A hands-on, vendor-neutral course on building production Retrieval-Augmented Generation (RAG) and LLM applications — the core applied-AI skill employers screen for in 2026. It covers why RAG beats fine-tuning for knowledge; embeddings and vector search (cosine similarity, HNSW/IVF, metadata filtering); document ingestion and the chunking strategies that make or break quality; retrieval and ranking (hybrid search, cross-encoder rerankers, HyDE, multi-query, MMR); grounded generation with citations and the 'lost in the middle' effect; agentic RAG and structured output; and the discipline that separates demos from products — evaluation (retrieval vs generation metrics, golden datasets, LLM-as-judge/RAGAS) and LLMOps (observability, cost/latency, guardrails, deployment). Every domain has plain-language lessons, concept tables, build-it labs, knowledge checks, a randomized mastery check, a full-length mock, and a spaced-repetition flashcard deck. Free.
0.00 USD
Create a free account to preview lessons. Browse all courses.