Question

A logistics company wants to build a lightweight information-extraction app using Azure Content Understanding in Foundry Tools to pull specific fields (shipment ID, destination, weight) from thousands of scanned bill-of-lading documents. Before the app can process any documents, what must the team do first in the Content Understanding workflow?

Accepted Answer

Create an analyzer that defines a schema specifying the named fields to extract

Answer

Train a custom neural voice to read the extracted values aloud

Answer

Deploy a text-to-image generative model to visualize the shipments

Answer

Configure a top-p sampling value to control extraction randomness