Match the project to your task before installing it.
Self-hosted AI Workspace · Public
R2R
Self-hosted LLM web UI covering Docker deployment, auth, model backends, OAI/Ollama endpoints, and reverse proxy checks.
Check whether this project matches your task before installing it.
What it can doSelf-hosting deployment checks, Docker volume review, auth configuration checks, OAI/Ollama endpoint validation, and recovery guidanceReview the portable capability path.
Before continuingVerify in a sandboxDo not treat a preview pack as a proven local install.
GitHub snapshot7.9k stars636 forks · 63 contributors
Doramagic.ai Last verification date: 2026-06-23 Verification method: source evidence, semantic profile, public page gate, and static build acceptance.
Publication status · 2026-06-23
What is R2R?
- R2R is a self-hosted LLM web UI for running model backends, knowledge features, user management, and chat access in your own environment.
- Best fit: Developers or small teams that need a self-hosted AI chat interface and can maintain Docker, storage, auth, model backends, and reverse proxy settings.
- Not for: Not for users who only need a single model API call or do not want to maintain containers, auth, networking, or service configuration.
- Capability added to an AI workflow: Self-hosting deployment checks, Docker volume review, auth configuration checks, OAI/Ollama endpoint validation, and recovery guidance
- First safe verification step: Verify Docker volumes, auth settings, OAI/Ollama endpoints, and rollback in an isolated environment first.
- Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
- Top risk: May increase setup, validation, or first-run risk for the user.
- Evidence base: https://github.com/SciPhi-AI/R2R, https://github.com/SciPhi-AI/R2R#readme, Human Manual, Pitfall Log
01
Quick decision
Use this section to decide whether the project is worth a deeper read.Self-hosted LLM web UI covering Docker deployment, auth, model backends, OAI/Ollama endpoints, and reverse proxy checks.
7.9k stars · 636 forks
02
What it can do
Translate the upstream project into concrete capabilities the user can judge before installing.Introduction, Installation & SDK Usage
Related topics: REST API, Services & Provider Architecture, Deployment, Configuration, Extensibility & Troubleshooting
Source: https://github.com/SciPhi-AI/R2R / Human Manual
REST API, Services & Provider Architecture
Related topics: Ingestion Modes, Parsers, Search & Agentic RAG, Deployment, Configuration, Extensibility & Troubleshooting
Source: https://github.com/SciPhi-AI/R2R / Human Manual
Ingestion Modes, Parsers, Search & Agentic RAG
Related topics: REST API, Services & Provider Architecture, Deployment, Configuration, Extensibility & Troubleshooting
Source: https://github.com/SciPhi-AI/R2R / Human Manual
Deployment, Configuration, Extensibility & Troubleshooting
Related topics: Introduction, Installation & SDK Usage, Ingestion Modes, Parsers, Search & Agentic RAG
Sources: [py/core/main/api/v3/documents_router.py](https://github.com/SciPhi-AI/R2R/blob/main/py/core/main/api/v3/documents_router.py) and [py/core/main/api/v3/retrieval_router.py](https://github.com/SciPhi-AI/R2R/blob/main/py/core/main/api/v3/retrieval_router.py).
Doramagic Pitfall Log
Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.
Source: Doramagic discovery, validation, and Project Pack records
Sources: https://github.com/SciPhi-AI/R2R, Human Manual, Project Pack evidence, and downstream validation signals.
03
Community Discussion Evidence
Project-level external discussion stays visible on the detail page, not only inside the manual.Community Discussion Evidence
12 source-linked itemsReview these external discussions before using R2R with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.
