AI-103: Developing AI Apps and Agents on AzureDemo

By Microsoft · Question Mode

QuestionQ59

Implement information extraction solutions

You have a Microsoft Foundry project that contains an agent.

You need to process mixed-format documents containing scanned text, tables, and multicolumn layouts. The extracted content must preserve the document's structure and be converted to Markdown format for downstream reasoning.

What should you configure first?

  • A an Azure Language in Foundry Tools text analysis model deployment
  • B a generative chat completion request
  • C an Azure OpenAI Responses API call that uses a multimodal model
  • D an Azure Content Understanding in Foundry Tools analyzer
Explanation

Azure Content Understanding in Foundry Tools is purpose-built to convert mixed-format documents — including scanned text, tables, and multicolumn layouts — into structured, layout-preserving Markdown output that downstream agents and reasoning models can consume. It is the recommended first step in a document-processing pipeline because it produces structure-aware output before any generative reasoning happens. An Azure Language text-analysis deployment performs text analytics (not structural extraction), a generic chat-completion request has no document-parsing capability of its own, and calling the Responses API with a multimodal model reasons over content but does not itself perform structure-preserving OCR and Markdown conversion.

Learn more

Community Discussion

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