sarvamai 0.1.23a7__py3-none-any.whl → 0.1.23a8__py3-none-any.whl

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/0.1.23a7",
+            "User-Agent": "sarvamai/0.1.23a8",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.23a7",
+            "X-Fern-SDK-Version": "0.1.23a8",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

sarvamai/doc_digitization_job/client.py

@@ -1,16 +1,32 @@
 # This file was auto-generated by Fern from our API Definition.
+# 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 ..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 ..types.doc_digitization_supported_language import DocDigitizationSupportedLanguage
+from ..types.doc_digitization_output_format import DocDigitizationOutputFormat
 from .raw_client import AsyncRawDocDigitizationJobClient, RawDocDigitizationJobClient
+from .job import DocDigitizationJob, AsyncDocDigitizationJob
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -99,12 +115,18 @@ class DocDigitizationJobClient:
         client.doc_digitization_job.initialise()
         """
         _response = self._raw_client.initialise(
-            job_parameters=job_parameters, callback=callback, request_options=request_options
+            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
+        self,
+        *,
+        job_id: str,
+        files: typing.Sequence[str],
+        request_options: typing.Optional[RequestOptions] = None,
     ) -> DocDigitizationUploadFilesResponse:
         """
         Returns presigned URLs for uploading input files.
@@ -142,7 +164,9 @@ class DocDigitizationJobClient:
             files=["files"],
         )
         """
-        _response = self._raw_client.get_upload_links(job_id=job_id, files=files, request_options=request_options)
+        _response = self._raw_client.get_upload_links(
+            job_id=job_id, files=files, request_options=request_options
+        )
         return _response.data
 
     def start(
@@ -269,13 +293,97 @@ class DocDigitizationJobClient:
             job_id="job_id",
         )
         """
-        _response = self._raw_client.get_download_links(job_id, request_options=request_options)
+        _response = self._raw_client.get_download_links(
+            job_id, request_options=request_options
+        )
         return _response.data
 
+    def create_job(
+        self,
+        language: DocDigitizationSupportedLanguage = "hi",
+        output_format: DocDigitizationOutputFormat = "html",
+        callback: typing.Optional[DocDigitizationWebhookCallbackParams] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> DocDigitizationJob:
+        """
+        Create a new Document Digitization job.
+
+        Parameters
+        ----------
+        language : DocDigitizationSupportedLanguage, default="hi"
+            ISO language code for the document.
+
+        output_format : DocDigitizationOutputFormat, default="html"
+            Output format: "html" for structured HTML or "md" for Markdown.
+
+        callback : typing.Optional[DocDigitizationWebhookCallbackParams], default=OMIT
+            Optional webhook configuration for job completion notification.
+
+        request_options : typing.Optional[RequestOptions], default=None
+            Request-specific configuration.
+
+        Returns
+        -------
+        DocDigitizationJob
+            A handle to the newly created Document Digitization job.
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(api_subscription_key="YOUR_API_SUBSCRIPTION_KEY")
+
+        # Create job and get handle
+        job = client.doc_digitization_job.create_job(language="hi", output_format="md")
+
+        # Upload PDF, start, wait, download
+        job.upload_file("/path/to/document.pdf")
+        job.start()
+        job.wait_until_complete()
+        job.download_output("./output.md")
+        """
+        response = self.initialise(
+            job_parameters=DocDigitizationJobParametersParams(
+                language=language,
+                output_format=output_format,
+            ),
+            callback=callback,
+            request_options=request_options,
+        )
+        return DocDigitizationJob(job_id=response.job_id, client=self)
+
+    def get_job(self, job_id: str) -> DocDigitizationJob:
+        """
+        Get an existing Document Digitization job handle by job ID.
+
+        Parameters
+        ----------
+        job_id : str
+            The job ID of a previously created Document Digitization job.
+
+        Returns
+        -------
+        DocDigitizationJob
+            A job handle which can be used to check status, upload files, or download results.
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(api_subscription_key="YOUR_API_SUBSCRIPTION_KEY")
+
+        # Get existing job
+        job = client.doc_digitization_job.get_job(job_id="your-job-uuid")
+        status = job.get_status()
+        """
+        return DocDigitizationJob(job_id=job_id, client=self)
+
 
 class AsyncDocDigitizationJobClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
-        self._raw_client = AsyncRawDocDigitizationJobClient(client_wrapper=client_wrapper)
+        self._raw_client = AsyncRawDocDigitizationJobClient(
+            client_wrapper=client_wrapper
+        )
 