-
01
Security: need a private contact — [email protected] bounces
github / github_issue
-
02
[Security] CRITICAL auth bypass (default admin superuser for unauthentic
github / github_issue
-
03
Docs suggestion: add a compact RAG failure mode taxonomy checklist for i
github / github_issue
-
04
The search fails on huge query
github / github_issue
-
05
[Security][High] SQL injection in vector index management (create_index
github / github_issue
-
06
Entity UUID Mismatch After Graph Pul
github / github_issue
-
07
r2r-docs.sciphi.ai Website Down
github / github_issue
-
08
R2R Documentation Main Site Is Down
github / github_issue
-
09
Broken Link For Installation Guide
github / github_issue
-
10
v3.6.5
github / github_release
-
11
v3.6.4
github / github_release
-
12
v3.6.3
github / github_release
04
How to start
Only source-backed commands are shown here. Verify them in an isolated environment first.Try the prompt first
Test the workflow without installing the upstream project.
previewRead the Human Manual
Understand inputs, outputs, limits, and failure modes.
manualTake context to your AI host
Use the compiled assets in your preferred AI environment.
contextRun sandbox verification
Confirm install commands and rollback before using a primary environment.
verifypip install r2rOfficial start command · https://github.com/SciPhi-AI/R2R#readme · verified: yes
05
Human Manual
The English page must expose the real manual, not a short placeholder.8+ sections · Human Manual
R2R Manual
R2R (Reason to Retrieve) is an open-source retrieval-augmented generation (RAG) framework that exposes a RESTful API for multimodal content ingestion, hybrid search, knowledge-graph constr...
Open the full manual- https://github.com/SciPhi-AI/R2R Project Manual
- Table of Contents
- Introduction, Installation & SDK Usage
- Related Pages
- Overview
- Installation
- Light Mode (Single Python Process)
- Full Mode (Docker Compose)
Introduction, Installation & SDK Usage
Related topics: REST API, Services & Provider Architecture, Deployment, Configuration, Extensibility & Troubleshooting
Source: https://github.com/SciPhi-AI/R2R / Human Manual
REST API, Services & Provider Architecture
Related topics: Ingestion Modes, Parsers, Search & Agentic RAG, Deployment, Configuration, Extensibility & Troubleshooting
Source: https://github.com/SciPhi-AI/R2R / Human Manual
Ingestion Modes, Parsers, Search & Agentic RAG
Related topics: REST API, Services & Provider Architecture, Deployment, Configuration, Extensibility & Troubleshooting
Source: https://github.com/SciPhi-AI/R2R / Human Manual
Deployment, Configuration, Extensibility & Troubleshooting
Related topics: Introduction, Installation & SDK Usage, Ingestion Modes, Parsers, Search & Agentic RAG
Sources: [py/core/main/api/v3/documents_router.py](https://github.com/SciPhi-AI/R2R/blob/main/py/core/main/api/v3/documents_router.py) and [py/core/main/api/v3/retrieval_router.py](https://github.com/SciPhi-AI/R2R/blob/main/py/core/main/api/v3/retrieval_router.py).
Doramagic Pitfall Log
Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.
Source: Doramagic discovery, validation, and Project Pack records
06
AI Context Pack and portable assets
After deciding to continue, take the project context into your own AI host.Complete pack plus user-owned assets
These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.
07
Preflight checks
Treat this page as a planning asset, not proof that your local environment is ready.- The manual is generated from source-linked project files and Doramagic validation signals.
- Community evidence warnings stay visible instead of being converted into marketing claims.
- This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
- Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.
08
Pitfall Log and verification risks
Doramagic surfaces high-risk items before users treat a candidate capability as verified.Installation risk requires verification
May increase setup, validation, or first-run risk for the user.
Security or permission risk requires verification
May increase setup, validation, or first-run risk for the user.
Security or permission risk requires verification
May increase setup, validation, or first-run risk for the user.
Installation risk requires verification
May increase setup, validation, or first-run risk for the user.
Configuration risk requires verification
May increase setup, validation, or first-run risk for the user.
Configuration risk requires verification
May increase setup, validation, or first-run risk for the user.
Capability evidence risk requires verification
May increase setup, validation, or first-run risk for the user.
Maintenance risk requires verification
May increase setup, validation, or first-run risk for the user.