Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
Fundamentals of vector technologies, including:
- vectors
- AI vector embeddings
- popular AI embedding models
- semantic search
- distance measures
Analysis of vector indexing techniques:
- IVFFlat index
- HNSW index
Utilizing the PgVector extension in PostgreSQL:
- setup and installation
- management of high-dimensional vectors
- application of distance measures
- implementation of vector indexes
Application of the PgAI extension in PostgreSQL:
- setup and installation
- generation of embeddings
- execution of Retrieval-Augmented Generation
- advanced development patterns
Introduction to Text-to-SQL solutions via the LangChain framework
Course outcome: Upon completion, participants will be equipped to:
- design and construct AI-driven database applications using PostgreSQL extensions and libraries.
- apply practical techniques for integrating large language models (LLMs) and vector search into production systems, facilitating the creation of semantic search engines, AI assistants, and natural-language database interfaces.
Requirements
A foundational understanding of SQL, preliminary experience with PostgreSQL, and basic proficiency in Python or JavaScript are required.
Audience: Database developers and system architects
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.
