RAG Academy

A focused course on Retrieval-Augmented Generation: the concepts, the architectures, and the strategies that survive contact with production.

It covers chunking, embeddings, vector stores, retrieval strategies, reranking, evaluation and the failure modes that only appear in production. It is written for engineers building or debugging a retrieval-augmented system.

Every branch states the trade-off that decided it, so the recommendation you end on comes with the reasoning attached — something you can paste into a design note or defend in a review.