[syntaxing]

Has anyone done this with locally with LlamaIndex or LangChain? I saw a couple issue tickets trying it with LLaMa-30 and Alpaca but I haven’t been able to do it on a 3090. Any hints would be awesome

[35mm]

Yes, although I could only get it to work with Davinci and not any of the chat models. So it ended up being expensive in comparison.

What I was trying to do is give an answer that cited any relevant info in Pinecone, but refuse to answer if it couldn’t find a source.

That’s where I got stuck as it would often still make up an answer.