[Bug]: Picture Description not generated during document ingestion when feature is enabled

[Revathypv]

OpenRAG Version

0.3.0

Deployment Method

uv add (installed in project)

Operating System

macOS 26.3

Python Version

Python 3.13.3

Affected Area

Chat (chat interface, conversations, AI responses)

Bug Description

When Picture Description is enabled in the document ingestion settings, the system does not generate descriptions for images in the uploaded document. After uploading a document containing images and completing ingestion, asking questions related to the images returns the message: "No relevant supporting sources were found for the image description…" instead of providing an image description.

Steps to Reproduce

Make sure 'Picture Descriptions' is enabled in settings

1. Upload attached document
2. Navigate to chat
3. Ask question "Describe the image in the document "Image test pdf"

Image test pdf.pdf

Expected Behavior

The system should generate text descriptions for images and answer questions based on image content.

Actual Behavior

The system responds that no image details were found in the document

Relevant Logs

Screenshots

No response

Additional Context

No response

Checklist

• I have searched existing issues to ensure this bug hasn't been reported before.
• I have provided all the requested information.