Retrieval Python Packages

fastembed

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

11.6M 3K 196

mteb

MTEB: Massive Text Embedding Benchmark

2.7M 3K 608

bm25s

Fast BM25 search in Python, powered by Numpy and Numba

1.4M 2K 99

beir

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

39K 2K 243

pageindex

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

36K 26K 2K

gritlm

Generative Representational Instruction Tuning

18K 691 50

fastembed-gpu

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

16K 3K 196

cellin

build long-lived multimodal memory, dream over it, and retrieve context with transparent weighting

12K 0 0

act-atmos

Atmospheric data Community Toolkit - A python based toolkit for exploring and analyzing time series atmospheric datasets

11K 183 40

inferedge-moss

Official Repo of Moss

9K 330 33

libfmp

libfmp - Python package for teaching and learning Fundamentals of Music Processing (FMP)

8K 222 20

semble

Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read

8K 514 46

mxbai-rerank

Crispy reranking models by Mixedbread

8K 51 7

vera-ai

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

7K 70 8

intel-extension-for-transformers

Repository of Intel® Intel Extension for Transformers

6K 2K 217

memobase

User Profile-Based Long-Term Memory for AI Chatbot Applications.

5K 3K 209

prism-rag

PRISM — Epistemic Graph RAG with Spreading Activation. Novel retrieval that understands how knowledge relates, not just what it says.

5K 1 0

byaldi

Use late-interaction multi-modal models such as ColPali in just a few lines of code.

5K 847 93

bm25

Fast BM25 search in Python, powered by Numpy and Numba

4K 2K 99

context-router-cli

Memory-aware context engine for AI coding agents — up to 91% fewer tokens, 17/18 rank-1 across 6 OSS projects. MCP-native, multi-repo, with persistent observations & decisions.

4K 6 2

openkb

OpenKB: Open LLM Knowledge Base

4K 1K 113