Course Outline
Introduction to:
- vectors
- AI vector embeddings
- popular AI embedding models
- semantic search
- distance measures
Overview of vector indexing techniques:
- IVFFlat index
- HNSW index
PgVector extension for PostgreSQL:
- installation
- storing and querying high-dimensional vectors
- distance measures
- using vector indexes
PgAI extension for PostgreSQL:
- installation
- generating embeddings
- implementing Retrieval-Augmented Generation
- advanced development patterns
Overview of Text-to-SQL solutions: LangChain framework
Course outcome: By the end of the course, students will be able to:
- design and build elements of AI-powered database applications using PostgreSQL extensions and libraries.
- gain practical experience with techniques for integrating large language models (LLMs) and vector search into real-world systems, enabling them to develop applications such as semantic search engines, AI assistants, and natural-language database interfaces.
Requirements
basic knowledge of SQL, basic experience with PostgreSQL, basic knowledge of Python or JavaScript programming languages
Audience: database developers, system architects
Testimonials (3)
Tuning strategies.
Jeffrey Zieg - Matrix Consulting
Course - PostgreSQL Performance Tuning
Discussing the significant differences between certain commands available in PostgreSQL and the distinctive features of these databases (e.g., a clear and visual explanation of the differences between VACUUM and VACUUM FULL).
Maciej Golonka - CENTRUM INFORMATYKI RESORTU FINANSOW
Course - PostgreSQL Server Administration
Machine Translated
Logging behaviour when the instance is under stress, and the hierarchy/nomenclature of instances, databases, files, etc.
