search

pymupdf / RAG

RAG (Retrieval-Augmented Generation) Chatbot Examples Using PyMuPDF
https://pymupdf.readthedocs.io/en/latest/pymupdf4llm
GNU Affero General Public License v3.0
539 stars 82 forks source link

Add opportunity to filter out some images #48

Closed dantetemplar closed 5 months ago

dantetemplar commented 5 months ago

A lot of 5x5 pixel images were generated for my documents. I think it would be convenient to filter such images.

dantetemplar commented 5 months ago

https://github.com/dantetemplar/pymupdf4llm