Course Outline
Introduction to the following concepts:
- vectors
- AI vector embeddings
- leading AI embedding models
- semantic search
- distance metrics
An overview of vector indexing methods:
- IVFFlat index
- HNSW index
The PgVector extension for PostgreSQL:
- installation
- managing and querying high-dimensional vectors
- distance metrics
- utilizing vector indexes
Learning outcomes: Upon completion, students will possess a clear understanding of prominent AI-driven PostgreSQL extensions. They will also acquire hands-on experience in integrating large language models (LLMs) and vector search capabilities into real-world application scenarios.
Requirements
Foundational proficiency in SQL and basic familiarity with PostgreSQL
Lab setup: DaDesktops hosting Linux virtual machines (supplied by NobleProg)
Target audience: Developers of database applications, system architects, and data analysts
Testimonials (3)
performance knowledge
Adrian Ionut Chelaru - Banca Transilvania Cluj
Course - PostgreSQL Advanced - Performance Management
Tables indexes and qq reperforming & tuning in order to improve them
Roberto Esposito
Course - PostgreSQL AI for Developers
A good first contact with a new database technology