docu-devs-api-client 1.10.0__tar.gz → 1.10.1__tar.gz

{docu_devs_api_client-1.10.0 → docu_devs_api_client-1.10.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docu-devs-api-client
-Version: 1.10.0
+Version: 1.10.1
 Summary: A client library for accessing DocuDevs API
 Project-URL: Homepage, https://www.docudevs.ai/
 Project-URL: Repository, https://github.com/piizei/docudevs.git

{docu_devs_api_client-1.10.0 → docu_devs_api_client-1.10.1}/cli.py

@@ -1064,6 +1064,74 @@ async def operations_error_analysis(
         _echo_response(response)
 
 
+@operations.command("pdf-acroform")
+@click.argument("job_guid")
+@click.option("--llm-type", default="DEFAULT", type=click.Choice(["DEFAULT", "MINI", "HIGH"]), help="LLM type for visual field detection")
+@click.option("--ocr", default="PREMIUM", type=click.Choice(["PREMIUM", "DEFAULT", "AUTO"]), help="OCR mode used when page images are missing")
+@click.option("--page", "pages", multiple=True, type=int, help="1-based page number to inspect")
+@click.option("--min-confidence", type=float, help="Minimum accepted field detection confidence")
+@click.option("--max-fields-per-page", type=int, help="Maximum generated fields per page")
+@click.option("--force-ocr/--no-force-ocr", default=None, help="Force OCR image generation even if thumbnails exist")
+@click.option("--wait/--no-wait", default=True, help="Wait for completion")
+@click.option("--timeout", default=180, show_default=True, help="Wait timeout in seconds")
+@click.option("--poll-interval", default=5.0, show_default=True, help="Polling interval in seconds")
+@click.option("--output", type=click.Path(), help="Save the generated AcroForm PDF to this path")
+@click.pass_context
+@async_command
+async def operations_pdf_acroform(
+    ctx,
+    job_guid: str,
+    llm_type: str,
+    ocr: str,
+    pages: tuple[int, ...],
+    min_confidence: Optional[float],
+    max_fields_per_page: Optional[int],
+    force_ocr: Optional[bool],
+    wait: bool,
+    timeout: int,
+    poll_interval: float,
+    output: Optional[str],
+):
+    """Convert a completed PDF job into a fillable AcroForm PDF."""
+    if output and not wait:
+        raise click.BadParameter("--output requires --wait", param_hint="--output")
+
+    page_range = list(pages) or None
+    client: DocuDevsClient = ctx.obj["client"]
+    if wait:
+        result = await client.submit_and_wait_for_pdf_acroform_operation(
+            job_guid=job_guid,
+            llm_type=llm_type,
+            ocr=ocr,
+            page_range=page_range,
+            min_confidence=min_confidence,
+            max_fields_per_page=max_fields_per_page,
+            force_ocr=force_ocr,
+            timeout=timeout,
+            poll_interval=poll_interval,
+            save_to=output,
+        )
+        _echo_response(
+            {
+                "operationJobGuid": result.operation_job_guid,
+                "parentJobGuid": result.parent_job_guid,
+                "result": result.result,
+                "output": output,
+            }
+        )
+    else:
+        response = await client.submit_pdf_acroform_operation(
+            job_guid=job_guid,
+            llm_type=llm_type,
+            ocr=ocr,
+            page_range=page_range,
+            min_confidence=min_confidence,
+            max_fields_per_page=max_fields_per_page,
+            force_ocr=force_ocr,
+        )
+        _echo_response(response)
+
+
 @operations.command("generative-task")
 @click.argument("parent_job_id")
 @click.option("--prompt", required=True, help="Prompt for the generative task")

