AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ140

VerifiedPlan and manage an Azure AI solution

You have a Microsoft Foundry resource named AI1 that hosts three GPT-3.5 deployments. Each deployment is optimized for a distinct workload.

You plan to deploy three apps. Each app will use the REST API to access AI1 and the deployment optimized for that app’s intended workload.

You must give each app access to AI1 and its appropriate deployment, while ensuring that only the apps can access AI1.

What should you use to provide access to AI1, and what should each app use to connect to its appropriate deployment?

Select
Provide access to AI1 by using:
Connect to the deployment by using:
Explanation

Microsoft Entra ID bearer-token authentication supports granting the required Azure role to each app identity, so only authorized apps can access the resource. Azure OpenAI/Microsoft Foundry REST inference requests identify the target model by deployment name; the resource endpoint is shared by the deployments.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!