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

Efficient Retrieval Augmentation and Generation Framework

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

Open Source Semantic Search for your AI Agent

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

Late Interaction Models Training & Retrieval

Neural Search

High-Performance Engine for Multi-Vector Search

PyLate efficient inference engine

ColBERT humor dataset for the task of humor detection, containing 200,000 jokes/news

An easy-to-use python toolkit for flexibly adapting various neural ranking models to target domain.

Vector Database with support for late interaction and token level embeddings.

This repository helps you evaluate your models on the FreshStack benchmark!

Tree-based indexes for neural-search

A demonstration of hybrid search with reranking using Qdrant and BGE-M3 model. A showcase of dense and sparse retrieval combined with ColBERT reranking for optimal search results

LEMUR reduces multi-vector retrieval for late interaction models such as ColBERT into regular single-vector retrieval.

An overview of popular reranking models and architectures for 2 stage RAG pipelines

Official codebase for the ACL 2025 Findings paper: Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval.

A list of multi-vector retrieval resources

Efficient late-interaction retrieval systems in Julia!

CLI for semantic grep

ColBERT-style neural retrieval for Elixir

Boost RAG performance with question decomposer

Multi-paradigm embedding library: ColBERT, dense, sparse, vision-language, and time series models

Open source ColBERT based document database

Index GitHub repositories to ColBERT models and serve them with GRPC or FastAPI

A Powerful Python Library to Build AI Applications with the RAG

建設の技術基準に関する質問の専門性粒度（細かい/粗い）を96%正確に自動判定し、最適なRAGシステム（ColBERT/Naive）を選択する実用的なAgentic RAGシステムのMVPです。2025年11月に公開された河川砂防ダムの技術基準を対象に４つのRAGシステムを構築し、専門性の粒度が異なる200問の質問に対して、精度と速度を比較した。

This is the Information Retrieval 2023-2024 fall semester CEID course project.

This app is a personalized music recommendation system that uses a Retrieval-Augmented Generation (RAG) framework, leveraging Spotify's API, LangChain, ChromaDB, and ColBERT embeddings to create playlists based on user mood and preferences.