docu_devs_api_client-1.10.1/docudevs/api/job/get_pdf_acro_form_result.py

@@ -0,0 +1,92 @@
+from http import HTTPStatus
+from typing import Any, Optional, Union
+
+import httpx
+
+from ... import errors
+from ...client import AuthenticatedClient, Client
+from ...types import Response
+
+
+def _get_kwargs(
+    guid: str,
+) -> dict[str, Any]:
+    _kwargs: dict[str, Any] = {
+        "method": "get",
+        "url": f"/job/result/{guid}/pdf-acroform",
+    }
+
+    return _kwargs
+
+
+def _parse_response(*, client: Union[AuthenticatedClient, Client], response: httpx.Response) -> Optional[Any]:
+    if response.status_code == 200:
+        return None
+
+    if client.raise_on_unexpected_status:
+        raise errors.UnexpectedStatus(response.status_code, response.content)
+    else:
+        return None
+
+
+def _build_response(*, client: Union[AuthenticatedClient, Client], response: httpx.Response) -> Response[Any]:
+    return Response(
+        status_code=HTTPStatus(response.status_code),
+        content=response.content,
+        headers=response.headers,
+        parsed=_parse_response(client=client, response=response),
+    )
+
+
+def sync_detailed(
+    guid: str,
+    *,
+    client: Union[AuthenticatedClient, Client],
+) -> Response[Any]:
+    """
+    Args:
+        guid (str):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[Any]
+    """
+
+    kwargs = _get_kwargs(
+        guid=guid,
+    )
+
+    response = client.get_httpx_client().request(
+        **kwargs,
+    )
+
+    return _build_response(client=client, response=response)
+
+
+async def asyncio_detailed(
+    guid: str,
+    *,
+    client: Union[AuthenticatedClient, Client],
+) -> Response[Any]:
+    """
+    Args:
+        guid (str):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[Any]
+    """
+
+    kwargs = _get_kwargs(
+        guid=guid,
+    )
+
+    response = await client.get_async_httpx_client().request(**kwargs)
+
+    return _build_response(client=client, response=response)

{docu_devs_api_client-1.10.0 → docu_devs_api_client-1.10.1}/docudevs/cli.py

@@ -1064,6 +1064,74 @@ async def operations_error_analysis(
         _echo_response(response)
 
 
+@operations.command("pdf-acroform")
+@click.argument("job_guid")
+@click.option("--llm-type", default="DEFAULT", type=click.Choice(["DEFAULT", "MINI", "HIGH"]), help="LLM type for visual field detection")
+@click.option("--ocr", default="PREMIUM", type=click.Choice(["PREMIUM", "DEFAULT", "AUTO"]), help="OCR mode used when page images are missing")
+@click.option("--page", "pages", multiple=True, type=int, help="1-based page number to inspect")
+@click.option("--min-confidence", type=float, help="Minimum accepted field detection confidence")
+@click.option("--max-fields-per-page", type=int, help="Maximum generated fields per page")
+@click.option("--force-ocr/--no-force-ocr", default=None, help="Force OCR image generation even if thumbnails exist")
+@click.option("--wait/--no-wait", default=True, help="Wait for completion")
+@click.option("--timeout", default=180, show_default=True, help="Wait timeout in seconds")
+@click.option("--poll-interval", default=5.0, show_default=True, help="Polling interval in seconds")
+@click.option("--output", type=click.Path(), help="Save the generated AcroForm PDF to this path")
+@click.pass_context
+@async_command
+async def operations_pdf_acroform(
+    ctx,
+    job_guid: str,
+    llm_type: str,
+    ocr: str,
+    pages: tuple[int, ...],
+    min_confidence: Optional[float],
+    max_fields_per_page: Optional[int],
+    force_ocr: Optional[bool],
+    wait: bool,
+    timeout: int,
+    poll_interval: float,
+    output: Optional[str],
+):
+    """Convert a completed PDF job into a fillable AcroForm PDF."""
+    if output and not wait:
+        raise click.BadParameter("--output requires --wait", param_hint="--output")
+
+    page_range = list(pages) or None
+    client: DocuDevsClient = ctx.obj["client"]
+    if wait:
+        result = await client.submit_and_wait_for_pdf_acroform_operation(
+            job_guid=job_guid,
+            llm_type=llm_type,
+            ocr=ocr,
+            page_range=page_range,
+            min_confidence=min_confidence,
+            max_fields_per_page=max_fields_per_page,
+            force_ocr=force_ocr,
+            timeout=timeout,
+            poll_interval=poll_interval,
+            save_to=output,
+        )
+        _echo_response(
+            {
+                "operationJobGuid": result.operation_job_guid,
+                "parentJobGuid": result.parent_job_guid,
+                "result": result.result,
+                "output": output,
+            }
+        )
+    else:
+        response = await client.submit_pdf_acroform_operation(
+            job_guid=job_guid,
+            llm_type=llm_type,
+            ocr=ocr,
+            page_range=page_range,
+            min_confidence=min_confidence,
+            max_fields_per_page=max_fields_per_page,
+            force_ocr=force_ocr,
+        )
+        _echo_response(response)
+
+
 @operations.command("generative-task")
 @click.argument("parent_job_id")
 @click.option("--prompt", required=True, help="Prompt for the generative task")

