[throwaway675309]

What? It's only one file, and it definitely looks like it's using openAI to make the actual queries.

    qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0.1), db.as_retriever())

[sp332]

You can change the arguments to from_llm() to point to a local model instead. Example here: https://huggingface.co/TheBloke/MPT-7B-Instruct-GGML/discuss...