Explain what RAG is and how it connects large language models to external information. Understand retrieval, augmentation and generation, and how they differ from model training. Identify the roles of the knowledge base, retriever, integration layer and generator. Explain chunking and embeddings, including why preserving context matters. Compare keyword, vector and hybrid retrieval methods. Recognise practical RAG applications in research, customer support, content creation and organisational knowledge. Assess source relevance, freshness, citations and the limitations of retrieved evidence. Understand why accuracy, privacy, security and cost savings depend on system design and maintenance.