R2R, the Supabase for RAG, was designed to bridge the gap between local LLM experimentation and scalable, production-ready Retrieval-Augmented Generation (RAG) applications. R2R provides a comprehensive SOTA platform that is built around a RESTful API for ease of use.

Key Features

  • πŸ“ Multimodal Support: Ingest files ranging from .txt, .pdf, .json to .png, .mp3, and more.
  • πŸ” Hybrid Search: Combine semantic and keyword search with reciprocal rank fusion for enhanced relevancy.
  • πŸ”— Graph RAG: Automatically extract relationships and build knowledge graphs.
  • πŸ—‚οΈ App Management: Efficiently manage documents and users with full authentication.
  • πŸ”­ Observability: Observe and analyze your RAG engine performance.
  • πŸ”Œ Extensibility: Develop your application further with easy builder + factory pattern.
  • πŸ–₯️ Dashboard: Use the R2R Dashboard, an open-source React+Next.js app with optional authentication for interacting with R2R.


After installing, the R2R Quickstart is your go to for a step-by-step guide to get up and running with R2R in minutes. The guide demonstrates R2R’s Retrieval-Augmented Generation (RAG) system by ingesting sample documents and then showcasing features for search, RAG, logging, analytics, and document management.

Getting Started

To get started with R2R, we recommend starting with the quickstart and then moving on to specific cookbooks.

Auth & Admin Features

  • User Auth: A cookbook showing how to authenticate users using R2R.
  • Analytics & Observability: A cookbook showing R2Rs end to end logging and analytics.
  • Dashboard: A how-to guide on connecting with the R2R Admin/User Dashboard.

RAG Cookbooks

  • Multiple LLMs: A simple cookbook showing how R2R supports multiple LLMs.
  • Hybrid Search: A brief introduction to running hybrid search with R2R.
  • Multimodal RAG: A cookbook on multimodal RAG with R2R.
  • Knowledge Graphs: A walkthrough of automatic knowledge graph generation with R2R.
  • Advanced Graphs: A walkthrough of R2Rs advanced RAG features.
  • Local RAG: A quick cookbook demonstration of how to run R2R with local LLMs.
  • Reranking: A short guide on how to apply reranking to R2R results.


Join our Discord server to get support and connect with both the R2R team and other developers in the community. Whether you’re encountering issues, looking for advice on best practices, or just want to share your experiences, we’re here to help.