This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Simon Willison
simonwillison.net
did:plc:kft6lu4trxowqmter2b6vg6z
Anyone got a local LLM+RAG setup (for the popular "chat with your documents" / "chat with your data") that they find intuitive and useful?
I feel like local models - especially Llama 3.1 8B or Mistral Small 3 22B - should be capable for this more, what's the best software to run RAG with those?
2025-03-03T15:55:50.950Z