[Feature] request for reply the image in the pdf

[mikeyang01]

MaxKB Version

latest

Please describe your needs or suggestions for improvements

In the current version of MaxKB, when replying to user questions based on uploaded PDFs, image content from the PDF is not included in the response. This causes an issue when the PDF contains important visual information such as diagrams, charts, or tables that are essential for understanding the context.

This limitation reduces the completeness and usefulness of AI replies, especially for users relying on visual context in technical documents, manuals, or reports.

Please describe the solution you suggest

No response

Additional Information

No response

[baixin513]

Thank you for your feedback. The PDF itself is essentially an image, and the current document content extraction node only supports extracting text from PDFs, not images.