A private, self hosted engine for chatting with your own documents, grounded in what they actually say.
RAGFlow is an open source, self hosted retrieval augmented generation engine built on deep document understanding. It gives you a full web workspace to build knowledge bases from your own files, parse and chunk them with layout aware models, and chat with answers that are grounded in and cited back to your content. It adds template based chunking, hybrid retrieval and an agent flow builder for multi step retrieval.
It suits teams who want accurate question answering over their own documents, running inside their own cloud account rather than sending private content to a public service.
The cloudimg image installs RAGFlow with its full stack already wired together: an Elasticsearch index for hybrid retrieval, a MySQL metadata store, MinIO object storage and a CPU embedding service, so document embedding can run on box with no external key. No administrator ships in the image: you create your own account at the first sign-up screen, and per instance datastore secrets are generated uniquely on first boot. The paired deployment guide covers first sign-up, connecting a language model provider and building your first knowledge base, and every deployment carries 24/7 support.
Real screenshots taken while testing this image against its deployment guide.