Course catalog
Give your LLM a memory it can trust.
Large language models forget after their training cutoff, make things up, and have never seen your private data. Retrieval-Augmented Generation fixes all three by fetching the right facts at query time and feeding them to the model so it answers from evidence, with citations. You'll build a full RAG pipeline in Python — load, chunk, embed, store, retrieve, and generate — then level it up with hybrid search, rerankers, and query rewriting. Finally you'll ship it: evaluate faithfulness with RAGAS-style metrics, cut hallucinations and cost, and defend against prompt injection and data leakage.
Section 1
Understand what large language models can’t do alone, and how retrieval fixes it.
Section 2
Wire up the core RAG loop: load, chunk, embed, store, retrieve, and generate.
Analyze real data and build tested tools that talk to outside APIs safely and search your own content, using Python, Git, SQL, and vector search.
10 course sequence
Build and run a real AI product: it searches your own content, uses only the tools you approved, is tested the same way every time, has a plan for when it fails, and shows its speed and cost.
11 course sequence
Eligible first-time members can get 7 free days · Cancel anytime
Get startedSection 3
Push retrieval quality with hybrid search, rerankers, query rewriting and filters.
Section 4
Evaluate, secure, and scale RAG — plus where the field is heading in 2026.