Skip to main content
Screenshot 2025-03-27 at 6 35 02 AM

The most advanced AI retrieval system.

Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

About

R2R is an advanced AI retrieval system supporting Retrieval-Augmented Generation (RAG) with production-ready features. Built around a RESTful API, R2R offers multimodal content ingestion, hybrid search, knowledge graphs, and comprehensive document management.

R2R also includes a Deep Research API, a multi-step reasoning system that fetches relevant data from your knowledgebase and/or the internet to deliver richer, context-aware answers for complex queries.

Usage

# Basic search
results = client.retrieval.search(query="What is DeepSeek R1?")

# RAG with citations
response = client.retrieval.rag(query="What is DeepSeek R1?")

# Deep Research RAG Agent
response = client.retrieval.agent(
  message={"role":"user", "content": "What does deepseek r1 imply? Think about market, societal implications, and more."},
  rag_generation_config={
    "model": "anthropic/claude-3-7-sonnet-20250219",
    "extended_thinking": True,
    "thinking_budget": 4096,
    "temperature": 1,
    "top_p": None,
    "max_tokens_to_sample": 16000,
  },
)

Getting Started

# Quick install and run in light mode
pip install r2r
export OPENAI_API_KEY=sk-...
python -m r2r.serve

# Or run in full mode with Docker
# git clone git@github.com:SciPhi-AI/R2R.git && cd R2R
# export R2R_CONFIG_NAME=full OPENAI_API_KEY=sk-...
# docker compose -f compose.full.yaml --profile postgres up -d

For detailed self-hosting instructions, see the self-hosting docs.

Demo

https://github.com/user-attachments/assets/173f7a1f-7c0b-4055-b667-e2cdcf70128b

Using the API

1. Install SDK & Setup

# Install SDK
pip install r2r  # Python
# or
npm i r2r-js    # JavaScript

2. Client Initialization

from r2r import R2RClient
client = R2RClient(base_url="http://localhost:7272")
const { r2rClient } = require('r2r-js');
const client = new r2rClient("http://localhost:7272");

3. Document Operations

# Ingest sample or your own document
client.documents.create(file_path="/path/to/file")

# List documents
client.documents.list()

Key Features

  • 📁 Multimodal Ingestion: Parse .txt, .pdf, .json, .png, .mp3, and more
  • 🔍 Hybrid Search: Semantic + keyword search with reciprocal rank fusion
  • 🔗 Knowledge Graphs: Automatic entity & relationship extraction
  • 🤖 Agentic RAG: Reasoning agent integrated with retrieval
  • 🔐 User & Access Management: Complete authentication & collection system

Community & Contributing

Our Contributors

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

r2r-3.6.6.tar.gz (396.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

r2r-3.6.6-py3-none-any.whl (514.0 kB view details)

Uploaded Python 3

File details

Details for the file r2r-3.6.6.tar.gz.

File metadata

  • Download URL: r2r-3.6.6.tar.gz
  • Upload date:
  • Size: 396.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.11

File hashes

Hashes for r2r-3.6.6.tar.gz
Algorithm Hash digest
SHA256 f84c626e7fd9512ea312c75cc1d20221223a391222c382980a82100f25697258
MD5 8cb2f3505bc4f144a52c487cf3de0456
BLAKE2b-256 81009b9953e9adf115ed245e4d52ce1a9d8cbc4ae2c037315b748a7f0e2f1f6e

See more details on using hashes here.

File details

Details for the file r2r-3.6.6-py3-none-any.whl.

File metadata

  • Download URL: r2r-3.6.6-py3-none-any.whl
  • Upload date:
  • Size: 514.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.11

File hashes

Hashes for r2r-3.6.6-py3-none-any.whl
Algorithm Hash digest
SHA256 48c9326db0ff23c41affdb846df0c9014827b1316a14bcc87bb43c810b0410f9
MD5 a6d3f905c1e4f9e537dac7d9d1f4b92a
BLAKE2b-256 1413ad97d16a161bd96148b7562c3f6298c9cae79c7e0b7b1025a2fc74da95c0

See more details on using hashes here.

Release history Release notifications | RSS feed

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page