[feat] running the server from rust

[louis030195]

i'm looking for some production ready LLM API that I can use from rust as a lib in https://github.com/louis030195/screen-pipe

would it be possible to provide some abstraction like

let api = mistral_rs::api::new("phi42").load()
api.serve()
// openai style api ... function calling available if possible

i also use axum

atm implementing the api myself with candle