Azure Risk and Safety Evaluators on Arize Datasets+Experiments

This notebook demonstrates how to leverage Azure Risk and Safety Evaluators with Arize Datasets+Experiments to track and visualize experiments and evaluations in the Arize.

We will use the Hate Unfairness Evaluator to evaluate the output an Azure AI Foundry agent.

Prerequisites:

1. Arize AX account (Sign up for free)
2. Azure AI foundry account and project created (Sign up here)

Azure Evaluators: https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/evaluation-evaluators/risk-safety-evaluators

1. Setup and Installation

Now that we know how Azure evalators work, let's incorporate them into Arize datasets + experiments

2. Create a sample dataset + upload to Arize

3. Create an Azure AI Foundry agent for our task

4. Define Task

5. Define Evaluators

5. Run Experiments and log results to Arize

6. View experiments in Arize