     @property
     def with_raw_response(self) -> AsyncRawDocDigitizationJobClient:
@@ -364,12 +472,18 @@ class AsyncDocDigitizationJobClient:
         asyncio.run(main())
         """
         _response = await self._raw_client.initialise(
-            job_parameters=job_parameters, callback=callback, request_options=request_options
+            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
+        self,
+        *,
+        job_id: str,
+        files: typing.Sequence[str],
+        request_options: typing.Optional[RequestOptions] = None,
     ) -> DocDigitizationUploadFilesResponse:
         """
         Returns presigned URLs for uploading input files.
@@ -415,7 +529,9 @@ class AsyncDocDigitizationJobClient:
 
         asyncio.run(main())
         """
-        _response = await self._raw_client.get_upload_links(job_id=job_id, files=files, request_options=request_options)
+        _response = await self._raw_client.get_upload_links(
+            job_id=job_id, files=files, request_options=request_options
+        )
         return _response.data
 
     async def start(
@@ -469,7 +585,9 @@ class AsyncDocDigitizationJobClient:
 
         asyncio.run(main())
         """
-        _response = await self._raw_client.start(job_id, request_options=request_options)
+        _response = await self._raw_client.start(
+            job_id, request_options=request_options
+        )
         return _response.data
 
     async def get_status(
@@ -521,7 +639,9 @@ class AsyncDocDigitizationJobClient:
 
         asyncio.run(main())
         """
-        _response = await self._raw_client.get_status(job_id, request_options=request_options)
+        _response = await self._raw_client.get_status(
+            job_id, request_options=request_options
+        )
         return _response.data
 
     async def get_download_links(
@@ -566,5 +686,91 @@ class AsyncDocDigitizationJobClient:
 
         asyncio.run(main())
         """
-        _response = await self._raw_client.get_download_links(job_id, request_options=request_options)
+        _response = await self._raw_client.get_download_links(
+            job_id, request_options=request_options
+        )
         return _response.data
+
+    async def create_job(
+        self,
+        language: DocDigitizationSupportedLanguage = "hi",
+        output_format: DocDigitizationOutputFormat = "html",
+        callback: typing.Optional[DocDigitizationWebhookCallbackParams] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncDocDigitizationJob:
+        """
+        Create a new Document Digitization job.
+
+        Parameters
+        ----------
+        language : DocDigitizationSupportedLanguage, default="hi"
+            ISO language code for the document.
+
+        output_format : DocDigitizationOutputFormat, default="html"
+            Output format: "html" for structured HTML or "md" for Markdown.
+
+        callback : typing.Optional[DocDigitizationWebhookCallbackParams], default=OMIT
+            Optional webhook configuration for job completion notification.
+
+        request_options : typing.Optional[RequestOptions], default=None
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncDocDigitizationJob
+            A handle to the newly created Document Digitization job.
+
+        Examples
+        --------
+        import asyncio
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(api_subscription_key="YOUR_API_SUBSCRIPTION_KEY")
+
+        async def main():
+            job = await client.doc_digitization_job.create_job(language="hi", output_format="md")
+            await job.upload_file("/path/to/document.pdf")
+            await job.start()
+            await job.wait_until_complete()
+            await job.download_output("./output.md")
+
+        asyncio.run(main())
+        """
+        response = await self.initialise(
+            job_parameters=DocDigitizationJobParametersParams(
+                language=language,
+                output_format=output_format,
+            ),
+            callback=callback,
+            request_options=request_options,
+        )
+        return AsyncDocDigitizationJob(job_id=response.job_id, client=self)
+
+    def get_job(self, job_id: str) -> AsyncDocDigitizationJob:
+        """
+        Get an existing Document Digitization job handle by job ID.
+
+        Parameters
+        ----------
+        job_id : str
+            The job ID of a previously created Document Digitization job.
+
+        Returns
+        -------
+        AsyncDocDigitizationJob
+            A job handle which can be used to check status, upload files, or download results.
+
+        Examples
+        --------
+        import asyncio
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(api_subscription_key="YOUR_API_SUBSCRIPTION_KEY")
+
+        async def main():
+            job = client.doc_digitization_job.get_job(job_id="your-job-uuid")
+            status = await job.get_status()
+
+        asyncio.run(main())
+        """
+        return AsyncDocDigitizationJob(job_id=job_id, client=self)

