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 (2 days)
Course Outline
Foundational concepts including:
- vector mathematics
- AI vector embedding methodologies
- standard AI embedding models
- semantic search principles
- distance metric calculations
Summary of vector indexing approaches for government applications:
- IVFFlat index architecture
- HNSW index architecture
PgVector extension implementation for PostgreSQL:
- deployment procedures
- storage and retrieval of high-dimensional vectors
- application of distance metrics
- utilization of vector indexes
PgAI extension implementation for PostgreSQL:
- deployment procedures
- embedding generation workflows
- implementation of Retrieval-Augmented Generation
- advanced development patterns
Overview of Text-to-SQL solutions: LangChain framework
Course objectives: Upon completion, participants will be able to:
- design and construct components of AI-driven database solutions using PostgreSQL extensions and libraries suitable for government operations.
- acquire practical proficiency in integrating large language models (LLMs) and vector search into production systems, facilitating the development of semantic search engines, AI assistants, and natural-language database interfaces for public sector use.
Requirements
Foundational proficiency in SQL, baseline experience with PostgreSQL, and basic competency in Python or JavaScript programming languages
Target Audience: database developers, 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.