{docu_devs_api_client-1.10.0 → docu_devs_api_client-1.10.1}/docudevs/docudevs_client.py

@@ -83,6 +83,14 @@ class StructuredResultWithDocumentOutline:
     document_outline: dict | None
 
 
+@dataclass(eq=True)
+class PdfAcroFormOperationResult:
+    result: Any
+    pdf: bytes
+    operation_job_guid: str
+    parent_job_guid: str
+
+
 class DocuDevsClient:
     def __init__(self, api_url: str = "https://api.docudevs.ai", token: Optional[str] = None):
         # Create the openapi-python-client AuthenticatedClient
@@ -2232,7 +2240,7 @@ class DocuDevsClient:
             if custom_parameters:
                 custom_params_model = OperationParametersCustomParametersType1()
                 for key, value in custom_parameters.items():
-                    custom_params_model[key] = str(value)
+                    custom_params_model[key] = value
 
             llm_type_value = UNSET
             if llm_type:
@@ -2283,6 +2291,106 @@ class DocuDevsClient:
             custom_parameters=custom_parameters or None,
         )
 
+    async def submit_pdf_acroform_operation(
+        self,
+        job_guid: str,
+        *,
+        llm_type: Optional[str] = "DEFAULT",
+        ocr: str = "PREMIUM",
+        page_range: Optional[list[int]] = None,
+        min_confidence: Optional[float] = None,
+        max_fields_per_page: Optional[int] = None,
+        force_ocr: Optional[bool] = None,
+    ):
+        """Submit a pdf-acroform operation for an existing PDF job."""
+        if page_range is not None:
+            if any(int(page) < 1 for page in page_range):
+                raise ValueError("page_range must contain 1-based positive page numbers")
+            page_range = [int(page) for page in page_range]
+        if min_confidence is not None and not 0 <= min_confidence <= 1:
+            raise ValueError("min_confidence must be between 0 and 1")
+        if max_fields_per_page is not None and max_fields_per_page < 1:
+            raise ValueError("max_fields_per_page must be >= 1")
+
+        custom_parameters: dict[str, Any] = {
+            "ocr": ocr,
+            "fieldNameStyle": "source_snake_case",
+        }
+        if page_range is not None:
+            custom_parameters["pageRange"] = page_range
+        if min_confidence is not None:
+            custom_parameters["minConfidence"] = min_confidence
+        if max_fields_per_page is not None:
+            custom_parameters["maxFieldsPerPage"] = max_fields_per_page
+        if force_ocr is not None:
+            custom_parameters["forceOcr"] = force_ocr
+
+        return await self.submit_operation_with_parameters(
+            job_guid=job_guid,
+            operation_type="pdf-acroform",
+            llm_type=llm_type,
+            custom_parameters=custom_parameters,
+        )
+
+    async def get_pdf_acroform(self, operation_job_guid: str, save_to: str | None = None) -> bytes:
+        """Download the generated AcroForm PDF for a pdf-acroform operation job."""
+        response = await self._get_async_client().get(
+            f"/job/result/{quote(operation_job_guid, safe='')}/pdf-acroform"
+        )
+        if response.status_code == HTTPStatus.OK:
+            content = response.content
+            if save_to:
+                with open(save_to, "wb") as output:
