AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ80

VerifiedImplement information extraction solutions

You have a Microsoft Foundry project that contains an agent.

The agent uses Azure Content Understanding in Foundry Tools to process vendor onboarding packets. The packets include digital PDFs that contain tables and hyperlinks.

The extracted content is indexed for search and provided to a downstream agent in Markdown format.

You need to produce a Markdown output whose layout and semantic structure are optimized for Retrieval Augmented Generation (RAG) workflows.

Which built-in analyzer should you use?

Explanation

Azure Content Understanding provides a dedicated category of RAG analyzers that extract content with layout represented as markdown and apply semantic analysis to improve retrieval quality for downstream applications. Within this category, prebuilt-documentSearch extracts paragraphs, tables, and figures; generates detailed figure/chart/diagram descriptions; captures handwritten annotations; and produces a document summary, and it is the analyzer Microsoft explicitly recommends for document ingestion in RAG workflows. The other options do not meet this requirement: prebuilt-layout and prebuilt-read are content extraction analyzers focused on OCR and raw layout/structure extraction rather than RAG-optimized semantic markdown, and prebuilt-documentFieldSchema is a utility analyzer used to propose field schemas, not to generate RAG-ready markdown.

Learn more

Community Discussion

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