1. Learning Objectives

GENAIOPS: Model Exploration is part of the Getting Started stage. (click to view figure)

In the previous lab exercises, we learned about model selection by:

• Visiting the Azure AI Foundry portal in guest mode.
• Using the model catalog to discover models that meet your needs
• Using the model benchmarks to compare relevant models by metrics
• Using the model card to understand costs, capabilities & code use.

We went from 1800 models to a single candidate. Now, we need to test this model out to see how well it "fits" our requuirements. To do this, we need to deploy the model and explore it interactively in a chat playground. Let's see how we can do this in Azure AI Foundry, next.

By the end of this section you should know how to:

• Deploy a model from an Azure AI model catalog card
• Create an Azure AI project with a customized hub for this purpose
• View model deployment details in the Azure AI project
• View project and hub resource details in the Management center
• Launch the chat playground for the deployed model (and use it)