RAGFlow
RAG engine with deep document parsing (OCR, layout and tables) and cited answers.
Quick answer
RAGFlow is a RAG engine with deep document parsing (OCR, layout and tables) and cited answers, listed under Knowledge base & RAG. A typical small-business use: q&A over scanned contracts, invoices or technical drawings with tables. Official hardware: recommended 4 vCPU · 16 GB RAM · 50 GB disk (no separate minimum published). That fits a Hetzner Cloud CPX42 server at about €69.99/month (server only, excl. VAT). License: Apache-2.0, which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 22, 2026.
What is RAGFlow?
RAGFlow focuses on getting messy documents such as scanned PDFs and complex tables into a searchable knowledge base, then answering questions with citations. It includes agent and workflow features and runs as a multi-container Docker stack.
Where it fits in a 10–200 person business
- Q&A over scanned contracts, invoices or technical drawings with tables
- Research assistant for long reports where answers must show their source
- Knowledge back-end for other chat front-ends via its API
These use cases are our editorial suggestions, not claims made by the project.
Can a business use RAGFlow? (license)
| License | Apache-2.0 |
|---|---|
| Type | Permissive: MIT / Apache-2.0: use, modify and sell with few obligations. |
| Internal business use | Allowed under the license text |
| What to watch | Permissive. Internal and commercial use allowed; keep license and notices. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
What hardware does RAGFlow need?
| Minimum | Not published |
|---|---|
| Recommended | 4 vCPU · 16 GB RAM · 50 GB disk |
Recommended starting configuration. Actual needs depend on the document engine, data volume, parsing tasks and concurrency. Docker 24.0.0+ and Docker Compose v2.26.1+.
How much does it cost to host RAGFlow per month?
| Recommended spec | 4 vCPU · 16 GB RAM · 50 GB disk → CPX42 (8 vCPU, 16 GB, 320 GB disk) €69.99/mo |
|---|
How we got this: we took the cheapest Hetzner Cloud Regular Performance (shared AMD vCPU) plan with at least the RAM and vCPU the project lists, using prices read from www.hetzner.com/cloud/regular-performance on 2026-10-22. "From" monthly price cap shown by Hetzner, excluding VAT. Prices vary by location. Covers the server only; it excludes LLM API usage, backups, extra storage, GPUs and your time. Disk is not matched; add a volume if you need more than the plan includes.
How to deploy RAGFlow
Method: Docker Compose
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/docker
git checkout <latest-release-tag>
docker compose -f docker-compose.yml up -dFrom the official instructions: github.com/infiniflow/ragflow#-get-started. Always check the source for the current version before you run it.
Known gotchas when self-hosting RAGFlow
- When using Elasticsearch, set vm.max_map_count to at least 262144 on the Docker host (sudo sysctl -w vm.max_map_count=262144) and persist it in /etc/sysctl.conf. source
- In the 1.0 open-source release, DeepDoc layout analysis, OCR and table recognition run on CPU, so parsing large batches is CPU-heavy. source
Alternatives in Knowledge base & RAG
- AnythingLLM All-in-one private chat with your documents, agents and an embeddable widget. Compare AnythingLLM vs RAGFlow
- PrivateGPT API-first private document Q&A that sits on top of your own LLM server. Compare PrivateGPT vs RAGFlow
- Onyx (formerly Danswer) AI chat and enterprise search connected to 50+ workplace apps. Compare Onyx (formerly Danswer) vs RAGFlow
- FastGPT Knowledge-base Q&A and visual AI workflow platform. Compare FastGPT vs RAGFlow
- MaxKB Enterprise knowledge-base and agent platform with RAG and workflows. Compare MaxKB vs RAGFlow
RAGFlow FAQ
How much RAM does RAGFlow need?
The recommended spec is 4 vCPU · 16 GB RAM · 50 GB disk. Recommended starting configuration. Actual needs depend on the document engine, data volume, parsing tasks and concurrency. Docker 24.0.0+ and Docker Compose v2.26.1+.
How much does it cost to self-host RAGFlow?
The software is free to download. Based on the official recommended 4 vCPU · 16 GB RAM · 50 GB disk (no separate minimum published): That fits a Hetzner Cloud CPX42 server at about €69.99/month (server only, excl. VAT). That covers the server only, not LLM API usage, backups, extra storage or your time.
Is RAGFlow free for commercial use?
RAGFlow is licensed under Apache-2.0 (Permissive). Internal business use is allowed under the license text. Permissive. Internal and commercial use allowed; keep license and notices. This is a summary, not legal advice.
What are common problems when self-hosting RAGFlow?
When using Elasticsearch, set vm.max_map_count to at least 262144 on the Docker host (sudo sysctl -w vm.max_map_count=262144) and persist it in /etc/sysctl.conf. In the 1.0 open-source release, DeepDoc layout analysis, OCR and table recognition run on CPU, so parsing large batches is CPU-heavy.
Is RAGFlow still maintained?
Yes, it is actively developed. Last commit: Oct 22, 2026. Latest release: v1.0.0-rc2 (Oct 16, 2026). Checked Oct 22, 2026.
How do I install RAGFlow?
The official method is Docker Compose. The exact commands are in the "How to deploy" section above and in the official instructions: https://github.com/infiniflow/ragflow#-get-started
What are self-hosted alternatives to RAGFlow?
Other apps in Knowledge base & RAG: AnythingLLM, PrivateGPT, Onyx (formerly Danswer), FastGPT, MaxKB.
Sources
- GitHub repository: github.com/infiniflow/ragflow
- Official documentation, Hardware requirements, Deploy instructions, Gotcha 1, Gotcha 2: github.com/infiniflow/ragflow#-get-started
- License text: github.com/infiniflow/ragflow/blob/main/LICENSE
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-22. Spotted something out of date? Tell us.