AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ33

VerifiedImplement information extraction solutions

You have a Microsoft Foundry project that processes procurement documents submitted by suppliers. You need to implement two pipelines using Azure Content Understanding in Foundry Tools that meet the following requirements:

  • Pipeline1 must support cost-effective, high-volume processing of standalone PDF invoices.
  • Pipeline2 must support cross-document validation using multi-step reasoning and reference data.

How should you configure each pipeline? Each configuration can be used once, more than once, or not at all.

Drag & Drop
Pipeline1:
Pipeline2:
Explanation

Azure Content Understanding in Foundry Tools standard mode processes a single input document per task and is optimized for cost-effectiveness and low latency, making it the right fit for high-volume, standalone PDF invoice processing. Pro mode operates on multi-file tasks, supports supplying reference data at analyzer-creation time, and applies multi-step reasoning to validate and draw conclusions across documents (for example, checking whether an invoice matches a contract) - exactly the cross-document validation with reference data that the second pipeline requires.

Learn more

Community Discussion

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