Course Outline
Foundational concepts covered include:
- Vector mathematics
- AI-driven vector embeddings
- Leading AI embedding models
- Semantic search mechanisms
- Distance metrics
An examination of vector indexing methodologies:
- IVFFlat indexing
- HNSW indexing
Implementation of the PgVector extension in PostgreSQL:
- Deployment procedures
- Management and retrieval of high-dimensional vectors
- Application of distance metrics
- Leveraging vector indexes for performance
Learning outcomes: Upon completion, students will possess a comprehensive understanding of prominent AI-enabled PostgreSQL extensions. They will also gain practical proficiency in integrating large language models (LLMs) and vector search capabilities into production-grade applications.
Requirements
Solid foundation in SQL and prior experience working with PostgreSQL
Practical setup: DaDesktops equipped with Linux virtual machines (supplied by NobleProg)
Target participants: 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.