retrieval-augmented-generation

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

Unified framework for building enterprise RAG pipelines with small, specialized models

💡 All-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows

Retrieval and Retrieval-augmented LLMs

Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

Agent S: an open agentic framework that uses computers like a human

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

The open source platform for AI-native application development.

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

Harness LLMs with Multi-Agent Programming

Local Deep Research is an AI-powered assistant that transforms complex questions into comprehensive, cited reports by conducting iterative analysis using any LLM across diverse knowledge sources including academic databases, scientific repositories, web content, and private document collections.

AI Search & RAG Without Moving Your Data. Get instant answers from your company's knowledge across 100+ apps while keeping data secure. Deploy in minutes, not months.

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

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

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.