Someone should just get this working on Llama 2 instead of O̶p̶e̶n̶AI.com [0]
All this is it's just talking to a AI model sitting on someone else's server.
[0] https://github.com/microsoft/TypeChat/blob/main/src/model.ts...
The most recent gpt4all
(https://github.com/nomic-ai/gpt4all)
includes a local server compatible with OpenAPI -- this could be a useful start!