Retrieval & RAG Systems

For engineers who have built LLM applications and hit the ceiling of naive RAG. This course covers chunking as a retrieval design decision, hybrid BM25-plus-dense search with reciprocal rank fusion, query rewriting, cross-encoder re-ranking, retrieval metrics (recall@k, MRR, nDCG), faithfulness and groundedness evals, index freshness, permission-aware retrieval, and auditing AI-generated RAG pipelines.

Lessons are AI-assisted and human-reviewed. Learn more.