Computes BM25 Vectorization of Text.

High-performance BM25 implementation in TypeScript

Configurable BM25 Text Search Engine with simple semantic search support

A simple, easy to use implementation of the Okapi BM25 algorithm.

Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking

ParadeDB BM25 full-text search indexes and operators for Prisma 8

TypeScript port of tcvdb_text — BM25 sparse vector encoder for Tencent Cloud VectorDB

Shared knowledge core - parser, search (BM25), graph builder for CrewX

Unified PostGraphile v5 search plugin — abstracts tsvector, BM25, pg_trgm, and pgvector behind a single adapter-based architecture with composite searchScore

BM25 full-text search engine for CrewX documents and code

Kura — retrieval engine: BM25 keyword search (+ hybrid fusion), portable and zero-dependency. Pairs with @kurajs/core's vector search.

Bayesian probability transforms for BM25 retrieval scores

Chroma BM25 sparse embedding function implemented in TypeScript

A lightweight, file-backed vector database for Node.js and browsers with Pinecone-compatible filtering and hybrid BM25 search.

BM25 search, reranker, and hybrid fusion for hybrid RAG systems

The BM25 (Best Matching 25) embedding function is a sparse embedding implementation that uses the BM25 ranking algorithm to convert text into sparse vectors for efficient full-text search.

Native perf module for obsidian-tc — vector ops, BM25, sqlite-vec, V2 clustering hooks

TypeScript SDK for Ratel — context engineering platform for AI agents. BM25 tool retrieval, MCP ingestion, framework-neutral capability tools.

Noir store — embedded storage: better-sqlite3 + FTS5 (BM25, window snippets) + sqlite-vec (384-dim kNN).

Noir context — SHA-256 incremental indexer and hybrid retrieval (BM25 + vector kNN + Reciprocal Rank Fusion).