RAGFlow
InfiniFlowRAG engine built around deep document understanding, with template-based chunking and layout-aware parsing of complex PDFs, tables, figures and scans, producing answers with visible citations. Unlike a general orchestration framework it is a batteries-included RAG server, deployed with Docker Compose, and has since been extended with agent capabilities.
A managed cloud is sold beside the published engine, and there is no first-party package beyond the SDK client. Verified 2026-08-13 via the infiniflow/ragflow repository.
Openness
5 high confidence- license
- Apache-2.0(OSI)
- source
- public
- self-host
- primary(Docker)
- commercial
- cloud/enterprise(separate)
- core-gated
- ungated
Apache-2.0 self-hostable engine; cloud is the commercial tier.
- https://github.com/infiniflow/ragflow recorded 2026-08-13
Apache-2.0 license, full engine source published for Docker Compose self-hosting, 87.9k stars and 10.3k forks; managed cloud sold beside the published engine
Adoption
3 medium confidenceAbout 129,133 downloads a month across the product's real distribution channels: Docker Hub reports 3,590,166 cumulative pulls since 2023-12-12, about 112,087 a month, and ragflow-sdk adds 17,046 in the trailing 30 days. Bands at level 3 (100K-1M). RAGFlow ships as a Docker Compose stack, and ragflow-sdk on PyPI is an API client rather than the server, so it measures a different thing and counts only as a minor component - banding on the registry package alone would have measured a channel the product does not ship through. The Docker component is a lifetime average rather than a trailing-30-day count, so this level is a floor.
- https://hub.docker.com/v2/repositories/infiniflow/ragflow/ recorded 2026-08-13
3,590,166 cumulative pulls of infiniflow/ragflow
- https://pypistats.org/api/packages/ragflow-sdk/recent recorded 2026-08-13
17,046 downloads in the trailing 30 days for ragflow-sdk
Capability
4 medium confidenceOpinionated, document-centric RAG application; deeper parsing than general frameworks, narrower scope.
- https://github.com/infiniflow/ragflow recorded 2026-08-13
README key features - deep document understanding based knowledge extraction from unstructured data with complicated formats, template chunking, grounded citations, hybrid retrieval; no benchmark figure
Verified 2026-08-13