SciPhi-AI/R2R
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
This system helps you build intelligent applications that can answer complex questions using your own data and external information. You feed it various documents, like PDFs, text files, and even audio, and it provides accurate, context-aware answers. It's designed for developers who want to create sophisticated AI-powered tools.
7,725 stars.
Use this if you are a developer building an application that needs to answer nuanced questions by pulling information from a diverse set of internal documents and potentially the internet.
Not ideal if you are looking for an off-the-shelf chatbot or a simple search engine without needing to integrate it into a custom application.
Stars
7,725
Forks
630
Language
Python
License
MIT
Category
Last pushed
Nov 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/SciPhi-AI/R2R"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
HKUDS/LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
beir-cellar/beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across...
HKUDS/RAG-Anything
"RAG-Anything: All-in-One RAG Framework"
superlinear-ai/raglite
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
illuin-tech/vidore-benchmark
Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.