Course Outline
Key concepts covered in this course include:
- the basics of vectors
- AI vector embeddings
- leading AI embedding models
- semantic search
- distance metrics
We will also examine vector indexing strategies, specifically:
- IVFFlat index
- HNSW index
Furthermore, the curriculum details the PgVector extension for PostgreSQL, covering:
- installation procedures
- storage and retrieval of high-dimensional vectors
- application of distance metrics
- utilizing vector indexes
Course Outcome: Upon completion, participants will possess a solid understanding of prominent AI-enabled PostgreSQL extensions. They will also have acquired hands-on experience in integrating large language models (LLMs) and vector search capabilities into practical, real-world scenarios.
Requirements
Participants should possess foundational SQL knowledge and basic familiarity with PostgreSQL.
Lab Environment: Access to DaDesktops 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.