Course Outline
Introduction to vectors, AI vector embeddings, widely adopted AI embedding models, semantic search methodologies, and distance metrics.
Survey of vector indexing strategies: IVFFlat and HNSW indexes.
The PgVector extension for PostgreSQL: installation procedures, storage and querying of high-dimensional vectors, distance calculations, and effective use of vector indexes.
The PgAI extension for PostgreSQL: setup, embedding generation, implementation of Retrieval-Augmented Generation, and advanced development patterns.
Overview of Text-to-SQL solutions: focusing on the LangChain framework.
Course Outcome: Upon completion, students will be equipped to design and construct components of AI-driven database applications leveraging PostgreSQL extensions and libraries. They will gain practical expertise in integrating large language models (LLMs) and vector search into production systems, allowing them to develop 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 either Python or JavaScript.
Target Audience: Database developers and system architects
Testimonials (2)
The provided examples and labs
Christophe OSTER - EU Lisa
Course - PostgreSQL Advanced DBA
1. A very well-structured training program 2. The warm atmosphere the trainer created, along with his outstanding personal professionalism 3. That the trainer explained everything as if he were talking to a complete beginner, without slipping into any technical jargon.
