Add remote model support #7
Description
Hello, cool project!
I'm running my LLM on a server using the Obabooga Web UI which exposes an OpenAI API to allow other services to make use of it. This allows me to use a comparably big LLM for every day tasks.
I think this project should absolutely keep the ability to run a (small?) local LLM, but I think it would greatly benefit from the ability to also use a remote LLM. As the OpenAI API seems to be the current de-facto standard, I suggest using it and documenting on how to set the URL to the custom host.
Additionally, with the configuration options to be increasing, it may be a good idea to store them in a configuration file instead.
Cheers!