openparser-sdk 1.0.0__tar.gz → 1.0.2__tar.gz

{openparser_sdk-1.0.0 → openparser_sdk-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: openparser-sdk
-Version: 1.0.0
+Version: 1.0.2
 Summary: Parse documents and extract structured data with Python
 Project-URL: Homepage, https://openparser.dev
 Project-URL: Documentation, https://docs.openparser.dev
@@ -121,6 +121,36 @@ suggested = client.extract.suggest_schema(
 )
 ```
 
+### Grounding and lineage
+
+Set `"grounding": "field"` to receive verified citations and a `lineage@1`
+derivation DAG:
+
+```python
+extracted = client.extract.sync(
+    {
+        "ocr_model": "mistral-ocr-4",
+        "llm_model": "openai/gpt-5.6-terra",
+        "grounding": "field",
+        "schema": {
+            "type": "object",
+            "properties": {"total": {"type": "number"}},
+        },
+    },
+    file=Path("invoice.pdf"),
+)
+
+lineage = extracted.to_dict().get("lineage")
+if lineage is not None:
+    print(lineage["outputs"])
+```
+
+The graph connects each output value to its source evidence and the operations
+that produced it. Evidence carries the closest recognition confidence supplied
+by the selected OCR model. Applications can append normalization, calculation,
+inference, and human-review activities without replacing the original machine
+result.
+
 `OpenParserClient` is synchronous. Methods named `async_` submit durable jobs
 without waiting for processing to finish.
 

{openparser_sdk-1.0.0 → openparser_sdk-1.0.2}/README.md

@@ -86,6 +86,36 @@ suggested = client.extract.suggest_schema(
 )
 ```
 
+### Grounding and lineage
+
+Set `"grounding": "field"` to receive verified citations and a `lineage@1`
+derivation DAG:
+
+```python
+extracted = client.extract.sync(
+    {
+        "ocr_model": "mistral-ocr-4",
+        "llm_model": "openai/gpt-5.6-terra",
+        "grounding": "field",
+        "schema": {
+            "type": "object",
+            "properties": {"total": {"type": "number"}},
+        },
+    },
+    file=Path("invoice.pdf"),
+)
+
+lineage = extracted.to_dict().get("lineage")
+if lineage is not None:
+    print(lineage["outputs"])
+```
+
+The graph connects each output value to its source evidence and the operations
+that produced it. Evidence carries the closest recognition confidence supplied
+by the selected OCR model. Applications can append normalization, calculation,
+inference, and human-review activities without replacing the original machine
+result.
+
 `OpenParserClient` is synchronous. Methods named `async_` submit durable jobs
 without waiting for processing to finish.
 

{openparser_sdk-1.0.0 → openparser_sdk-1.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "openparser-sdk"
-version = "1.0.0"
+version = "1.0.2"
 description = "Parse documents and extract structured data with Python"
 readme = "README.md"
 requires-python = ">=3.10"

openparser_sdk-1.0.2/src/openparser/_generated/api/jobs/complete_extraction_review.py

