Vector Databases and Retrieval Data Engineering

О курсе

This course teaches learners to design, operate, secure, and evaluate vector-based retrieval systems used in semantic search and RAG applications. Learners work with embeddings, vector schemas, index design, refresh strategies, consistency checks, evaluation signals, retrieval observability, and permissions-aware access controls. The course focuses on practical system design and tradeoffs rather than low-level algorithm implementation. By the end of the course, learners can explain how embeddings enable semantic retrieval, compare dense, sparse, and hybrid retrieval patterns, design vector database schemas and refresh workflows, evaluate retrieval quality, and apply governance and security controls to retrieval systems. Topics include vector stores, metadata filtering, HNSW and IVF concepts, recall/latency tradeoffs, retrieval drift, and audit logging.

Навыки, которые вы освоите

Учитесь у экспертов

Antonio Cangiano

Engineering Manager and AI Specialist

Ruslan Podgaets

Преподаватель курса