> ## Documentation Index
> Fetch the complete documentation index at: https://arize-ax.mintlify.site/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# January 2024

> New Releases, Enhancements, + Changes

## What's New

January 18, 2024

#### Native Multi-Class Classification Support

We now support multi-class classification models natively, up to 100 classes. Learn more [here](/docs/ax/machine-learning/machine-learning/use-cases-ml/multiclass-classification).

<Frame caption="">
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/931a18b9-image.jpeg" />
</Frame>

#### Granularity Selector

January 4, 2024

Analyze performance by hour, day, week or month using the new granularity selector. Options default to the optimal granularity for a given time range. The granularity selector is available on the monitors page, all the relevant model pages, and the dashboards page.

<Frame caption="">
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/748f5fad-image.jpeg" />
</Frame>

#### Slice Performance Over Time for Tracing

Users can now view the performance of individual feature slices over time. In the performance tracing tab, select a feature and click "Slice Performance Over Time". This will plot the performance of the top five slices of that feature. Correlate performance issues with individual slices, further debug your features, or better understand trends over time.

<Frame caption="">
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/43cd41a1-image.jpeg" />
</Frame>

#### Google Gemini Support

Users can now utilize Google's new Gemini model via the Vertex AI integration in Arize's [Prompt Playground](/docs/ax/concepts/prompts/overview).

<Frame caption="">
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/f2752124-image.jpeg" />
</Frame>

#### Phoenix Demo Page

Check out LLM Tracing via Phoenix's UI via [https://phoenix-demo.arize.com/tracing](https://phoenix-demo.arize.com/tracing). For more info, [head over to Phoenix docs on tracing your LLM application](https://arize.com/docs/phoenix/quickstart/llm-traces).

## Enhancements

January 18, 2024

#### Dashboard -> Performance Tracing Connectivity

Users can now navigate from a dashboard widget to Performance Tracing for debugging workflows by clicking a point and selecting an option.

<Frame caption="">
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/c5aeb1ad-image.jpeg" />
</Frame>

#### Model Overview Refresh

The non-generative model overview page has undergone a couple of changes to increase ease of use:

* Quick Actions cards linking to various in app workflows

* Model Schema is now included on the left side navigation

<Frame caption="">
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/062b50ed-image.jpeg" />
</Frame>

#### Generative LLM Overview Refresh

January 4, 2024

The generative LLM model overview page has undergone a couple of changes to increase ease of use:

* Quick Actions cards linking to various in app workflows

* Model Schema is now included on the left side navigation

<Frame caption="">
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/f64b571a-image.jpeg" />
</Frame>

#### Python SDK v7.9.0

This release brings to life a new model type: multi-class. Users can now log not only the classes by their classification models, but also the non-selected ones, giving a detailed view of how the model operates. Currently, only the record-at-a-time logging option is supported, but stay tuned for the release of pandas batch ingestion.

#### Python SDK v7.8.0

This release enables latent actuals for generative LLM models. In addition, users will now be alerted when their data files are too large.

### 📚 New Content

* [AI Conferences 2024](https://arize.com/blog/ai-conferences-2024-generative/) - Top AI Events to look forward to this year

* [LLM Observability Checklist](https://arize.com/resource/llm-observability-checklist/) for your company

* [LLM evaluations](https://arize.com/blog-course/llm-evaluation-the-definitive-guide/): everything you need to know

* [OpenAI Function Calling](https://arize.com/blog/calling-all-functions-benchmarking-openai-function-calling-and-explanations/): Benchmarking, Explanations

* [Exec Snapshot: LLM Observability](https://arize.com/resource/exec-snapshot-llm-obs/)

* [Prompt Templates](https://arize.com/blog-course/evaluating-prompt-playground/?utm_campaign=Q423:%20Content\&utm_source=Content) & Evaluating Prompts

* [Text To SQL](https://arize.com/blog/how-to-prompt-llms-for-text-to-sql-paper-reading/) with AI: A Study in Zero-shot, Single-domain, and Cross-domain Settings

* [Mistral AI](https://arize.com/blog/mistral-ai): A Deep Dive Into the Latest Models