Localhosted language model (like llama.cpp)

[anzestrela]

I don't like that you have to pay openai and send them the data to use the new AI smart picker tools.

I think it'd be great if we could use localhosted models like llama.cpp.

[marcelklehr]

Also note that integration_openai can now also connect to a LocalAI instance which allows you to selfhost stuff