@@ -0,0 +1,258 @@
+from http import HTTPStatus
+from typing import Any, cast
+from urllib.parse import quote
+
+import httpx
+
+from ...client import AuthenticatedClient, Client
+from ...types import Response, UNSET
+from ... import errors
+
+from ...models.complete_extraction_review_request import CompleteExtractionReviewRequest
+from ...models.error_response import ErrorResponse
+from ...models.extraction_review import ExtractionReview
+from typing import cast
+
+
+
+def _get_kwargs(
+    id: str,
+    *,
+    body: CompleteExtractionReviewRequest,
+
+) -> dict[str, Any]:
+    headers: dict[str, Any] = {}
+
+
+
+
+
+
+    _kwargs: dict[str, Any] = {
+        "method": "post",
+        "url": "/jobs/{id}/review/complete".format(id=quote(str(id), safe=""),),
+    }
+
+    _kwargs["json"] = body.to_dict()
+
+
+    headers["Content-Type"] = "application/json"
+
+    _kwargs["headers"] = headers
+    return _kwargs
+
+
+
+def _parse_response(*, client: AuthenticatedClient | Client, response: httpx.Response) -> ErrorResponse | ExtractionReview | None:
+    if response.status_code == 200:
+        response_200 = ExtractionReview.from_dict(response.json())
+
+
+
+        return response_200
+
+    if response.status_code == 400:
+        response_400 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_400
+
+    if response.status_code == 401:
+        response_401 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_401
+
+    if response.status_code == 403:
+        response_403 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_403
+
+    if response.status_code == 404:
+        response_404 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_404
+
+    if response.status_code == 409:
+        response_409 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_409
+
+    if response.status_code == 413:
+        response_413 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_413
+
+    if response.status_code == 429:
+        response_429 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_429
+
+    if client.raise_on_unexpected_status:
+        raise errors.UnexpectedStatus(response.status_code, response.content)
+    else:
+        return None
+
+
+def _build_response(*, client: AuthenticatedClient | Client, response: httpx.Response) -> Response[ErrorResponse | ExtractionReview]:
+    return Response(
+        status_code=HTTPStatus(response.status_code),
+        content=response.content,
+        headers=response.headers,
+        parsed=_parse_response(client=client, response=response),
+    )
+
+
+def sync_detailed(
+    id: str,
+    *,
+    client: AuthenticatedClient | Client,
+    body: CompleteExtractionReviewRequest,
+
+) -> Response[ErrorResponse | ExtractionReview]:
+    """ Approve or reject an extraction review
+
+     Finalize a pending review as approved or rejected. A completed review is frozen: field
+    confirmations are rejected until it is reopened. Uses the same optimistic version check as
+    field confirmations.
+
+    Args:
+        id (str): Prefixed public id for an OCR job (`opj_…`). Example: opj_V1StGXR8_Z5jdHi6B-myT.
+        body (CompleteExtractionReviewRequest):
+
+    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[ErrorResponse | ExtractionReview]
+     """
+
+
+    kwargs = _get_kwargs(
+        id=id,
+body=body,
+
+    )
+
+    response = client.get_httpx_client().request(
+        **kwargs,
+    )
+
+    return _build_response(client=client, response=response)
+
+def sync(
+    id: str,
+    *,
+    client: AuthenticatedClient | Client,
+    body: CompleteExtractionReviewRequest,
+
+) -> ErrorResponse | ExtractionReview | None:
+    """ Approve or reject an extraction review
+
+     Finalize a pending review as approved or rejected. A completed review is frozen: field
+    confirmations are rejected until it is reopened. Uses the same optimistic version check as
+    field confirmations.
+
+    Args:
+        id (str): Prefixed public id for an OCR job (`opj_…`). Example: opj_V1StGXR8_Z5jdHi6B-myT.
+        body (CompleteExtractionReviewRequest):
+
+    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:
+        ErrorResponse | ExtractionReview
+     """
+
+
+    return sync_detailed(
+        id=id,
+client=client,
+body=body,
+
+    ).parsed
+
+async def asyncio_detailed(
+    id: str,
+    *,
+    client: AuthenticatedClient | Client,
+    body: CompleteExtractionReviewRequest,
+
+) -> Response[ErrorResponse | ExtractionReview]:
+    """ Approve or reject an extraction review
+
+     Finalize a pending review as approved or rejected. A completed review is frozen: field
+    confirmations are rejected until it is reopened. Uses the same optimistic version check as
+    field confirmations.
+
+    Args:
+        id (str): Prefixed public id for an OCR job (`opj_…`). Example: opj_V1StGXR8_Z5jdHi6B-myT.
+        body (CompleteExtractionReviewRequest):
+
+    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[ErrorResponse | ExtractionReview]
+     """
+
+
+    kwargs = _get_kwargs(
+        id=id,
+body=body,
+
+    )
+
+    response = await client.get_async_httpx_client().request(
+        **kwargs
+    )
+
+    return _build_response(client=client, response=response)
+
+async def asyncio(
+    id: str,
+    *,
+    client: AuthenticatedClient | Client,
+    body: CompleteExtractionReviewRequest,
+
+) -> ErrorResponse | ExtractionReview | None:
+    """ Approve or reject an extraction review
+
+     Finalize a pending review as approved or rejected. A completed review is frozen: field
+    confirmations are rejected until it is reopened. Uses the same optimistic version check as
+    field confirmations.
+
+    Args:
+        id (str): Prefixed public id for an OCR job (`opj_…`). Example: opj_V1StGXR8_Z5jdHi6B-myT.
+        body (CompleteExtractionReviewRequest):
+
+    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:
+        ErrorResponse | ExtractionReview
+     """
+
+
+    return (await asyncio_detailed(
+        id=id,
+client=client,
+body=body,
+
+    )).parsed

