Adding MistralAI mode

[itsliamdowd]

Description

Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.

I added a Mistral mode where users can interact with Mistral's API for chat completion and generating embeddings. This mode requires the llama-index-embeddings-mistralai package in llama index to work properly and uses the already installed llama-index-llms-openai-like package for the llm to work.

Type of Change

Please delete options that are not relevant.

• New feature (non-breaking change which adds functionality)
• This change requires a documentation update

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

• I stared at the code and made sure it makes sense

Test Configuration:

• Firmware version:
• Hardware:
• Toolchain:
• SDK:

Checklist:

• My code follows the style guidelines of this project
• I have performed a self-review of my code

[jaluma]

Thank you for your contribution, it is very helpful. Please review the comments below :)

[itsliamdowd]

Thanks for the corrections - I removed the Mistral LLM case but this results in settings being pulled from the OpenAI settings page instead of the Mistral settings page. Should I eliminate the Mistral settings page altogether?

[jaluma]

Thanks for the corrections - I removed the Mistral LLM case but this results in settings being pulled from the OpenAI settings page instead of the Mistral settings page. Should I eliminate the Mistral settings page altogether?

I would say yes. With settings-mistralai.yaml, it's all that you need to load load the model, right? Reviewing again the PR, I realised that the documentation update would be missing :)

[itsliamdowd]

Yes it would need api_base, api_key, model, embedding_model, prompt_style, and request_timeout. I removed the settings-mistral.yaml because all of these can be included in the OpenAI like settings with a documentation update.

[jaluma]

Sorry for delay @itsliamdowd.
LGTM. Thank you.
Can you merge main and execute poetry lock --no-update?