Course Outline
Foundations covering:
- vector concepts
- AI vector embeddings
- leading AI embedding models
- semantic search principles
- distance metrics
Insight into vector indexing methodologies:
- IVFFlat index structure
- HNSW index structure
Implementing the PgVector extension in PostgreSQL:
- setup and installation
- managing high-dimensional vector data storage and retrieval
- application of distance metrics
- leveraging vector indexes
Learning Outcomes: Upon completion, participants will possess a clear understanding of prominent AI-enhanced PostgreSQL extensions. They will also develop practical expertise in integrating large language models (LLMs) and vector search capabilities into production-grade applications.
Requirements
Fundamental SQL proficiency and basic familiarity with PostgreSQL
Lab environment: DaDesktops utilizing Linux virtual machines (supplied 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.