Course Outline
Introduction to vectors, AI vector embeddings, prevalent AI embedding models, semantic search, and distance metrics.
Survey of vector indexing strategies: IVFFlat and HNSW indexes.
PgVector extension for PostgreSQL: setup, storage and retrieval of high-dimensional vectors, distance calculations, and utilization of vector indexes.
PgAI extension for PostgreSQL: installation, embedding generation, RAG implementation, and advanced development patterns.
Survey of Text-to-SQL solutions: The LangChain framework.
Course outcome: Upon completion, learners will be equipped to design and construct components of AI-driven database applications leveraging PostgreSQL extensions and libraries. They will obtain hands-on experience with techniques for integrating large language models (LLMs) and vector search into practical systems, empowering them to build applications such as semantic search engines, AI assistants, and natural-language database interfaces.
Requirements
Foundational understanding of SQL, practical experience with PostgreSQL, and basic proficiency in Python or JavaScript programming languages.
Audience: Database developers, system architects
Testimonials (2)
advance topics hands on + discussion like timescaleDB and hypertable , trainer's knowledge on the subject :)
Shivam - Paessler LLC
Course - PostgreSQL Fundamentals
The patiance and the style of teaching of Michał was nice.