+                    output.write(content)
+            return content
+        if response.status_code == HTTPStatus.NOT_FOUND:
+            raise FileNotFoundError(
+                f"No pdf-acroform result found for operation job {operation_job_guid}"
+            )
+        raise Exception(f"Error downloading pdf-acroform result: {response.status_code} - {response.text}")
+
+    async def submit_and_wait_for_pdf_acroform_operation(
+        self,
+        job_guid: str,
+        *,
+        llm_type: Optional[str] = "DEFAULT",
+        ocr: str = "PREMIUM",
+        page_range: Optional[list[int]] = None,
+        min_confidence: Optional[float] = None,
+        max_fields_per_page: Optional[int] = None,
+        force_ocr: Optional[bool] = None,
+        timeout: int = 180,
+        poll_interval: float = 5.0,
+        save_to: str | None = None,
+    ) -> PdfAcroFormOperationResult:
+        """Submit a pdf-acroform operation, wait for completion, then download the PDF."""
+        operation_response = await self.submit_pdf_acroform_operation(
+            job_guid,
+            llm_type=llm_type,
+            ocr=ocr,
+            page_range=page_range,
+            min_confidence=min_confidence,
+            max_fields_per_page=max_fields_per_page,
+            force_ocr=force_ocr,
+        )
+        operation_guid = getattr(operation_response, "job_guid", None)
+        if not operation_guid:
+            raise Exception("No operation job GUID returned from pdf-acroform operation")
+        result = await self._wait_for_operation_job_result(
+            operation_guid,
+            parent_job_guid=job_guid,
+            operation_type="pdf-acroform",
+            timeout=timeout,
+            poll_interval=poll_interval,
+        )
+        pdf = await self.get_pdf_acroform(operation_guid, save_to=save_to)
+        return PdfAcroFormOperationResult(
+            result=result,
+            pdf=pdf,
+            operation_job_guid=operation_guid,
+            parent_job_guid=job_guid,
+        )
+
     async def get_operation_status(self, job_guid: str):
         """Get status of all operations for a job."""
         return await get_operation_status_async(client=self._client, job_guid=job_guid)

{docu_devs_api_client-1.10.0 → docu_devs_api_client-1.10.1}/docudevs_client.py

@@ -83,6 +83,14 @@ class StructuredResultWithDocumentOutline:
     document_outline: dict | None
 
 
+@dataclass(eq=True)
+class PdfAcroFormOperationResult:
+    result: Any
+    pdf: bytes
+    operation_job_guid: str
+    parent_job_guid: str
+
+
 class DocuDevsClient:
     def __init__(self, api_url: str = "https://api.docudevs.ai", token: Optional[str] = None):
         # Create the openapi-python-client AuthenticatedClient
@@ -2232,7 +2240,7 @@ class DocuDevsClient:
             if custom_parameters:
                 custom_params_model = OperationParametersCustomParametersType1()
                 for key, value in custom_parameters.items():
-                    custom_params_model[key] = str(value)
+                    custom_params_model[key] = value
 
             llm_type_value = UNSET
             if llm_type:
@@ -2283,6 +2291,106 @@ class DocuDevsClient:
             custom_parameters=custom_parameters or None,
         )
 
