---
title: "Deploy Open WebUI (Private AI Chat + RAG)"
description: "Private ChatGPT alternative: multi-user auth, RAG, bring your own API keys."
category: "AI/ML"
url: https://railway.com/deploy/open-webui-private-ai-chat-rag
---

# Deploy Open WebUI (Private AI Chat + RAG)

Private ChatGPT alternative: multi-user auth, RAG, bring your own API keys.

**[Deploy Open WebUI (Private AI Chat + RAG) on Railway](https://railway.com/template/open-webui-private-ai-chat-rag)**

- **Creator:** Nick K's Projects
- **Category:** AI/ML
- **Total deploys:** 3

## Template content

### open-webui https://devicons.railway.com/i/open-webui.svg

- **Image:** ghcr.io/open-webui/open-webui:v0.10.2
- **Public domain:** Yes

## Documentation

# Deploy and Host Open WebUI (Private AI Chat + RAG) on Railway

Open WebUI is the most popular open-source AI chat interface — a private, self-hosted ChatGPT alternative with multi-user authentication, model management, and built-in RAG (chat with your documents). This template deploys the official image with secure defaults, persistent storage, and bring-your-own-API-key support for OpenAI, Anthropic, and any OpenAI-compatible endpoint.

## About Hosting Open WebUI (Private AI Chat + RAG)

Hosting Open WebUI means running the official `ghcr.io/open-webui/open-webui` container with a persistent volume for user accounts, chat history, and uploaded documents. This template pins a stable release (v0.10.2), mounts a volume at `/app/backend/data`, generates a strong `WEBUI_SECRET_KEY` automatically, disables all telemetry, and passes Railway's healthcheck at `/health`. The first account created becomes the admin; further signups are held in a pending state until approved, so your instance is never open to strangers. Connect any model provider by pasting an API key in Admin Settings — no redeploys needed.

## Common Use Cases

- Private team ChatGPT: one interface, many providers, per-user accounts and access control
- Chat with your documents (RAG): upload PDFs, docs, and notes and query them with citations
- Single pane for multiple LLMs: OpenAI, Anthropic, OpenRouter, Groq, or a remote Ollama — switch models per chat

## Dependencies for Open WebUI (Private AI Chat + RAG) Hosting

- An API key from at least one model provider (OpenAI, Anthropic via proxy, OpenRouter, Groq, etc.) or a reachable Ollama server
- Persistent volume (included) for accounts, chats, and RAG document storage

### Deployment Dependencies

- [Open WebUI documentation](https://docs.openwebui.com)
- [Open WebUI GitHub repository](https://github.com/open-webui/open-webui)
- [Environment variable reference](https://docs.openwebui.com/getting-started/env-configuration)

### Implementation Details

Security defaults shipped by this template:

```
WEBUI_SECRET_KEY   auto-generated 48-char secret (signs sessions/JWTs)
DEFAULT_USER_ROLE  pending — new signups need admin approval
ENABLE_SIGNUP      true (first user = admin)
JWT expiry         1 week
Telemetry          fully disabled
```

Add `OPENAI_API_KEY` (or set any provider in Admin → Settings → Connections) and start chatting. To use RAG, upload documents in a chat or the Documents workspace.

## Why Deploy Open WebUI (Private AI Chat + RAG) on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying Open WebUI (Private AI Chat + RAG) on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.

## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/open-webui-private-ai-chat-rag