Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
- Learn how to use Azure Database for PostgreSQL as a data foundation for AI applications, including schema design, SQL queries, and Python integration.
After completing this module, you'll be able to:
- Explain the architecture and key features of Azure Database for PostgreSQL
- Establish secure connections to PostgreSQL using Microsoft Entra authentication and TLS
- Create and manage database schemas including tables, indexes, and constraints
- Write efficient SQL queries for common data operations
- Integrate Azure Database for PostgreSQL into applications using Python
- Learn how to implement vector search in Azure Database for PostgreSQL using the pgvector extension for semantic search, recommendations, and RAG pipelines.
After completing this module, you'll be able to:
- Store and query vector embeddings using the pgvector extension in Azure Database for PostgreSQL
- Execute vector similarity searches using different distance metrics and operators
- Create and manage vector indexes to optimize search performance
- Implement embedding update and refresh strategies for evolving datasets
- Build retrieval patterns that integrate PostgreSQL vector search with RAG pipelines
- Tune pgvector configuration, select vector indexes, design efficient data layouts, and scale Azure Database for PostgreSQL for high-performance AI workloads.
After completing this module, you'll be able to:
- Tune PostgreSQL and pgvector configuration parameters to optimize query latency and memory usage for AI workloads
- Select and configure the appropriate vector index type based on dataset size, query patterns, and accuracy requirements
- Design data layouts that optimize vector storage and metadata filtering performance
- Scale Azure Database for PostgreSQL to handle high-volume vector workloads
- Implement connection pooling and session management strategies for AI applications
