Course Outline
Foundations covering:
- Vector mathematics
- AI vector embeddings
- Leading AI embedding models
- Principles of semantic search
- Distance metric calculations
Analysis of vector indexing strategies:
- IVFFlat indexing
- HNSW indexing
Deep dive into the PgVector extension for PostgreSQL:
- Setup and installation procedures
- Managing and querying high-dimensional vector data
- Application of distance measures
- Optimization using vector indexes
Learning Outcomes: Upon completion, students will possess a comprehensive understanding of prominent AI-driven PostgreSQL extensions. They will also acquire practical expertise in integrating large language models (LLMs) and vector search capabilities into production-grade applications.
Requirements
• Foundational knowledge of SQL and basic practical experience with PostgreSQL
Lab Environment: DaDesktops Linux virtual machines (Provided by NobleProg)
Target Audience: Database application developers, system architects, and data analysts
Testimonials (2)
Tuning strategies.
Jeffrey Zieg - Matrix Consulting
Course - PostgreSQL Performance Tuning
Logging behaviour when the instance is under stress, and the hierarchy/nomenclature of instances, databases, files, etc.