sarvamai/doc_digitization_job/job.py

@@ -0,0 +1,496 @@
+"""
+Document Digitization Job helper classes.
+
+This module provides high-level abstractions for managing document digitization jobs,
+including file uploads, status polling, and output downloads.
+"""
+
+import asyncio
+import mimetypes
+import os
+import time
+import typing
+
+import httpx
+from http import HTTPStatus
+
+from ..types.doc_digitization_job_status_response import (
+    DocDigitizationJobStatusResponse,
+)
+
+if typing.TYPE_CHECKING:
+    from .client import AsyncDocDigitizationJobClient, DocDigitizationJobClient
+
+
+class AsyncDocDigitizationJob:
+    """
+    Async helper class for managing a Document Digitization job.
+
+    Provides high-level methods for uploading files, starting the job,
+    polling for completion, and downloading outputs.
+    """
+
+    def __init__(self, job_id: str, client: "AsyncDocDigitizationJobClient"):
+        """
+        Initialize the asynchronous document digitization job.
+
+        Parameters
+        ----------
+        job_id : str
+            The unique identifier for the job.
+        client : AsyncDocDigitizationJobClient
+            The async client instance to use for API calls.
+        """
+        self._job_id = job_id
+        self._client = client
+
+    @property
+    def job_id(self) -> str:
+        """Returns the job ID associated with this job instance."""
+        return self._job_id
+
+    async def upload_file(self, file_path: str, timeout: float = 120.0) -> bool:
+        """
+        Upload the input PDF or ZIP file for the document digitization job.
+
+        Parameters
+        ----------
+        file_path : str
+            Path to the PDF or ZIP file to upload.
+        timeout : float, default=120.0
+            Timeout in seconds for the upload request.
+
+        Returns
+        -------
+        bool
+            True if upload was successful.
+
+        Raises
+        ------
+        ValueError
+            If the file is not a PDF or ZIP file.
+        FileNotFoundError
+            If the file does not exist.
+        httpx.HTTPStatusError
+            If the upload request fails.
+        """
+        if not os.path.exists(file_path):
+            raise FileNotFoundError(f"File not found: {file_path}")
+
+        ext = os.path.splitext(file_path)[1].lower()
+        if ext not in [".pdf", ".zip"]:
+            raise ValueError(f"Only PDF or ZIP files are supported, got: {ext}")
+
+        file_name = os.path.basename(file_path)
+
+        # Get upload URL
+        upload_response = await self._client.get_upload_links(
+            job_id=self._job_id,
+            files=[file_name],
+        )
+
+        if not upload_response.upload_urls:
+            raise ValueError("No upload URL returned from API")
+
+        upload_detail = list(upload_response.upload_urls.values())[0]
+        upload_url = upload_detail.file_url
+
+        # Determine content type
+        content_type, _ = mimetypes.guess_type(file_path)
+        if content_type is None:
+            content_type = "application/octet-stream"
+
+        # Upload the file
+        async with httpx.AsyncClient(timeout=timeout) as http_client:
+            with open(file_path, "rb") as f:
+                file_content = f.read()
+
+            response = await http_client.put(
+                upload_url,
+                content=file_content,
+                headers={
+                    "Content-Type": content_type,
+                    "x-ms-blob-type": "BlockBlob",
+                },
+            )
+            response.raise_for_status()
+
+        return True
+
+    async def start(self) -> DocDigitizationJobStatusResponse:
+        """
+        Start the document digitization job processing.
+
+        Returns
+        -------
+        DocDigitizationJobStatusResponse
+            The job status after starting.
+        """
+        return await self._client.start(job_id=self._job_id)
+
+    async def get_status(self) -> DocDigitizationJobStatusResponse:
