thom-heinrich/chonkify

Extractive document compression for RAG and agent pipelines. +69% vs LLMLingua, +175% vs LLMLingua2 on information recovery. Compiled wheels, try it out.

3 best points · 0 comments · 1 Hacker News post · 21 GitHub stars · View on GitHub

Hacker News discussions

• Chonkify – compression for RAG and Agents that outperforms LLMLingua by ~4 times (3 points, 0 comments, by thomheinrich, 2026-03-26)