Drag-and-drop LLM app and agent builder - no code required to wire up a RAG pipeline.
Flowise is a visual builder for LangChain-style chains and agents - instead of writing Python to wire a prompt to a model to a vector store, you drag nodes onto a canvas and connect them.
It's the same category as Langflow and Dify: aimed at people who want to build something like 'a chatbot that answers questions from our internal docs' without standing up a full development environment first.
Every flow you build can be exposed as its own API endpoint, so it plugs into an existing app or website once you're happy with it.
| Image | flowiseai/flowise:latest |
| Port | 3000 |
| Persistent volume | /root/.flowise |
No - that's the point of the visual builder. Familiarity with LangChain's concepts (chains, retrievers, agents) helps you use the nodes faster, but you don't write any of that code directly.
Yes - connect a document loader node to a vector store (Qdrant or Chroma, both one-click DeployOS templates) and a retrieval-augmented-generation flow is a few connected nodes, not a custom pipeline.
Free download, no account needed. AI templates are on paid plans.
Download DeployOS