+            Successful Response
+
+        Examples
+        --------
+        import asyncio
+
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.doc_digitization_job.get_status(
+                job_id="job_id",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.get_status(job_id, request_options=request_options)
+        return _response.data
+
+    async def get_download_links(
+        self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> DocDigitizationDownloadFilesResponse:
+        """
+        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
+        -------
+        DocDigitizationDownloadFilesResponse
+            Successful Response
+
+        Examples
+        --------
+        import asyncio
+
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.doc_digitization_job.get_download_links(
+                job_id="job_id",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.get_download_links(job_id, request_options=request_options)
+        return _response.data