RAGFlow on Ubuntu 24.04 LTS by cloudimg
by cloudimg
RAG engine for AI teams: parse documents and serve grounded, citation-backed answers via LLMs.
RAGFlow is a popular 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 documents, parse and chunk them with layout aware models, and chat with answers that are grounded in and cited back to your content, plus an agent builder for multi step retrieval. This image is built and maintained by cloudimg on a hardened, fully patched Ubuntu 24.04 LTS base, running RAGFlow with Elasticsearch, MySQL, MinIO, Redis and a CPU embedding service so the appliance is complete on its own.
Security is built in. The image ships with no default login and no user rows: registration is open, so your first visit lands on the sign up screen and the first account you create becomes the administrator. The MySQL, MinIO, Redis and Elasticsearch passwords are generated uniquely on the first boot of every VM into a root only file, so no two instances share a datastore secret and nothing secret ships inside the image.
Every datastore binds to the internal container network or the loopback interface and is never exposed; only the web workspace on port 80 is reachable. A local CPU embedding service is included so document embedding can run on box with no external key. For chat and answer generation you add your own large language model provider, such as OpenAI, Anthropic or a local OpenAI compatible endpoint, from the interface after sign up. No third party AI key ships in the image, and the stack refreshes to the pinned release on first boot.
RAGFlow is free software licensed under the Apache License 2.0. This image is provided by cloudimg and is not affiliated with or endorsed by the RAGFlow project or its maintainers. Backed by 24/7 cloudimg support.