Add Mistral API analogous to OpenAI API

[pchalasani]

https://github.com/mistralai/client-python

[rachittshah]

Hey @pchalasani I'd love to take this up.

I'll refer the TGI endpoint implementation by huggingface to build this TGI endpoint details

[pchalasani]

@rachittshah If I understood the TGI post correctly, we would simply set api_base to be access models on TGI. We already have this in langroid, i.e. you can set OpenAIGPTConfig.chat_model = "local/localhost:5000/v1") and under the hood the api_base and api_key are set to the appropriate values.

What I had in mind with this issue is directly using the Mistral python API client to access models on their servers. Provided their API is OpenAI-compatible (which I'm not sure yet, as they don't seem to mention OpenAI anywhere in their API docs), this would be very simple, i.e. adding a couple of model name enums in langroid/language_models/openai_gpt.py and switching to their chat/completion endpoint based on the chat_model setting (just like we currently switch between litellm and openai completion calls).

[rachittshah]

@pchalasani understood, and it makes sense to have a switch between litellm and openai call.

I'm new to Langdrioid, but I'd love to pick this up!

[pchalasani]

@rachittshah sure go ahead , thanks. I can elaborate a bit more what I had in mind later when I have time.