feat: Adding 2 Mistral models to complete existing list

[didier-durand]

Description

Adding 2 models missing in Mistral AI list: I need those models for a run module in OWL project.

See list below

Checklist

Go over all the following points, and put an x in all the boxes that apply.

• [X ] I have read the CONTRIBUTION guide (required)
• [ ] I have linked this PR to an issue using the Development section on the right sidebar or by adding Fixes #issue-number in the PR description (required)
• [X ] I have checked if any dependencies need to be added or updated in pyproject.toml and uv lock
• [ ] I have updated the tests accordingly (required for a bug fix or a new feature)
• [ ] I have updated the documentation if needed:
• [ ] I have added examples if this is a new feature

If you are unsure about any of these, don't hesitate to ask. We are here to help!

[didier-durand]

Hi, I already fixed is_mistral function and key_modules/models.md (line 17). See additional commits.

[didier-durand]

@Wendong-Fan :

the features (tokens, etc.) of pixtral-large-latest are already properly defined as part of litellm package in .venv/lib/python3.12/site-packages/litellm/model_prices_and_context_window_backup.json. They match the values defined at https://llm-stats.com/models/pixtral-large

So, it that ok for this model ? Otherwise, let me know precisely in which other file they should be duplicated.

Re. Mistral OCR model, Mistral doesn't detail its features (tokens, etc.) as for other models. Shall we remove it from this PR until those features get public ?

[Wendong-Fan]

@Wendong-Fan :

the features (tokens, etc.) of pixtral-large-latest are already properly defined as part of litellm package in .venv/lib/python3.12/site-packages/litellm/model_prices_and_context_window_backup.json. They match the values defined at https://llm-stats.com/models/pixtral-large

So, it that ok for this model ? Otherwise, let me know precisely in which other file they should be duplicated.

Re. Mistral OCR model, Mistral doesn't detail its features (tokens, etc.) as for other models. Shall we remove it from this PR until those features get public ?

hey @didier-durand , sorry for the late reply, for pixtral I think it's all good, but for ocr model I think it's not a general LLM, the interface to call this model is also different like below:

ocr_response = client.ocr.process(
    model="mistral-ocr-latest",
    document={
        "type": "document_url",
        "document_url": "https://arxiv.org/pdf/2201.04234"
    },
    include_image_base64=True
)

for this model maybe we can see it as loader could be put under camel/loaders instead of adding to model list, WDYT?

[JINO-ROHIT]

yeah i think mistral ocr is more of a pdf extractor/reader