feat: inference-mistral-extension

[freelerobot]

Problem
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

We ❤️ mistral

Success Criteria
A clear and concise description of what you want to happen.

• similar to openai remote api
• lets have a mistral remote api

Additional context
Add any other context or screenshots about the feature request here.

[hiro-v]

Mistral uses OpenAI compatible APIs for chat/completion and embedding.
We can support this with integration docs. Should not create another extension.

However, I think it's a good time that we think through and add remote api provider abstraction as users might need to configure multiple providers and switch between them.
As in my observation, almost all providers (already have openai compatible API or not), will add OpenAI compatible API support.

We can focus on OpenAI compatible API providers first:

• LMStudio, Nitro, Ollama
• OpenAI platform, Azure OpenAI, Mistral, Openrouter, Anyscale, Together.ai, Lepton.ai
• vLLM, etc

[louis-menlo]

Mistral uses OpenAI compatible APIs for chat/completion and embedding. We can support this with integration docs. Should not create another extension.

However, I think it's a good time that we think through and add remote api provider abstraction as users might need to configure multiple providers and switch between them. As in my observation, almost all providers (already have openai compatible API or not), will add OpenAI compatible API support.

We can focus on OpenAI compatible API providers first:

• LMStudio, Nitro, Ollama
• OpenAI platform, Azure OpenAI, Mistral, Openrouter, Anyscale, Together.ai, Lepton.ai
• vLLM, etc

Is this the one I mentioned earlier for you to refactor, @hiro-v? Would you like to take ownership of this issue?

[hiro-v]

I can after the leave, can work on this if it's not picked up on March 1st.
But I think @hieu-jan has been working on the documentation for the integration and trying to work in Jan App pod, it's a good issue to follow

[louis-menlo]

As a part of Inference Provider revamp epic

[Van-QA]

hi @Inchoker, the case of invalid API for Mistral extension, is throwing something amiss ❌

Expectation ✅ :
Similar to other extension, to highlight the invalid API key: Invalid API key. Please check your API key from Settings and try again.

see related PR: #2645

[Van-QA]

looking good on Jan v0.4.10-369 ✅