+        """
+        Retrieve the current status of the job.
+
+        Returns
+        -------
+        DocDigitizationJobStatusResponse
+            The current job status.
+        """
+        return await self._client.get_status(self._job_id)
+
+    async def wait_until_complete(
+        self, poll_interval: int = 5, timeout: int = 1800
+    ) -> DocDigitizationJobStatusResponse:
+        """
+        Polls job status until it completes, partially completes, or fails.
+
+        Parameters
+        ----------
+        poll_interval : int, default=5
+            Seconds between status checks.
+        timeout : int, default=1800
+            Maximum seconds to wait before raising TimeoutError.
+
+        Returns
+        -------
+        DocDigitizationJobStatusResponse
+            The final job status.
+
+        Raises
+        ------
+        TimeoutError
+            If the job does not complete within the timeout period.
+        """
+        start_time = time.time()
+        terminal_states = {"completed", "partiallycompleted", "failed"}
+
+        while True:
+            status = await self.get_status()
+
+            if status.job_state and status.job_state.lower() in terminal_states:
+                return status
+
+            elapsed = time.time() - start_time
+            if elapsed >= timeout:
+                raise TimeoutError(
+                    f"Job {self._job_id} did not complete within {timeout} seconds. "
+                    f"Current state: {status.job_state}"
+                )
+
+            await asyncio.sleep(poll_interval)
+
+    async def download_output(self, output_path: str, timeout: float = 120.0) -> bool:
+        """
+        Download the output file (HTML or Markdown) to the specified path.
+
+        Parameters
+        ----------
+        output_path : str
+            Path where the output file should be saved.
+        timeout : float, default=120.0
+            Timeout in seconds for the download request.
+
+        Returns
+        -------
+        bool
+            True if download was successful.
+
+        Raises
+        ------
+        ValueError
+            If no download URL is available.
+        httpx.HTTPStatusError
+            If the download request fails.
+        """
+        download_response = await self._client.get_download_links(job_id=self._job_id)
+
+        if not download_response.download_urls:
+            raise ValueError("No download URL returned from API")
+
+        download_detail = list(download_response.download_urls.values())[0]
+        download_url = download_detail.file_url
+
+        async with httpx.AsyncClient(timeout=timeout) as http_client:
+            response = await http_client.get(download_url)
+            response.raise_for_status()
+
+            # Ensure output directory exists
+            os.makedirs(os.path.dirname(os.path.abspath(output_path)), exist_ok=True)
+
+            with open(output_path, "wb") as f:
+                f.write(response.content)
+
+        return True
+
+    async def get_page_metrics(self) -> typing.Optional[typing.Dict[str, int]]:
+        """
+        Get page processing metrics from the job status.
+
+        Returns
+        -------
+        typing.Optional[typing.Dict[str, int]]
+            Dictionary with keys: total_pages, pages_processed, pages_succeeded, pages_failed.
+            Returns None if job_detail is not available.
+        """
+        status = await self.get_status()
+        if status.job_details and len(status.job_details) > 0:
+            detail = status.job_details[0]
+            return {
+                "total_pages": detail.total_pages or 0,
+                "pages_processed": detail.pages_processed or 0,
+                "pages_succeeded": detail.pages_succeeded or 0,
+                "pages_failed": detail.pages_failed or 0,
+            }
+        return None
+
+    async def get_page_errors(self) -> typing.Optional[typing.List[typing.Any]]:
+        """
