# July 25: Support for Mistral Large 2 & Nemo, Groq Llama 3.1 models, bug fixes

### New Features

* :bulb: Graphlit now supports the Mistral Large 2 and Mistral Nemo models. The existing `MISTRAL_LARGE` model enum now will use Mistral Large 2.
* :bulb: Graphlit now supports the Llama 3.1 8b, 70b and 405b models on Groq.  (Note, these are rate-limited according to Groq's platform constraints.)
* Added support for revision strategy on data extraction specifications.  Now you can prompt the LLM to revise its previous data extraction response, similar to the existing completion revision strategy.
* Added `version` property for `AzureDocumentPreparationProperties` type for assigning the [API version](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/overview?view=doc-intel-4.0.0) used by Azure AI Document Intelligence.   By default, Graphlit will continue to use the v4.0 (Preview) API version, but you can override this to assign `version` to `V2023_10_31` to use the v3.1 (GA) API version instead.  For some documents, the General Availability (GA) version of the API can provide better results.

### Bugs Fixed

* GPLA-2988: Not extracting hyperlinks from Office documents.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://changelog.graphlit.dev/july-2024/july-25-support-for-mistral-large-2-and-nemo-groq-llama-3.1-models-bug-fixes.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.