AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ115

VerifiedImplement information extraction solutions

You have an Azure AI Search indexer that ingests PDF policy manuals.

Client applications must display page-level citations that include bounding polygons for both text and images.

You need to add a single built-in multimodal content extraction skill to the Azure AI Search skillset. The solution must meet the following requirements:

  • Provide text and image location metadata.
  • Extract tables that span multiple pages.

What should you add?

Explanation

The Azure Content Understanding skill (Microsoft.Skills.Util.ContentUnderstandingSkill) extracts text and images and, when extractionOptions includes "images" and "locationMetadata", returns location metadata (page range and positional polygon data) for both text chunks and images, which supports page-level citations. It can also recognize tables that span multiple pages and extract each cross-page table as a single unit. The Document Layout skill also returns location metadata but outputs tables as plain text and does not offer cross-page table handling; Document Extraction provides no location metadata; GenAI Prompt is for generative enrichment, not structural extraction.

Learn more

Community Discussion

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