AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ32

VerifiedImplement information extraction solutions

You have a Microsoft Foundry project named Project1 that contains an application for processing PDF vendor invoices.

You need to configure Azure Document Intelligence in Foundry Tools to produce Markdown output that preserves the sections and table structure of the PDFs. The solution must minimize development effort.

What should you do?

Explanation

The Document Intelligence analyze-document call accepts an output_content_format parameter; setting it to ContentFormat.MARKDOWN (outputContentFormat=markdown at the REST level) instructs the prebuilt-layout model to return the extracted content as GitHub-Flavored Markdown that preserves headings/sections and table structure. This requires only a single parameter change with no custom post-processing. "output=figures" and "content=markdown" are not valid SDK/API parameter names, and raising the confidence threshold has no bearing on the output format.

Learn more

Community Discussion

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