AI-103: Developing AI Apps and Agents on AzureDemo

By Microsoft · Question Mode

QuestionQ34

Plan and manage an Azure AI solution

You are building a web app named App1 that generates responses by using a model deployed to a Microsoft Foundry project named Project1.

Before sending prompts to the model, App1 must retrieve documents by using Azure AI Search.

You need to integrate Project1 and App1. The solution must meet the following requirements:

  • Multiple client applications must use the same search configuration.
  • A security policy must prevent key-based authentication.
  • Administrative effort must be minimized.

What should you do?

  • A Create a custom HTTP connection in Foundry and manually configure Azure AI Search endpoints per application.
  • B Configure an Azure AI Search connection in Project1 and reference the connection in each application.
  • C Call Azure AI Search directly from each application by using Microsoft Entra authentication.
  • D Enable a managed identity for each application and call Azure AI Search directly.
Explanation

Defining a single Azure AI Search connection at the Project1 level lets every client application reference the same centrally managed search configuration instead of duplicating endpoint and index settings per app. Microsoft Foundry project connections support Microsoft Entra ID (token-based, keyless) authentication, so no API keys need to be issued or rotated, satisfying the shared-configuration, no-key-based-auth, and low-administrative-overhead requirements at once. Building a custom per-app HTTP connection, or having each application call Azure AI Search directly (with or without its own managed identity), duplicates configuration across apps and increases ongoing administrative effort.

Learn more

Community Discussion

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