---
title: "Deploy RAGFlow"
description: "RAGFlow v1.0.0 RAG engine: Elasticsearch, MinIO, MySQL, all on volumes"
category: "AI/ML"
url: https://railway.com/deploy/ragflow-2
---

# Deploy RAGFlow

RAGFlow v1.0.0 RAG engine: Elasticsearch, MinIO, MySQL, all on volumes

**[Deploy RAGFlow on Railway](https://railway.com/template/ragflow-2)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/ragflow-2/manifest.json

- **Creator:** Agaz Self-Host
- **Category:** AI/ML

## Template content

### NATS https://cdn.jsdelivr.net/gh/cncf/artwork@main/projects/nats/icon/color/nats-icon-color.png

- **Source:** https://github.com/aalfath/ragflow-railway-template
- **Health check:** /healthz

### Elasticsearch https://cdn.jsdelivr.net/gh/homarr-labs/dashboard-icons/png/elasticsearch.png

- **Source:** https://github.com/aalfath/ragflow-railway-template
- **Health check:** /_cluster/health

### MinIO https://cdn.jsdelivr.net/gh/homarr-labs/dashboard-icons/png/minio.png

- **Source:** https://github.com/aalfath/ragflow-railway-template
- **Health check:** /minio/health/live

### MySQL https://cdn.jsdelivr.net/gh/homarr-labs/dashboard-icons/png/mysql.png

- **Source:** https://github.com/aalfath/ragflow-railway-template

### Kvrocks https://kvrocks.apache.org/img/logo.svg

- **Source:** https://github.com/aalfath/ragflow-railway-template

### RAGFlow https://raw.githubusercontent.com/infiniflow/ragflow/v1.0.0/web/public/logo.svg

- **Source:** https://github.com/aalfath/ragflow-railway-template
- **Health check:** /api/v1/system/healthz
- **Public domain:** Yes

## Documentation

# Deploy and Host RAGFlow on Railway

RAGFlow is an open-source retrieval-augmented generation (RAG) engine by InfiniFlow. It parses PDFs, Word and Excel files, slides, scans and web pages into searchable chunks, then answers questions over them with citations. You build chat assistants, search apps and agent workflows on top of your own documents, with the LLM provider you choose.

## About Hosting RAGFlow

RAGFlow v1.0.0 is a stack of six parts: the RAGFlow server (web UI, API, admin console and ingestion worker), Elasticsearch for full-text and vector search, MinIO for uploaded files, MySQL for metadata, Kvrocks for cache and run state, and NATS JetStream for the parsing queue. This template deploys all six, wired over Railway's private network, with every image pinned to a version and digest and every stateful service on its own volume. All passwords are generated per deployment, self-registration is off, and only the RAGFlow web service is public. Plan for about 3 GB of memory at rest; parsing large PDFs is CPU-heavy.

## Common Use Cases

* Chat with your company's documents, contracts, manuals or papers, with answers that cite the source passages
* Build a private knowledge base and search app over PDFs, spreadsheets and scanned files
* Create agent workflows that retrieve from your datasets and call an LLM of your choice (OpenAI, Anthropic, Gemini, Ollama and more)

## Dependencies for RAGFlow Hosting

* An API key for an LLM and an embedding model provider (added in RAGFlow's UI after deploy, not in Railway)
* About 3 GB of memory for the whole stack at rest

### Deployment Dependencies

* RAGFlow v1.0.0 release: https://github.com/infiniflow/ragflow/releases/tag/v1.0.0
* RAGFlow docs: https://ragflow.io/docs/
* Template repo (Dockerfiles, changelog): https://github.com/aalfath/ragflow-railway-template

### Implementation Details

What you get: RAGFlow (public, port 80), Elasticsearch 8.11.3, MinIO (pgsty/silo), MySQL 8.4, Kvrocks 2.16 and NATS 2.14, each built from a folder of the template repo. Volumes hold Elasticsearch indexes, uploaded files, the MySQL database, Kvrocks data and the NATS queue, so a redeploy or restart keeps everything.

After deploy:

1. Open your RAGFlow URL and add `/admin`. Sign in as `admin@ragflow.io` with the value of `DEFAULT_SUPERUSER_PASSWORD` from the RAGFlow service's Variables tab. This account is for the admin console only.
2. Under User management, create your own account and one for each teammate. Self-registration is off; set `ENABLE_REGISTER=1` on the RAGFlow service to open it.
3. Sign in at your RAGFlow URL with your new account, add a model provider under Model providers, then create a dataset, upload documents and parse them.

Updates: the services build from the public repo `aalfath/ragflow-railway-template`. When a new RAGFlow version is tested there, Railway shows you an "update available" notice. Read `CHANGELOG.md` in the repo first, and back up the MySQL and MinIO volumes before a major upgrade.

Not included: GPU mode and the local embedding server (Railway has no GPUs), and the agent code sandbox, which needs the Docker socket.

## Why Deploy RAGFlow 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 RAGFlow 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.
- [Weaviate](https://railway.com/deploy/weaviate-1) — Vector database with hybrid search and an API key-protected API
- [Möbius Personal AI OS](https://railway.com/deploy/mobius-v01-personal-ai-os) — Self-hosted AI agent that builds and runs apps for you, with memory.

Open this page in a browser: https://railway.com/deploy/ragflow-2
