doc-loader: retain Azure Doc Intelligence API metadata in Document parser #28382
Conversation
dosubot
bot
added
the
size:XS
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
dosubot
bot
added
community
| @@ -71,7 +71,7 @@ def _generate_docs_page(self, result: Any) -> Iterator[Document]: | |||
| yield d | |||
|
|
|||
| def _generate_docs_single(self, result: Any) -> Iterator[Document]: | |||
| yield Document(page_content=result.content, metadata={}) | |||
| yield Document(page_content=result.content, metadata=result) | |||
There was a problem hiding this comment.
is result always a dict? I see it typed as Any.
There was a problem hiding this comment.
No you are right, it is type AnalyzeResult which has an as_dict method. I will adjust accordingly, thanks for pointing out!
The azure result function is implemented generically using a type placeholder (type variable) (PollingReturnType_co), which allows flexibility for different use cases. This is why the docstring states Any. However, during initialization, the specific polling method enforces the return type to be AnalyzeResult in this context, as it deserializes the server response into this strongly-typed object.
There was a problem hiding this comment.
@ccurme I kindly ask if there is an update in the review process :)
dosubot
bot
added
the
lgtm
Description:
This PR modifies the doc_intelligence.py parser in the community package to include all metadata returned by the Azure Doc Intelligence API in the Document object. Previously, only the parsed content (markdown) was retained, while other important metadata such as bounding boxes (bboxes) for images and tables was discarded. These image bboxes are crucial for supporting use cases like multi-modal RAG workflows when using Azure Doc Intelligence.
The change ensures that all information returned by the Azure Doc Intelligence API is preserved by setting the metadata attribute of the Document object to the entire result returned by the API, rather than an empty dictionary. This extends the parser's utility for complex use cases without breaking existing functionality.
Issue:
This change does not address a specific issue number, but it resolves a critical limitation in supporting multimodal workflows when using the LangChain wrapper for the Azure API.
Dependencies:
No additional dependencies are required for this change.