+    async def submit_pdf_acroform_operation(
+        self,
+        job_guid: str,
+        *,
+        llm_type: Optional[str] = "DEFAULT",
+        ocr: str = "PREMIUM",
+        page_range: Optional[list[int]] = None,
+        min_confidence: Optional[float] = None,
+        max_fields_per_page: Optional[int] = None,
+        force_ocr: Optional[bool] = None,
+    ):
+        """Submit a pdf-acroform operation for an existing PDF job."""
+        if page_range is not None:
+            if any(int(page) < 1 for page in page_range):
+                raise ValueError("page_range must contain 1-based positive page numbers")
+            page_range = [int(page) for page in page_range]
+        if min_confidence is not None and not 0 <= min_confidence <= 1:
+            raise ValueError("min_confidence must be between 0 and 1")
+        if max_fields_per_page is not None and max_fields_per_page < 1:
+            raise ValueError("max_fields_per_page must be >= 1")
+
+        custom_parameters: dict[str, Any] = {
+            "ocr": ocr,
+            "fieldNameStyle": "source_snake_case",
+        }
+        if page_range is not None:
+            custom_parameters["pageRange"] = page_range
+        if min_confidence is not None:
+            custom_parameters["minConfidence"] = min_confidence
+        if max_fields_per_page is not None:
+            custom_parameters["maxFieldsPerPage"] = max_fields_per_page
+        if force_ocr is not None:
+            custom_parameters["forceOcr"] = force_ocr
+
+        return await self.submit_operation_with_parameters(
+            job_guid=job_guid,
+            operation_type="pdf-acroform",
+            llm_type=llm_type,
+            custom_parameters=custom_parameters,
+        )
+
+    async def get_pdf_acroform(self, operation_job_guid: str, save_to: str | None = None) -> bytes:
+        """Download the generated AcroForm PDF for a pdf-acroform operation job."""
+        response = await self._get_async_client().get(
+            f"/job/result/{quote(operation_job_guid, safe='')}/pdf-acroform"
+        )
+        if response.status_code == HTTPStatus.OK:
+            content = response.content
+            if save_to:
+                with open(save_to, "wb") as output:
+                    output.write(content)
+            return content
+        if response.status_code == HTTPStatus.NOT_FOUND:
+            raise FileNotFoundError(
+                f"No pdf-acroform result found for operation job {operation_job_guid}"
+            )
+        raise Exception(f"Error downloading pdf-acroform result: {response.status_code} - {response.text}")
+
+    async def submit_and_wait_for_pdf_acroform_operation(
+        self,
+        job_guid: str,
+        *,
+        llm_type: Optional[str] = "DEFAULT",
+        ocr: str = "PREMIUM",
+        page_range: Optional[list[int]] = None,
+        min_confidence: Optional[float] = None,
+        max_fields_per_page: Optional[int] = None,
+        force_ocr: Optional[bool] = None,
+        timeout: int = 180,
+        poll_interval: float = 5.0,
+        save_to: str | None = None,
+    ) -> PdfAcroFormOperationResult:
+        """Submit a pdf-acroform operation, wait for completion, then download the PDF."""
+        operation_response = await self.submit_pdf_acroform_operation(
+            job_guid,
+            llm_type=llm_type,
+            ocr=ocr,
+            page_range=page_range,
+            min_confidence=min_confidence,
+            max_fields_per_page=max_fields_per_page,
+            force_ocr=force_ocr,
+        )
+        operation_guid = getattr(operation_response, "job_guid", None)
+        if not operation_guid:
+            raise Exception("No operation job GUID returned from pdf-acroform operation")
+        result = await self._wait_for_operation_job_result(
+            operation_guid,
+            parent_job_guid=job_guid,
+            operation_type="pdf-acroform",
+            timeout=timeout,
+            poll_interval=poll_interval,
+        )
+        pdf = await self.get_pdf_acroform(operation_guid, save_to=save_to)
+        return PdfAcroFormOperationResult(
+            result=result,
+            pdf=pdf,
+            operation_job_guid=operation_guid,
+            parent_job_guid=job_guid,
+        )
+
     async def get_operation_status(self, job_guid: str):
         """Get status of all operations for a job."""
         return await get_operation_status_async(client=self._client, job_guid=job_guid)

{docu_devs_api_client-1.10.0 → docu_devs_api_client-1.10.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docu-devs-api-client"
-version = "1.10.0"
+version = "1.10.1"
 description = "A client library for accessing DocuDevs API"
 authors = [{name = "pj@docudevs.ai"}]
 readme = "README.md"