Merge pull request #53791 from ivorb/info-extract-new

Add consolidated doc intel module

Author: Stacyrch140

learn-pr/paths/insight-visual-data/index.yml

@@ -0,0 +1,46 @@
+### YamlMime:LearningPath
+uid: learn.extract-insights-visual-data-azure
+metadata:
+  title: Extract insights from visual data on Azure
+  description: Use generative AI vision and Content Understanding in Azure to extract insights from visual data.
+  ms.date: 03/11/2026
+  author: ivorb
+  ms.author: berryivor
+  ms.topic: learning-path
+title: Extract insights from visual data on Azure
+summary: |
+  Use generative AI, computer vision, and Content Understanding capabilities in Azure to extract insights from visual data, supporting scenarios like:
+  - Image and video generation
+  - Image and video analysis
+  - Content Understanding and enrichment
+  - Visual search and classification
+  - Digital asset management (DAM)
+  - Multimodal AI solutions
+prerequisites: |
+  Before starting this learning path, you should already have:
+  - Familiarity with Azure and Microsoft Foundry.
+  - Programming experience.
+iconUrl: /training/achievements/generic-badge.svg
+levels:
+- intermediate
+roles:
+- ai-engineer
+- developer
+subjects:
+- artificial-intelligence
+products:
+- foundry-tools
+- microsoft-foundry
+- azure-cognitive-search
+modules:
+- learn.wwl.generate-images-azure-openai
+- learn.wwl.generate-video-with-foundry
+- learn.wwl.analyze-images-with-content-understanding
+- learn.wwl.develop-generative-ai-vision-apps
+- learn.wwl.analyze-content-ai
+- learn.wwl.analyze-content-ai-api
+- learn.wwl.extract-data-with-document-intelligence
+- learn.wwl.ai-knowledge-mining
+trophy:
+  uid: learn.extract-insights-visual-data-azure.trophy
+

learn-pr/wwl-data-ai/extract-data-with-document-intelligence/1-introduction.yml

@@ -0,0 +1,14 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.extract-data-with-document-intelligence.introduction
+title: Introduction
+metadata:
+  title: Introduction
+  description: Introduction to extracting data with Azure Document Intelligence.
+  ms.date: 03/11/2026
+  author: ivorb
+  ms.author: berryivor
+  ms.topic: unit
+  ai-usage: ai-assisted
+durationInMinutes: 3
+content: |
+  [!include[](includes/1-introduction.md)]

learn-pr/wwl-data-ai/extract-data-with-document-intelligence/2-what-is-document-intelligence.yml

@@ -0,0 +1,14 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.extract-data-with-document-intelligence.what-is-document-intelligence
+title: What is Azure Document Intelligence?
+metadata:
+  title: What is Azure Document Intelligence?
+  description: Learn about the capabilities, components, and access options of Azure Document Intelligence.
+  ms.date: 03/11/2026
+  author: ivorb
+  ms.author: berryivor
+  ms.topic: unit
+  ai-usage: ai-assisted
+durationInMinutes: 8
+content: |
+  [!include[](includes/2-what-is-document-intelligence.md)]

learn-pr/wwl-data-ai/extract-data-with-document-intelligence/3-use-document-intelligence-studio.yml

@@ -0,0 +1,14 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.extract-data-with-document-intelligence.use-document-intelligence-studio
+title: Use the Document Intelligence Studio
+metadata:
+  title: Use the Document Intelligence Studio
+  description: Learn how to use the Document Intelligence Studio to analyze, test, and build document processing solutions.
+  ms.date: 03/11/2026
+  author: ivorb
+  ms.author: berryivor
+  ms.topic: unit
+  ai-usage: ai-assisted
+durationInMinutes: 6
+content: |
+  [!include[](includes/3-use-document-intelligence-studio.md)]

learn-pr/wwl-data-ai/extract-data-with-document-intelligence/4-use-prebuilt-models.yml

@@ -0,0 +1,14 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.extract-data-with-document-intelligence.use-prebuilt-models
+title: Use prebuilt models
+metadata:
+  title: Use prebuilt models
+  description: Learn about document analysis models and prebuilt models for extracting data from common document types.
+  ms.date: 03/11/2026
+  author: ivorb
+  ms.author: berryivor
+  ms.topic: unit
+  ai-usage: ai-assisted
+durationInMinutes: 10
+content: |
+  [!include[](includes/4-use-prebuilt-models.md)]

learn-pr/wwl-data-ai/extract-data-with-document-intelligence/5-train-custom-models.yml

@@ -0,0 +1,14 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.extract-data-with-document-intelligence.train-custom-models
+title: Train and use custom models
+metadata:
+  title: Train and use custom models
+  description: Learn how to train custom neural and template models and use them to extract data from your documents.
+  ms.date: 03/11/2026
+  author: ivorb
+  ms.author: berryivor
+  ms.topic: unit
+  ai-usage: ai-assisted
+durationInMinutes: 8
+content: |
+  [!include[](includes/5-train-custom-models.md)]

learn-pr/wwl-data-ai/extract-data-with-document-intelligence/6-exercise.yml

@@ -0,0 +1,14 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.extract-data-with-document-intelligence.exercise
+title: Exercise - Analyze documents with Document Intelligence
+metadata:
+  title: Exercise - Analyze documents with Document Intelligence
+  description: Practice using Azure Document Intelligence to analyze documents with prebuilt models.
+  ms.date: 03/11/2026
+  author: ivorb
+  ms.author: berryivor
+  ms.topic: unit
+  ai-usage: ai-assisted
+durationInMinutes: 30
+content: |
+  [!include[](includes/6-exercise.md)]

learn-pr/wwl-data-ai/extract-data-with-document-intelligence/7-knowledge-check.yml

@@ -0,0 +1,52 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.extract-data-with-document-intelligence.knowledge-check
+title: Module assessment
+metadata:
+  title: Module assessment
+  description: Knowledge check for extracting data with Azure Document Intelligence.
+  ms.date: 03/11/2026
+  author: ivorb
+  ms.author: berryivor
+  ms.topic: unit
+  ai-usage: ai-assisted
+  module_assessment: true
+durationInMinutes: 3
+content: |
+  [!include[](includes/7-knowledge-check.md)]
+quiz:
+  title: "Check your knowledge"
+  questions:
+  - content: "You need to extract text and table structure from a set of documents that have varying formats. You don't need to identify specific labeled fields. Which Document Intelligence model should you use?"
+    choices:
+    - content: "The read model."
+      isCorrect: false
+      explanation: "Incorrect. The read model extracts text and languages but doesn't extract tables or structural information."
+    - content: "The layout model."
+      isCorrect: true
+      explanation: "Correct. The layout model extracts text, tables, selection marks, and document structure information, making it ideal for documents with varying formats where you need structural data."
+    - content: "The invoice model."
+      isCorrect: false
+      explanation: "Incorrect. The invoice model is a prebuilt model designed specifically for invoices, not general documents with varying formats."
+  - content: "You're building a custom model in Azure Document Intelligence. What training artifacts are required when training with the REST API?"
+    choices:
+    - content: "Only the sample form documents in a blob container."
+      isCorrect: false
+      explanation: "Incorrect. In addition to sample forms, you need JSON files that describe the fields, labels, and OCR data for each form."
+    - content: "Sample forms along with ocr.json, labels.json, and fields.json files in a blob container."
+      isCorrect: true
+      explanation: "Correct. You need an ocr.json file for each sample form, a labels.json file for each form mapping fields to locations, and a single fields.json file describing the fields to extract."
+    - content: "A minimum of 100 labeled forms and a trained classifier."
+      isCorrect: false
+      explanation: "Incorrect. You can train a custom model with as few as five to six sample forms. A classifier is optional and separate from the extraction model."
+  - content: "A company processes both invoices and receipts. They want a single endpoint that routes each document to the correct extraction model. What should they use?"
+    choices:
+    - content: "A custom neural model."
+      isCorrect: false
+      explanation: "Incorrect. A custom neural model extracts data from one type of document. It doesn't automatically route between different document types."
+    - content: "A prebuilt read model."
+      isCorrect: false
+      explanation: "Incorrect. The read model extracts text but doesn't classify documents or extract domain-specific fields."
+    - content: "A composed model or a custom classifier paired with extraction models."
+      isCorrect: true
+      explanation: "Correct. A composed model combines multiple custom models into a single endpoint and classifies each document to the appropriate component model. Alternatively, a custom classifier can identify the document type before routing to the correct extraction model."
+

learn-pr/wwl-data-ai/extract-data-with-document-intelligence/8-summary.yml

@@ -0,0 +1,14 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.extract-data-with-document-intelligence.summary
+title: Summary
+metadata:
+  title: Summary
+  description: Summary of extracting data with Azure Document Intelligence.
+  ms.date: 03/11/2026
+  author: ivorb
+  ms.author: berryivor
+  ms.topic: unit
+  ai-usage: ai-assisted
+durationInMinutes: 3
+content: |
+  [!include[](includes/8-summary.md)]

learn-pr/wwl-data-ai/extract-data-with-document-intelligence/includes/1-introduction.md

@@ -0,0 +1,19 @@
+Forms and documents are used to communicate information in every industry, every day. Many organizations still manually extract data from forms to exchange information, whether it's filing claims, enrolling patients, processing receipts for expense reports, or reviewing operations data.
+
+Imagine you work for a company that processes thousands of invoices, receipts, and tax forms each month. You want to automate the extraction of key data from these documents to reduce manual effort and improve accuracy. Azure Document Intelligence provides the AI-powered tools you need to build this kind of solution.
+
+Azure Document Intelligence is a cloud-based service in Microsoft Foundry that uses optical character recognition (OCR) and deep learning models to extract text, key-value pairs, tables, and structured data from forms and documents. It offers prebuilt models for common document types, document analysis models for general text extraction, and the ability to train custom models for your specific forms.
+
+## Learning objectives
+
+By the end of this module, you'll be able to:
+
+- Describe the capabilities and components of Azure Document Intelligence.
+- Use the Document Intelligence Studio to explore and test models.
+- Use prebuilt models to extract data from common document types.
+- Train and use custom models for industry-specific forms.
+
+## Prerequisites
+
+- Familiarity with Azure and the Azure portal.
+- Programming experience with C# or Python.