Course Outline
Key concepts introduced:
- Vectors
- AI vector embeddings
- Leading AI embedding models
- Semantic search
- Distance metrics
Insights into vector indexing methods:
- IVFFlat index
- HNSW index
Deep dive into the PgVector extension for PostgreSQL:
- Installation procedures
- Managing and querying high-dimensional vectors
- Applying distance metrics
- Leveraging vector indexes
Learning outcomes: Upon completion, students will have a solid grasp of popular AI-enhanced PostgreSQL extensions. They will also acquire practical skills in integrating large language models (LLMs) and vector search capabilities into real-world applications.
Requirements
Foundational knowledge of SQL and basic experience with PostgreSQL
Lab setup: DaDesktops running 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.