Docker — The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) with a RESTful API.

This installation guide is for Full R2R. For solo developers or teams prototyping, we recommend starting with R2R Light.

This guide will walk you through installing and running R2R using Docker, which is the quickest and easiest way to get started.

Prerequisites

Docker installed on your system. If you haven’t installed Docker yet, please refer to the official Docker installation guide.

Install the R2R CLI & Python SDK

First, install the R2R CLI and Python SDK:

$ pip install r2r

We are actively developing a distinct CLI binary for R2R for easier installation. Please reach out if you have any specific needs or feature requests.

Start R2R with Docker

The full R2R installation does not use the default r2r.toml, instead it provides overrides through a pre-built custom configuration, full.toml.

Cloud LLM RAG

Local LLMs

Custom Configuration

The above command will automatically pull the necessary Docker images and start all the required containers, including R2R, Hatchet, and Postgres+pgvector. The required additional services come bundled into the full R2R Docker Compose by default.

The end result is a live server at http://localhost:7272 serving the R2R API.

In addition to launching a RESTful API, the R2R Docker also launches a applications at localhost:7273 and localhost:7274, which you can read more about here.

Stopping R2R

Safely stop your system by running r2r docker-down to avoid potential shutdown complications.

Next Steps

After successfully installing R2R:

Verify Installation: Ensure all components are running correctly by accessing the R2R API at http://localhost:7272/v3/health.
Quick Start: Follow our R2R Quickstart Guide to set up your first RAG application.
In-Depth Tutorial: For a more comprehensive understanding, work through our R2R Walkthrough.
Customize Your Setup: Configuration your R2R system.

If you encounter any issues during installation or setup, please use our Discord community or GitHub repository to seek assistance.