+        Get any page-level errors from the job.
+
+        Returns
+        -------
+        typing.Optional[typing.List[typing.Any]]
+            List of page errors, or None if not available.
+        """
+        status = await self.get_status()
+        if status.job_details and len(status.job_details) > 0:
+            return status.job_details[0].page_errors
+        return None
+
+
+class DocDigitizationJob:
+    """
+    Sync helper class for managing a Document Digitization job.
+
+    Provides high-level methods for uploading files, starting the job,
+    polling for completion, and downloading outputs.
+    """
+
+    def __init__(self, job_id: str, client: "DocDigitizationJobClient"):
+        """
+        Initialize the document digitization job.
+
+        Parameters
+        ----------
+        job_id : str
+            The unique identifier for the job.
+        client : DocDigitizationJobClient
+            The client instance to use for API calls.
+        """
+        self._job_id = job_id
+        self._client = client
+
+    @property
+    def job_id(self) -> str:
+        """Returns the job ID associated with this job instance."""
+        return self._job_id
+
+    def upload_file(self, file_path: str, timeout: float = 120.0) -> bool:
+        """
+        Upload the input PDF or ZIP file for the document digitization job.
+
+        Parameters
+        ----------
+        file_path : str
+            Path to the PDF or ZIP file to upload.
+        timeout : float, default=120.0
+            Timeout in seconds for the upload request.
+
+        Returns
+        -------
+        bool
+            True if upload was successful.
+
+        Raises
+        ------
+        ValueError
+            If the file is not a PDF or ZIP file.
+        FileNotFoundError
+            If the file does not exist.
+        httpx.HTTPStatusError
+            If the upload request fails.
+        """
+        if not os.path.exists(file_path):
+            raise FileNotFoundError(f"File not found: {file_path}")
+
+        ext = os.path.splitext(file_path)[1].lower()
+        if ext not in [".pdf", ".zip"]:
+            raise ValueError(f"Only PDF or ZIP files are supported, got: {ext}")
+
+        file_name = os.path.basename(file_path)
+
+        # Get upload URL
+        upload_response = self._client.get_upload_links(
+            job_id=self._job_id,
+            files=[file_name],
+        )
+
+        if not upload_response.upload_urls:
+            raise ValueError("No upload URL returned from API")
+
+        upload_detail = list(upload_response.upload_urls.values())[0]
+        upload_url = upload_detail.file_url
+
+        # Determine content type
+        content_type, _ = mimetypes.guess_type(file_path)
+        if content_type is None:
+            content_type = "application/octet-stream"
+
+        # Upload the file
+        with httpx.Client(timeout=timeout) as http_client:
+            with open(file_path, "rb") as f:
+                file_content = f.read()
+
+            response = http_client.put(
+                upload_url,
+                content=file_content,
+                headers={
+                    "Content-Type": content_type,
+                    "x-ms-blob-type": "BlockBlob",
+                },
+            )
+            response.raise_for_status()
+
+        return True
+
+    def start(self) -> DocDigitizationJobStatusResponse:
+        """
+        Start the document digitization job processing.
+
+        Returns
+        -------
+        DocDigitizationJobStatusResponse
+            The job status after starting.
+        """
+        return self._client.start(job_id=self._job_id)
+
+    def get_status(self) -> DocDigitizationJobStatusResponse:
+        """
+        Retrieve the current status of the job.
+
+        Returns
+        -------
+        DocDigitizationJobStatusResponse
+            The current job status.
+        """
+        return self._client.get_status(self._job_id)
+
+    def wait_until_complete(
