Hacker News new | ask | show | jobs
by hugodutka 695 days ago
PyMuPDF, a PDF library for Python.
1 comments
jimmySixDOF 693 days ago
A different approach from vanilla OCR/parsing seems to be this mixed ColPali integrating a purposed small vision models and a ColBERT type indexing for retrieval. So - if search is the intended use case - it can skip the whole OCR step entirely.

[1] https://huggingface.co/blog/manu/colpali

link