Michael-JB/bm25

Fast BM25 search in Python, powered by Numpy and Numba

Two-tier hybrid search for Rust: sub-millisecond initial results via potion-128M, quality-refined rankings in 150ms via MiniLM-L6-v2. Combines lexical (Tantivy BM25) and semantic (vector cosine) search with Reciprocal Rank Fusion. Progressive iterator API, f16 SIMD vector index, feature-gated compilation.

BM25 full-text search that actually finds what you type — fuzzy substrings across token boundaries, accent-insensitive, with byte-offset highlights. Python + Rust, built for hybrid search with vector DBs.

SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.

Retrieval and Retrieval-augmented LLMs

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

Rust library for generating vector embeddings and reranking locally!

A collection of languages stemmers and stopwords for Lunr Javascript library