pymupdf

PDF → LLM-ready markdown. Built for RAG pipelines that actually work. Open source.

[pymupdf @pymupdf]

@henry19840301 Hello from PyMuPDF! I'm wondering how you use PyMuPDF in Deerflow and if you are considering integrating the new PyMuPDF 2.0 with the project?

[pymupdf @pymupdf]

Hello! PyMuPDF 2.0 released this week! See https://t.co/N58mRFGE9i for details.

[pymupdf @pymupdf]

@yfedoseev Noticed your PDF Oxide project, what version of PyMuPDF & PyMuPDF4LLM did you use for your benchmarking results?

[pymupdf @pymupdf]

@prantheman__ Just curious what happened to Glimmer?

[pymupdf @pymupdf]

New blog just released: https://t.co/b3frTHdhq4

[pymupdf @pymupdf]

@VenuChoudhary6 @dasepmochly LOL - good to know!

[pymupdf @pymupdf]

@VenuChoudhary6 @dasepmochly Benchmarks please if possible! Version of PyMuPDF, if PyMuPDF4LLM used etc. :)

[kami @sanv1rathore]

my top 5 python libraries this month:

- requests
- sqlite3
- tqdm
- concurrent.futures
- PyMuPDF

[Kalvin Mizzi @kalvinmizzi]

Needed to share bank statements but only the lines for one specific vendor. Asked Claude Code to black out everything else across 5 PDFs. It pulled in PyMuPDF, found the right rows, drew redaction boxes, and saved clean copies. Marker-on-paper, automated.

[CHIAMAKA ODIKE @chia_makahh]

So how did I make it work?

I extracted the PDF text with PyMuPDF, split it into chunks, turned them into embeddings with Sentence Transformers, and stored them in ChromaDB.

PDF → chunks → embeddings → ChromaDB
That was the basic setup

[pymupdf @pymupdf]

Great article explaining routing shortcuts with PDF Extraction: https://t.co/ylvHXH3otP

[pymupdf @pymupdf]

https://t.co/wtxB3aCWIS

[Kushal Byatnal @kushalbyatnal]

proposal for ending the document processing benchmark wars:

1. assume every benchmark is biased (alas)
2. test vendors on your own data
3. choose the one that works
4. everyone stops arguing and we go back to building

thank you for coming to my ted talk

[pymupdf @pymupdf]

@ajanraj25 @pranvtwt respect - thank you @ajanraj25

[pymupdf @pymupdf]

@ajanraj25 @pranvtwt Well at least I appreciate this - thank you :) Ghostscript is AGPL licensed and this was politely pointed out - that is all.

[pymupdf @pymupdf]

And of course 10 years! :)

[pymupdf @pymupdf]

It's time to celebrate over 1 billion downloads of PyMuPDF! 🎉
https://t.co/pFCbTRUL0r

[pymupdf @pymupdf]

We hit the 1 billion mark on PyPI yesterday! https://t.co/fRJZwIwP49
🐮🎉

[artifex @artifex]

With PyMuPDF4LLM 1.28.2, we move to a fully AGPL v3 licensing with the PyMuPDF Layout package dependency and all the source goes public. The fastest CPU-only layout engine for PDF is now genuinely open source.
Read more: https://t.co/ABDBZOKjmk

[artifex @artifex]

Sometimes an open source contribution starts as a problem in your own workflow. The author of this piece wanted PyMuPDF4LLM as a LangChain document loader, found it didn't exist, and built it. This is a great writeup of what followed, from first PR to standalone package: https://t.co/BxiSAbZz8x