+        self, poll_interval: int = 5, timeout: int = 1800
+    ) -> DocDigitizationJobStatusResponse:
+        """
+        Polls job status until it completes, partially completes, or fails.
+
+        Parameters
+        ----------
+        poll_interval : int, default=5
+            Seconds between status checks.
+        timeout : int, default=1800
+            Maximum seconds to wait before raising TimeoutError.
+
+        Returns
+        -------
+        DocDigitizationJobStatusResponse
+            The final job status.
+
+        Raises
+        ------
+        TimeoutError
+            If the job does not complete within the timeout period.
+        """
+        start_time = time.time()
+        terminal_states = {"completed", "partiallycompleted", "failed"}
+
+        while True:
+            status = self.get_status()
+
+            if status.job_state and status.job_state.lower() in terminal_states:
+                return status
+
+            elapsed = time.time() - start_time
+            if elapsed >= timeout:
+                raise TimeoutError(
+                    f"Job {self._job_id} did not complete within {timeout} seconds. "
+                    f"Current state: {status.job_state}"
+                )
+
+            time.sleep(poll_interval)
+
+    def download_output(self, output_path: str, timeout: float = 120.0) -> bool:
+        """
+        Download the output file (HTML or Markdown) to the specified path.
+
+        Parameters
+        ----------
+        output_path : str
+            Path where the output file should be saved.
+        timeout : float, default=120.0
+            Timeout in seconds for the download request.
+
+        Returns
+        -------
+        bool
+            True if download was successful.
+
+        Raises
+        ------
+        ValueError
+            If no download URL is available.
+        httpx.HTTPStatusError
+            If the download request fails.
+        """
+        download_response = self._client.get_download_links(job_id=self._job_id)
+
+        if not download_response.download_urls:
+            raise ValueError("No download URL returned from API")
+
+        download_detail = list(download_response.download_urls.values())[0]
+        download_url = download_detail.file_url
+
+        with httpx.Client(timeout=timeout) as http_client:
+            response = http_client.get(download_url)
+            response.raise_for_status()
+
+            # Ensure output directory exists
+            os.makedirs(os.path.dirname(os.path.abspath(output_path)), exist_ok=True)
+
+            with open(output_path, "wb") as f:
+                f.write(response.content)
+
+        return True
+
+    def get_page_metrics(self) -> typing.Optional[typing.Dict[str, int]]:
+        """
+        Get page processing metrics from the job status.
+
+        Returns
+        -------
+        typing.Optional[typing.Dict[str, int]]
+            Dictionary with keys: total_pages, pages_processed, pages_succeeded, pages_failed.
+            Returns None if job_detail is not available.
+        """
+        status = self.get_status()
+        if status.job_details and len(status.job_details) > 0:
+            detail = status.job_details[0]
+            return {
+                "total_pages": detail.total_pages or 0,
+                "pages_processed": detail.pages_processed or 0,
+                "pages_succeeded": detail.pages_succeeded or 0,
+                "pages_failed": detail.pages_failed or 0,
+            }
+        return None
+
+    def get_page_errors(self) -> typing.Optional[typing.List[typing.Any]]:
+        """
+        Get any page-level errors from the job.
+
+        Returns
+        -------
+        typing.Optional[typing.List[typing.Any]]
+            List of page errors, or None if not available.
+        """
+        status = self.get_status()
+        if status.job_details and len(status.job_details) > 0:
+            return status.job_details[0].page_errors
+        return None

