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

Open-source context retrieval layer for AI agents

MTEB: Massive Text Embedding Benchmark

SimpleMem: Efficient Lifelong Memory for LLM Agents

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

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

Apache Lucene.NET

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

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

Study guides for MIT's 15.003 Data Science Tools

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Fast lexical search implementing BM25 in Python

Superlinked is a Python framework for AI Engineers building high-performance search & recommendation applications that combine structured and unstructured data.

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

Parsing-free RAG supported by VLMs

SGPT: GPT Sentence Embeddings for Semantic Search

Epsilla is a high performance Vector Database Management System

Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.

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

Rust library for vector embeddings and reranking.

[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"

Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.

Generative Representational Instruction Tuning

My personal note about local and global descriptor

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

🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved benchmark datasets and supports 7+ retrieval techniques, 24+ state-of-the-art Reranking models, and multiple RAG methods.

Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache.

Retrieve, Read and LinK: Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget (ACL 2024)

In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.

The official implementation of ICLR 2020, "Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering".