Building a Knowledge Store with Azure AI Search

Azure AI Search is Microsoft's cloud-based search-as-a-service solution that brings enterprise-grade search capabilities to applications and data analytics workflows. Beyond traditional keyword search, it offers AI-powered enrichment that can extract insights, detect languages, identify key phrases, and transform unstructured content into structured, searchable data. A powerful feature of Azure AI Search is the knowledge store, which persists AI-enriched data to Azure Storage in multiple formats, enabling organizations to build data pipelines, create analytics dashboards, and train machine learning models without repeatedly processing the same content.

In this lab, you will build a complete knowledge store solution using Azure AI Search to enrich book catalog data with AI-powered insights. You'll learn how to configure the enrichment pipeline, define knowledge store projections, and persist enriched data in multiple formats for analytics and downstream processing.

Objectives

Upon completion of this intermediate level lab, you will be able to:

• Configure data sources and skillsets with built-in AI capabilities
• Define knowledge store projections in table and object formats
• Create and execute indexers to populate knowledge stores with enriched data
• Explore and analyze enriched data stored in Azure Storage
• Understand the differences between projection types for various analytical use cases

Who is this lab for?

This lab is designed for:

• Data Engineers building data enrichment pipelines with Azure AI services
• Cloud Solutions Architects designing search and analytics solutions on Azure
• AI/ML Engineers preparing enriched datasets for machine learning workflows
• Business Intelligence Developers creating data sources for analytics and reporting tools
• Azure Developers implementing cognitive search capabilities in applications
• Data Scientists working with AI-enriched data for analysis and modeling