AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ15

VerifiedImplement information extraction solutions

You have a Microsoft Foundry project that contains an agent.

The agent ingests scanned PDF vendor invoices that contain tables and embedded QR codes. The agent must preserve the PDF layout in the extracted output so that downstream processing can reference sections and tables.

You plan to call Azure Content Understanding in Foundry Tools.

You need to extract the content and layout elements and detect the QR codes, without requiring a language model deployment.

Which built-in analyzer should you use?

Explanation

The prebuilt-layout analyzer extracts content and layout elements — words, paragraphs, tables, and section structure — while preserving document layout, and it also detects and decodes barcodes, including QR codes, as part of its output; it runs as a layout/OCR-based analyzer and does not require deploying a language model. prebuilt-read performs OCR text extraction only, without table or layout structure, and prebuilt-documentFieldSchema and prebuilt-documentSearch are not the layout-and-barcode extraction analyzer.

Learn more

Community Discussion

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