openparser_sdk-1.0.2/src/openparser/_generated/api/jobs/get_extraction_review.py

@@ -0,0 +1,223 @@
+from http import HTTPStatus
+from typing import Any, cast
+from urllib.parse import quote
+
+import httpx
+
+from ...client import AuthenticatedClient, Client
+from ...types import Response, UNSET
+from ... import errors
+
+from ...models.error_response import ErrorResponse
+from ...models.extraction_review import ExtractionReview
+from typing import cast
+
+
+
+def _get_kwargs(
+    id: str,
+
+) -> dict[str, Any]:
+
+
+
+
+
+
+    _kwargs: dict[str, Any] = {
+        "method": "get",
+        "url": "/jobs/{id}/review".format(id=quote(str(id), safe=""),),
+    }
+
+
+    return _kwargs
+
+
+
+def _parse_response(*, client: AuthenticatedClient | Client, response: httpx.Response) -> ErrorResponse | ExtractionReview | None:
+    if response.status_code == 200:
+        response_200 = ExtractionReview.from_dict(response.json())
+
+
+
+        return response_200
+
+    if response.status_code == 401:
+        response_401 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_401
+
+    if response.status_code == 403:
+        response_403 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_403
+
+    if response.status_code == 404:
+        response_404 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_404
+
+    if response.status_code == 409:
+        response_409 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_409
+
+    if response.status_code == 429:
+        response_429 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_429
+
+    if client.raise_on_unexpected_status:
+        raise errors.UnexpectedStatus(response.status_code, response.content)
+    else:
+        return None
+
+
+def _build_response(*, client: AuthenticatedClient | Client, response: httpx.Response) -> Response[ErrorResponse | ExtractionReview]:
+    return Response(
+        status_code=HTTPStatus(response.status_code),
+        content=response.content,
+        headers=response.headers,
+        parsed=_parse_response(client=client, response=response),
+    )
+
+
+def sync_detailed(
+    id: str,
+    *,
+    client: AuthenticatedClient | Client,
+
+) -> Response[ErrorResponse | ExtractionReview]:
+    """ Get an extraction review
+
+     Return the immutable machine output beside the current corrected output and append-only
+    review events. A succeeded extraction with no confirmations returns a synthesized pending review
+    at version 0. Cross-tenant and unknown jobs return `404`.
+
+    Args:
+        id (str): Prefixed public id for an OCR job (`opj_…`). Example: opj_V1StGXR8_Z5jdHi6B-myT.
+
+    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[ErrorResponse | ExtractionReview]
+     """
+
+
+    kwargs = _get_kwargs(
+        id=id,
+
+    )
+
+    response = client.get_httpx_client().request(
+        **kwargs,
+    )
+
+    return _build_response(client=client, response=response)
+
+def sync(
+    id: str,
+    *,
+    client: AuthenticatedClient | Client,
+
+) -> ErrorResponse | ExtractionReview | None:
+    """ Get an extraction review
+
+     Return the immutable machine output beside the current corrected output and append-only
+    review events. A succeeded extraction with no confirmations returns a synthesized pending review
+    at version 0. Cross-tenant and unknown jobs return `404`.
+
+    Args:
+        id (str): Prefixed public id for an OCR job (`opj_…`). Example: opj_V1StGXR8_Z5jdHi6B-myT.
+
+    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:
+        ErrorResponse | ExtractionReview
+     """
+
+
+    return sync_detailed(
+        id=id,
+client=client,
+
+    ).parsed
+
+async def asyncio_detailed(
+    id: str,
+    *,
+    client: AuthenticatedClient | Client,
+
+) -> Response[ErrorResponse | ExtractionReview]:
+    """ Get an extraction review
+
+     Return the immutable machine output beside the current corrected output and append-only
+    review events. A succeeded extraction with no confirmations returns a synthesized pending review
+    at version 0. Cross-tenant and unknown jobs return `404`.
+
+    Args:
+        id (str): Prefixed public id for an OCR job (`opj_…`). Example: opj_V1StGXR8_Z5jdHi6B-myT.
+
+    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[ErrorResponse | ExtractionReview]
+     """
+
+
+    kwargs = _get_kwargs(
+        id=id,
+
+    )
+
+    response = await client.get_async_httpx_client().request(
+        **kwargs
+    )
+
+    return _build_response(client=client, response=response)
+
+async def asyncio(
+    id: str,
+    *,
+    client: AuthenticatedClient | Client,
+
+) -> ErrorResponse | ExtractionReview | None:
+    """ Get an extraction review
+
+     Return the immutable machine output beside the current corrected output and append-only
+    review events. A succeeded extraction with no confirmations returns a synthesized pending review
+    at version 0. Cross-tenant and unknown jobs return `404`.
+
+    Args:
+        id (str): Prefixed public id for an OCR job (`opj_…`). Example: opj_V1StGXR8_Z5jdHi6B-myT.
+
+    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:
+        ErrorResponse | ExtractionReview
+     """
+
+
+    return (await asyncio_detailed(
+        id=id,
+client=client,
+
+    )).parsed