RAGFlow
RAG engine with deep document parsing (OCR, layout and tables) and cited answers.
Activity data comes from GitHub and was last refreshed Oct 22, 2026.
What it does
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.
License: can a business use it?
| 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.
Hardware requirements
| 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+.
Estimated monthly hosting cost
| 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
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 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
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.