Retrieval Python Packages

fastembed

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

mteb

MTEB: Massive Text Embedding Benchmark

bm25s

Fast BM25 search in Python, powered by Numpy and Numba

beir

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

pageindex

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

fastembed-gpu

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

gritlm

Generative Representational Instruction Tuning

act-atmos

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

cellin

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

libfmp

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

semble

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

inferedge-moss

Official Repo of Moss

mxbai-rerank

Crispy reranking models by Mixedbread

intel-extension-for-transformers

Repository of Intel® Intel Extension for Transformers

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.

prism-rag

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

openkb

OpenKB: Open LLM Knowledge Base

byaldi

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

memobase

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

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.

bm25

Fast BM25 search in Python, powered by Numpy and Numba

aelfrice

Bayesian memory that learns from feedback for LLM agents

brinicle

A resource-efficient C++ vector index engine built for low-RAM production workloads

vidore-benchmark

Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.