R2R/README.md

The ultimate open source AI powered answer engine

About

R2R (RAG to Riches) bridges local LLM experiments with production-ready Retrieval-Augmented Generation (RAG). It offers developers a cutting-edge, comprehensive RAG system with a RESTful API for seamless integration.

For a more complete view of R2R, check out the full documentation.

Key Features

• 📁 Multimodal Support: Ingest files ranging from .txt, .pdf, .json to .png, .mp3, and more.
• 🔍 Hybrid Search: Combine semantic and keyword search with reciprocal rank fusion for enhanced relevancy.
• 🔗 Graph RAG: Automatically extract relationships and build knowledge graphs.
• 🗂️ App Management: Efficiently manage documents and users with rich observability and analytics.
• 🌐 Client-Server: RESTful API support out of the box.
• 🧩 Configurable: Provision your application using intuitive configuration files.
• 🔌 Extensible: Develop your application further with easy builder + factory pattern.
• 🖥️ Dashboard: Use the R2R Dashboard, an open-source React+Next.js app for a user-friendly interaction with R2R.

Table of Contents

1. Install
2. R2R Quickstart
3. R2R Dashboard
4. Community and Support
5. Contributing

Install

Note

Windows users are advised to use Docker to run R2R.

Installing with Pip 🐍

pip install r2r

# setup env
export OPENAI_API_KEY=sk-...
export POSTGRES_USER=YOUR_POSTGRES_USER
export POSTGRES_PASSWORD=YOUR_POSTGRES_PASSWORD
export POSTGRES_HOST=YOUR_POSTGRES_HOST
export POSTGRES_PORT=YOUR_POSTGRES_PORT
export POSTGRES_DBNAME=YOUR_POSTGRES_DBNAME

Installing with Docker 🐳

Note: The R2R client must still be installed, even when running with Docker. Download the Python client with pip install r2r.

To run R2R using Docker:

docker pull emrgntcmplxty/r2r:latest

docker run -d \
   --name r2r \
   -p 8000:8000 \
   -e POSTGRES_USER=$YOUR_POSTGRES_USER \
   -e POSTGRES_PASSWORD=$YOUR_POSTGRES_PASSWORD \
   -e POSTGRES_HOST=$YOUR_POSTGRES_HOST \
   -e POSTGRES_PORT=$YOUR_POSTGRES_PORT \
   -e POSTGRES_DBNAME=$YOUR_POSTGRES_DBNAME \
   -e OPENAI_API_KEY=$YOUR_OPENAI_API_KEY \
   emrgntcmplxty/r2r:latest

For local LLMs:

docker run -d \
   --name r2r \
   --add-host=host.docker.internal:host-gateway \
   -p 8000:8000 \
   -e POSTGRES_USER=$YOUR_POSTGRES_USER \
   -e POSTGRES_PASSWORD=$YOUR_POSTGRES_PASSWORD \
   -e POSTGRES_HOST=$YOUR_POSTGRES_HOST \
   -e POSTGRES_PORT=$YOUR_POSTGRES_PORT \
   -e POSTGRES_DBNAME=$YOUR_POSTGRES_DBNAME \
   -e OLLAMA_API_BASE=http://host.docker.internal:11434 \
   -e CONFIG_OPTION=local_ollama \
  emrgntcmplxty/r2r:latest

R2R Quickstart

The following quickstart offers a step-by-step guide on running R2R locally as well as through the Python SDK. The guide ingests a list of provided provided documents and shows search, RAG, and advanced functionality. The script powering the quickstart can be found at r2r/examples/quickstart.py, and it can be configured and extended with sufficient developer familiarity.

Document Ingestion and Management

1. Ingest Files:

   python -m r2r.examples.quickstart ingest_as_files
   

2. View Document Info:

   python -m r2r.examples.quickstart documents_overview
   

3. View User Overview:

   python -m r2r.examples.quickstart users_overview
   

Search and RAG Operations

1. Search Documents:

   python -m r2r.examples.quickstart search --query="Who was Aristotle?"
   

2. RAG Completion:

   python -m r2r.examples.quickstart rag --query="What was Uber's profit in 2020?"
   

3. Streaming RAG:

   python -m r2r.examples.quickstart rag --query="What was Lyft's profit in 2020?" --streaming=true
   

4. Hybrid Search RAG:

   python -m r2r.examples.quickstart rag --query="Who is John Snow?" --do_hybrid_search
   

For more detailed examples and advanced features, please refer to our Quickstart Guide.

R2R Dashboard

Interact with R2R using our open-source React+Next.js dashboard. Check out the Dashboard Cookbook to get started!

Community and Support

• Discord: Chat live with maintainers and community members
• Github Issues: Report bugs and request features

Explore our R2R Docs for tutorials and cookbooks on various R2R features and integrations, including:

• Client-Server
• Multiple LLMs
• Knowledge Graph RAG
• Multimodal RAG
• Hybrid Search
• Local RAG
• Reranking
• Dashboard

Contributing

We welcome contributions of all sizes! Here's how you can help:

• Open a PR for new features, improvements, or better documentation.
• Submit a feature request or bug report

Our Contributors