{sarvamai-0.1.23a7.dist-info → sarvamai-0.1.23a8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.23a7
+Version: 0.1.23a8
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.23a7.dist-info → sarvamai-0.1.23a8.dist-info}/RECORD

@@ -5,7 +5,7 @@ sarvamai/chat/raw_client.py,sha256=A2kRuZcVWlJhyYCD7YKgqNkZEp3cYa1731KhRkhirU0,1
 sarvamai/client.py,sha256=Ii9ASYuAJXPE4R0byshfXEtb8ivjm2xJjeJNm95rJz0,8505
 sarvamai/core/__init__.py,sha256=YE2CtXeASe1RAbaI39twKWYKCuT4tW5is9HWHhJjR_g,1653
 sarvamai/core/api_error.py,sha256=44vPoTyWN59gonCIZMdzw7M1uspygiLnr3GNFOoVL2Q,614
-sarvamai/core/client_wrapper.py,sha256=mciSkny4fu-Z7OMxtWtGTid4k5pYy8_scuoAStsHRYQ,2570
+sarvamai/core/client_wrapper.py,sha256=VT-vH4EOWOIsBhQdXoxlma-fjFBBvEnqYOjuKTSEErc,2570
 sarvamai/core/datetime_utils.py,sha256=nBys2IsYrhPdszxGKCNRPSOCwa-5DWOHG95FB8G9PKo,1047
 sarvamai/core/events.py,sha256=HvKBdSoYcFetk7cgNXb7FxuY-FtY8NtUhZIN7mGVx8U,1159
 sarvamai/core/file.py,sha256=d4NNbX8XvXP32z8KpK2Xovv33nFfruIrpz0QWxlgpZk,2663
@@ -19,7 +19,8 @@ sarvamai/core/remove_none_from_dict.py,sha256=EU9SGgYidWq7SexuJbNs4-PZ-5Bl3Vppd8
 sarvamai/core/request_options.py,sha256=h0QUNCFVdCW_7GclVySCAY2w4NhtXVBUCmHgmzaxpcg,1681
 sarvamai/core/serialization.py,sha256=ECL3bvv_0i7U4uvPidZCNel--MUbA0iq0aGcNKi3kws,9818
 sarvamai/doc_digitization_job/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,85
-sarvamai/doc_digitization_job/client.py,sha256=ltlsrwk-OONpho8EQ4D__D07xyvw1620lRdt8maFlF0,17496
+sarvamai/doc_digitization_job/client.py,sha256=3c4V13RIeuZjKl28loxZS1TTTIhI6zyRf-0NXYujrcw,23715
+sarvamai/doc_digitization_job/job.py,sha256=lbQ0N6GxTgNAp_dJ_Q-6YlvpVwcgTdXyCn-ZoE9kbHg,15542
 sarvamai/doc_digitization_job/raw_client.py,sha256=RjjYexOrF0GmaW97pyHXV_4QvtK7LN2O-qAgV-3r2kQ,48300
 sarvamai/environment.py,sha256=hdwTU767BqRgSMLiAOocY_Vpw8V2N_hAy3yhoK8VFS0,402
 sarvamai/errors/__init__.py,sha256=EEGwHETz9DGVcwYvrxxvTpfqaG-tjF-SiYEe6ULeXt4,595
@@ -256,6 +257,6 @@ sarvamai/types/transliterate_mode.py,sha256=1jSEMlGcoLkWuk12TgoOpSgwifa4rThGKZ1h
 sarvamai/types/transliterate_source_language.py,sha256=bSY9wJszF0sg-Cgg6F-YcWC8ly1mIlj9rqa15-jBtx8,283
 sarvamai/types/transliteration_response.py,sha256=yt-lzTbDeJ_ZL4I8kQa6oESxA9ebeJJY7LfFHpdEsmM,815
 sarvamai/version.py,sha256=Qkp3Ee9YH-O9RTix90e0i7iNrFAGN-QDt2AFwGA4n8k,75
-sarvamai-0.1.23a7.dist-info/METADATA,sha256=vGml1SuUGdWr-JcBB7lIVVu627x7HP7Veg-sFET1Rcg,26753
-sarvamai-0.1.23a7.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
-sarvamai-0.1.23a7.dist-info/RECORD,,
+sarvamai-0.1.23a8.dist-info/METADATA,sha256=oZaRA_igtRwhVfU3GPr8jvbkAmdw0N-KdY42VN-8-Xw,26753
+sarvamai-0.1.23a8.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
+sarvamai-0.1.23a8.dist-info/RECORD,,