chunkrank

Model-aware text chunking and answer re-ranking for LLM pipelines. Automatically adapts chunk size to tokenizer and context window, then consolidates and ranks answers across chunks.

Installation

In a virtualenv (see these instructions if you need to create one):

pip3 install chunkrank

Dependencies

  • None

Releases

Version Released Bullseye
Python 3.9
Bookworm
Python 3.11
Trixie
Python 3.13
Files
1.0.0 2026-03-10      
0.2.4 2026-01-15      
0.2.3 2026-01-15      
0.2.2 2026-01-15      
0.2.1 2026-01-15      
0.2.0 2026-01-13      

Issues with this package?

Page last updated 2026-03-13 04:34:25 UTC