Course Outline
Foundations covered include:
- vectors
- AI vector embeddings
- prevalent AI embedding models
- semantic search
- distance metrics
An examination of vector indexing strategies:
- IVFFlat index
- HNSW index
Implementation details for the PgVector extension in PostgreSQL:
- installation procedures
- managing high-dimensional vectors (storage and retrieval)
- application of distance measures
- utilization of vector indexes
Learning Outcomes: Upon completion, students will possess a comprehensive understanding of leading AI-driven PostgreSQL extensions. They will have developed practical competence in integrating large language models (LLMs) and vector search capabilities into production-ready applications.
Requirements
Foundational proficiency in SQL and basic working knowledge of PostgreSQL
Lab environment: DaDesktops hosting Linux virtual machines (provided by NobleProg)
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.