Others have said that RAG is only good up to a few 100s of files, eh? And since this is based on IndexLlama which is RAG-based, this would have the same limitation, eh?

I've tried LocalGPT, PrivateGPT, and H2OGPT. Have you been satisfied with the responses you get from PrivateGPT? When I tried it, it seemed very shallow/cursory in its responses. I saw much more detailed and complete responses when trying H2OGPT.

The models released over the last two weeks are much much better than the defaults. Try changing settings.yaml to use https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGU... .