Skip to main content
rank_bm25 is an open-source collection of algorithms designed to query documents and return the most relevant ones, commonly used for creating search engines. See its project page for available algorithms.

​
Installation and setup

First, you need to install rank_bm25 python package. 
pip install rank_bm25

​
Retriever

See a usage example. 
from langchain_community.retrievers import BM25Retriever
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.