Michael-JB/bm25

A BM25 embedder, scorer, and search engine, written in Rust.

56
/ 100
Established

This project helps you build a keyword search engine or relevance scorer for text documents. You provide a collection of documents, and it processes them to create numerical representations, allowing you to quickly find documents most relevant to a specific search query. It's designed for software developers who need to integrate efficient text search capabilities into their applications.

56 stars and 291,616 monthly downloads.

Use this if you are a developer building an application that needs fast, in-memory keyword search or document-to-query relevance scoring.

Not ideal if you need a full-fledged, out-of-the-box search solution for end-users without writing code, or if you need to rank results based on semantic meaning beyond keywords.

information-retrieval text-search relevance-ranking application-development
No Package No Dependents
Maintenance 10 / 25
Adoption 18 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

56

Forks

7

Language

Rust

License

MIT

Last pushed

Mar 09, 2026

Monthly downloads

291,616

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Michael-JB/bm25"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.