RAGFlow on Railway

Retrieval-augmented generation engine with deep document parsing and cited answers, on Railway.

Official site · License: Apache-2.0 · 21 Railway templates

Deploy RAGFlow on RailwayCompare templates

RAGFlow is an open-source retrieval-augmented generation (RAG) engine built around deep document understanding. It parses PDFs, scans, tables and slides into structured chunks and answers questions with citations that point to the source passages.

Teams use it to chat with contracts, policies, manuals and research papers, to build knowledge bases over documents that plain text extractors handle poorly, and to expose a retrieval API or MCP endpoint for AI agents. It also has an agent workflow builder that combines retrieval with web search and tools.

RAGFlow is licensed Apache-2.0.

What RAGFlow can do

  • Deep document parsing with OCR and layout models
  • Chat with cited source passages
  • Knowledge bases over PDFs, scans, tables and slides
  • Retrieval API and MCP endpoint
  • Agent workflows with retrieval, web search and tools
  • Chat and embedding models configured in the UI

What people use it for

  • Chat with contracts, policies, manuals and papers
  • An internal knowledge base over scanned PDFs and tables
  • A retrieval API for AI agents
  • Agent workflows that mix retrieval and web search

Videos

RAGFlow: Free Open Source Generative AI Platform · Elestio
RagFlow: Ultimate RAG Engine - Semantic Search, Embeddings, Vector Search + Supports Graph! · WorldofAI
RAGFlow with Local LLMs and Ollama: Step-by-Step Guide for Free Retrieval-Augmented Generation · Aleksandar Haber PhD

Running RAGFlow on Railway

The Railway template deploys RAGFlow v0.27 as a web service and a separate parsing worker, with Elasticsearch 8.11.3, MySQL 9 and Redis 8.2 on volumes, and a Railway Bucket for uploaded files through RAGFlow's S3 backend instead of MinIO. Passwords and secrets are generated. It is a memory-heavy stack: the template's planning estimate is roughly 6 to 10 GB of RAM in total, an estimate and not a measurement. Parsing capacity scales with worker replicas.

RAGFlow templates on Railway

RAGFlow Document AI EngineMaintained by Tracklayer
Deploys RAGFlow v0.27, an open-source retrieval-augmented generation engine that parses PDFs, scans and tables into chunks and answers with citations. Includes a separate parsing w
4 deployments
Deploy
RAGFlow | Open Source RAG Engine by an independent creator
Self-host RAGFlow. Chat with your PDFs, contracts, papers & more
20 deployments
Deploy
RAGFlow by an independent creator
RAG with RAGFlow (RAG Flow): Infinity search, files and AI chat.
11 deployments
Deploy
RAGFlow by an independent creator
RAG engine with document parsing, citations, and agentic workflows
4 deployments
Deploy
RAGFlow by an independent creator
Deep-document RAG engine: chat with PDFs, docs and sheets, with citations
3 deployments
Deploy
RAGFlow CPU by an independent creator
Document ingestion and retrieval with private databases and CPU workers.
2 deployments
Deploy
RAGFlow by an independent creator
Turns your documents into a searchable, citable knowledge base
1 deployments
Deploy
RAGFlow Document RAG Stack by an independent creator
RAGFlow document RAG with Elasticsearch, MySQL, MinIO and Valkey
1 deployments
Deploy
Deploy RAGFlow Retrieval API by an independent creator
RAGFlow HTTP API for retrieval and chat
0 deployments
Deploy
RAGFlow by an independent creator
RAGFlow v1.0.0 RAG engine: Elasticsearch, MinIO, MySQL, all on volumes
0 deployments
Deploy
RAGFlow by an independent creator
Deep-document RAG with citations, v0.27.2 digest-pinned
0 deployments
Deploy
RAGFlow 1.0.0 by an independent creator
RAGFlow 1.0 GraphRAG engine: knowledge graph, deep document parsing, chat
0 deployments
Deploy
RAGFlow Agent by an independent creator
Build agentic RAG flows on the RAGFlow canvas
0 deployments
Deploy
RAGFlow Chat Widget by an independent creator
Embed a RAGFlow assistant on your website
0 deployments
Deploy
RAGFlow Gemini by an independent creator
Use Google Gemini chat and embedding models in RAGFlow
0 deployments
Deploy
RAGFlow GraphRAG by an independent creator
Knowledge graph extraction over your RAG datasets
0 deployments
Deploy
RAGFlow MCP by an independent creator
Expose RAGFlow datasets to AI clients over MCP
0 deployments
Deploy
RAGFlow Ollama by an independent creator
Point self-hosted RAGFlow at your own Ollama models
0 deployments
Deploy
RAGFlow PDF Parsing by an independent creator
Layout-aware PDF, table and scan parsing for RAG
0 deployments
Deploy
RAGFlow Python SDK by an independent creator
Script datasets, parsing and chat assistants with ragflow-sdk
0 deployments
Deploy
RAGFlow vs AnythingLLM by an independent creator
Team RAG engine compared with desktop-first AnythingLLM
0 deployments
Deploy

Tracklayer templates are listed first. Other RAGFlow templates follow, ordered by total deployments on Railway. How this works.

Deployment numbers as of 2026-11-20.

Questions about RAGFlow

How do I log in?

Wait for the ragflow healthcheck to pass, which can take several minutes on first start, open the public URL and register. Registration is open by default, so set REGISTER_ENABLED to 0 on the ragflow service afterwards.

Where do model keys go?

In the UI. Add your chat and embedding model providers, such as OpenAI, Azure, Gemini, Ollama or a LiteLLM gateway.

What drives the cost?

Memory: Elasticsearch, the parsing worker (each executor needs roughly 1.5 to 3 GB while parsing) and the web service. The template estimates 6 to 10 GB of RAM in total.

Is my data kept across redeploys?

Yes. Elasticsearch, MySQL and Redis use volumes, and original files are stored in the Railway Bucket.

Are there licence notes?

RAGFlow is Apache-2.0. Elasticsearch 8.11 is distributed under Elastic License 2.0 or SSPL, and running it unmodified as a backing service is permitted under ELv2. MySQL Community is GPL-2.0 and Redis 8 is RSALv2, SSPLv1 or AGPLv3.

Guides

Similar apps

Tracklayer maintains the templates marked as such; RAGFlow is a trademark of its owners and this site is not affiliated with them.