bm25

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

search-engine vector nearest-neighbor-search full-text-search approximate-nearest-neighbor-search embedding bm25 information-retrival cpp20 rag hnsw vector-search vector-database hybrid-search cpp20-modules ai-native tensor-database vectordatabase multi-vector

UpdatedNov 4, 2025
C++

SylphAI-Inc /AdalFlow

Star3.9k

AdalFlow: The library to build & auto-optimize LLM applications.

python nlp agent machine-learning information-retrieval framework ai chatbot optimizer question-answering summarization trainer bm25 retriever faiss reranker rag llm generative-ai auto-prompting

UpdatedOct 8, 2025
Python

SeekStorm /SeekStorm

Star1.8k

SeekStorm - sub-millisecond full-text search library & multi-tenancy server in Rust

search rust search-engine query realtime saas full-text-search index apache2 bm25 enterprise-search search-service geosearch faceting okapi-bm25 search-server lexical-search sparse-retrieval

UpdatedOct 23, 2025
Rust

xhluca /bm25s

Star1.4k

Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy

search information-retrieval retrieval bm25 okapi-bm25 rag robertson bm25-plus bm25-l lexical-search

UpdatedOct 31, 2025
Python

winkjs /wink-nlp

Star1.3k

Developer friendly Natural Language Processing ✨

visualization nlp natural-language-processing sentiment-analysis pattern-matching chatbot vectorizer ner wink hacktoberfest pos-tagging tokenize bm25 sentence-boundary-detection word-vectors sbd named-entity-extraction negation-handling custom-entity-detection wink-nlp

UpdatedAug 9, 2025
JavaScript

dorianbrown /rank_bm25

Star1.3k

A Collection of BM25 Algorithms in Python

information-retrieval algorithm ranking bm25

UpdatedOct 8, 2024
Python

shibing624 /similarities

Star879

Similarities: a toolkit for similarity calculation and semantic search. 相似度计算、匹配搜索工具包，支持亿级数据文搜文、文搜图、图搜图，python3开发，开箱即用。

nlp search-engine deep-learning matching pytorch similarity image-search bm25 text-matching similarity-search image-similarity faiss

UpdatedOct 29, 2024
Python

BUAADreamer /EasyRAG

Star590

Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案

qa retrieval network-operations bge ccf bm25 hyde gte aiops rag rrf llm retrieval-augmented-generation minicpm glm4

UpdatedNov 17, 2024
Python

raphaelsty /cherche

Star334

Neural Search

search nlp machine-learning natural-language-processing information-retrieval retrieval reader neural-networks question-answering semantic-search searching bm25 flashtext vector-search neural-search

UpdatedJun 1, 2024
Python

cjymz886 /sentence-similarity

Star291

对四种句子/文本相似度计算方法进行实验与比较

word2vec text-similarity idf bm25 sentence-similarity cosinesimilarity

UpdatedSep 1, 2020
Python

nhirakawa /BM25

Star238

A Python implementation of the BM25 ranking function.

python search-engine information-retrieval parse bm25 query-processor

UpdatedNov 13, 2019
Python

AmenRa /retriv

Star238

A Python Search Engine for Humans 🥸

search search-engine information-retrieval tf-idf numba semantic-search bm25 search-engine-optimization dense-retrieval sparse-retrieval hybrid-retrieval

UpdatedApr 22, 2024
Python

iresearch-toolkit /iresearch

Star184

IResearch is a cross-platform, high-performance search analytics library written entirely in C++ with the focus on a pluggability of different ranking/similarity models

search-engine analytics ranking tf-idf bm25 relevant-search