[Feature] Add Optical Character Recognition (OCR) Fallback for Scanned PDFs

[knoxiboy]

Description
If a user uploads a scanned PDF or a document consisting of images, the standard text extraction libraries will fail, resulting in an empty or useless vector index.

Implementation

1. Integrate an OCR library (e.g., Tesseract via pytesseract or a cloud API like AWS Textract) into the document processing pipeline.
2. Implement a check: if the standard PDF parser extracts very few text characters relative to the file size, automatically fall back to processing the pages as images through the OCR engine.
3. Inform the user in the UI if OCR is being used, as it may take longer to process.

Level: Advanced
Affected Files: backend/parser.py, frontend/

[knoxiboy]

/assign gssoc'26
@param20h Please assigne this issue to me.

[github-actions]

Hi @knoxiboy! 👋

Thanks for opening this issue! We are thrilled to have you contribute to PDF-Assistant-RAG for GSSoC 2026.

📌 Before you start:

• Make sure you have read our Contributing Guidelines.
• Wait for a project admin to assign this issue to you before working on it.
• Remember to branch off dev and not main.

Happy Coding! 🚀