---
title: "Deploy Ragflow v0.26.4 (Last Version)"
description: "ragflow stack lowest consumption with Infinity, 100% work, RAGFlow rag"
category: "AI/ML"
url: https://railway.com/deploy/ragflow-with-infinity-working
---

# Deploy Ragflow v0.26.4 (Last Version)

ragflow stack lowest consumption with Infinity, 100% work, RAGFlow rag

**[Deploy Ragflow v0.26.4 (Last Version) on Railway](https://railway.com/template/ragflow-with-infinity-working)**

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

- **Creator:** Xav's Projects
- **Category:** AI/ML
- **Total deploys:** 8

## Template content

### minio https://res.cloudinary.com/h5kvzw/image/upload/v1706062979/MINIO_Bird_vbtpet.png

- **Image:** minio/minio
- **Start command:** `sh -c "minio server /data --console-address :9001 & sleep 5 && mc alias set local http://127.0.0.1:9000 $MINIO_ROOT_USER $MINIO_ROOT_PASSWORD && mc mb -p local/ragflow || true; wait"`
- **Public domain:** Yes

### MySQL https://devicons.railway.app/i/mysql.svg

- **Image:** mysql:9.4
- **Start command:** `docker-entrypoint.sh mysqld --innodb-use-native-aio=0 --disable-log-bin --performance_schema=0 --innodb-buffer-pool-size=1G`

### Redis https://cdn.sanity.io/images/sy1jschh/production/0ce0bfdcfbdbf69662b1116671f97c2dd788b655-157x157.svg

- **Image:** redis:8.2.1
- **Start command:** `/bin/sh -c "rm -rf $RAILWAY_VOLUME_MOUNT_PATH/lost+found/ && exec docker-entrypoint.sh redis-server --requirepass $REDIS_PASSWORD --save 60 1 --dir $RAILWAY_VOLUME_MOUNT_PATH"`

### ragflow https://ragflow.io/img/logo.svg

- **Source:** XavTo/Ragflow
- **Public domain:** Yes

### infinity https://infiniflow.org/img/favicon.ico

- **Image:** infiniflow/infinity:v0.7.0

## Documentation

# Deploy and Host Ragflow with infinity --- Working ✅ on Railway

RAGFlow with Infinity is a production-ready Retrieval-Augmented
Generation (RAG) stack combining document ingestion, vector search, and
AI-powered chat. It integrates Infinity as a vector database, MinIO for
object storage, and MySQL/Redis for persistence and caching.

## About Hosting Ragflow with infinity --- Working ✅

This template deploys a complete multi-service RAG architecture on
Railway. RAGFlow handles ingestion, chunking, embedding, and querying.
Infinity stores vectors for semantic search, MinIO stores files, MySQL
handles metadata, and Redis manages caching and queues.

All services are preconfigured to work together using internal Railway
networking. The setup is optimized for CPU deployments and includes
automatic MinIO bucket creation, secure credentials, and ready-to-use
environment variables. Once deployed, you can upload documents and
instantly query them via chat.

## Service Versions

-   ragflow: infiniflow/ragflow:v0.23.1
-   infinity: infiniflow/infinity:v0.6.15
-   redis: redis:8.2.1
-   mysql: mysql:9.4
-   minio: minio/minio:latest

## Common Use Cases

-   Internal AI knowledge base over documents
-   Chatbot with semantic document search
-   Enterprise search across PDFs, text, and data

## Dependencies for Ragflow with infinity --- Working ✅ Hosting

-   Python (included in container)
-   Infinity vector database
-   Object storage (MinIO)
-   SQL database (MySQL)
-   Cache/queue system (Redis)

### Deployment Dependencies

-   RAGFlow: https://github.com/infiniflow/ragflow
-   Infinity: https://github.com/infiniflow/infinity
-   MinIO: https://min.io
-   Railway: https://railway.app

### Implementation Details

Environment variables (essential):

``` bash
# Core
REGISTER_ENABLED=1 # Set to 1 to enable registration, 0 to disable
TZ="UTC" # Timezone
DEVICE="cpu" # Compute device
DOC_ENGINE="infinity" # Vector engine

# Infinity
INFINITY_HOST="${{infinity.RAILWAY_PRIVATE_DOMAIN}}" # Internal host
INFINITY_PORT="${{infinity.INFINITY_PORT}}" # API port

# MinIO
MINIO_HOST="${{minio.RAILWAY_PRIVATE_DOMAIN}}" # Storage host
MINIO_PORT="9000" # Storage port
MINIO_USER="${{minio.MINIO_ROOT_USER}}" # Access key
MINIO_PASSWORD="${{minio.MINIO_ROOT_PASSWORD}}" # Secret key
MINIO_BUCKET="ragflow" # Bucket name
MINIO_SECURE="false" # Disable HTTPS internally

# MySQL
MYSQL_HOST="${{MySQL.MYSQLHOST}}" # DB host
MYSQL_PORT="${{MySQL.MYSQLPORT}}" # DB port
MYSQL_USER="${{MySQL.MYSQLUSER}}" # DB user
MYSQL_PASSWORD="${{MySQL.MYSQL_ROOT_PASSWORD}}" # DB password
MYSQL_DBNAME="${{MySQL.MYSQLDATABASE}}" # DB name

# Redis
REDIS_HOST="${{Redis.RAILWAY_PRIVATE_DOMAIN}}" # Cache host
REDIS_PORT="${{Redis.REDISPORT}}" # Cache port
REDIS_USERNAME="${{Redis.REDISUSER}}" # Cache user
REDIS_PASSWORD="${{Redis.REDISPASSWORD}}" # Cache password

# App
SECRET_KEY="${{ secret(32) }}" # App secret
API_PROXY_SCHEME="python" # API mode
```

## Why Deploy Ragflow with infinity --- Working ✅ 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 with infinity --- Working ✅ 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/ragflow-with-infinity-working