Has anyone got a local model working with the RAG API, or implemented their own custom model? My goal is to either have a completely local version of rag in docker, or use my own hosted RAG model somewhere.
#Has anyone got a local model working with the RAG API, or implemented their own custom model?
tepid cave
echo hemlock
Has anyone got a local model working with the RAG API, or implemented their own ...
Look in this thread for Rag working with local Ollama model (there was a bit of troubleshooting going on but I believe there’s enough info to get going)
#1236459793464557599 message