Domain 2 is the heaviest on the exam. It covers the three data services an AI back end relies on: Azure Cosmos DB for NoSQL (SDK queries, indexing policies, consistency, vector search, and the change feed processor), Azure Database for PostgreSQL (schemas, pgvector indexes, compute sizing, RAG with metadata filters, and connection pooling), and Azure Managed Redis (caching, expiration, invalidation, and vector indexing).
Skills measured
Objectives and skills below are quoted from the official study guide. The count beside each skill is how many exam simulator questions test it.
2.1 Develop AI solutions by using Azure Cosmos DB for NoSQL
- Connect to Azure Cosmos DB for NoSQL by using the SDK and run queries2
- Optimize query performance and Request Units (RUs) consumption by using indexing policies and consistency levels3
- Store and retrieve embeddings and execute vector similarity search for semantic retrieval2
- Implement a change feed processor to detect and handle new or updated items3
2.2 Develop AI solutions by using Azure Database for PostgreSQL
- Connect and query Azure Database for PostgreSQL by using SDKs1
- Model schemas and implement indexing strategies, including designing tables and choosing appropriate data types1
- Implement indexing strategies, including optimizing query latency and reducing pgvector compute overhead2
- Configure compute, memory, and storage resources to support vector workloads2
- Run vector similarity search, including storing embeddings, semantic retrieval, and implementing retrieval-augmented generation (RAG) patterns by using metadata filter2
- Implement connection optimization to improve throughput and minimize latency3
2.3 Integrate Azure Managed Redis in AI solutions
- Implement Azure Managed Redis data operations, including caching, expiration, and invalidation6
- Implement vector indexing to enable similarity search3
Official Microsoft Learn training
These are the learning paths from the official AI-200T00 course that cover this domain. Durations are Microsoft's estimates.
Develop AI solutions with Azure Cosmos DB for NoSQL · 4 hr 12 min
- Build queries for Azure Cosmos DB for NoSQL · 1 hr 12 min · includes a hands-on exercise
- Implement vector search on Azure Cosmos DB for NoSQL · 1 hr 24 min · includes a hands-on exercise
- Optimize query performance for Azure Cosmos DB for NoSQL · 1 hr 36 min · includes a hands-on exercise
Develop AI solutions with Azure Database for PostgreSQL · 4 hr 54 min
- Build and query with Azure Database for PostgreSQL · 1 hr 29 min · includes a hands-on exercise
- Implement vector search with Azure Database for PostgreSQL · 1 hr 34 min · includes a hands-on exercise
- Optimize vector search in Azure Database for PostgreSQL · 1 hr 51 min · includes a hands-on exercise
Enhance AI solutions with Azure Managed Redis · 3 hr 42 min
- Implement data operations in Azure Managed Redis · 1 hr 1 min · includes a hands-on exercise
- Implement event messaging with Azure Managed Redis · 1 hr 21 min · includes a hands-on exercise
- Implement vector storage in Azure Managed Redis · 1 hr 20 min · includes a hands-on exercise
