Skip to content
Dr. Ram KumarDiabetes & metabolic health

Medical AI · Track 6 of 10

Retrieval-augmented generation (RAG)

Grounding LLM answers in trusted sources such as clinical guidelines: chunking, embeddings, retrieval, citations and evaluation.

Generative AI & LLMs track recommended first.

By the end of this track you should be able to

  • Explain when RAG is the right tool and when it is not
  • Chunk and index a clinical guideline
  • Measure retrieval quality and answer faithfulness
  • Build a guideline question-answering assistant that cites its sources

Lessons

  1. Why RAG? Grounding answers in trusted sources

    Beginner · Clinical · 20 min · Exercise

  2. Chunking clinical guidelines

    Intermediate · Technical · 30 min · Exercise

  3. Embeddings and vector stores

    Intermediate · Technical · 35 min · Exercise

  4. Evaluating retrieval

    Intermediate · Technical · 30 min · Exercise

  5. Citations and answer grounding

    Intermediate · Technical · 30 min · Exercise

  6. Build a guideline Q&A assistant

    Intermediate · Technical · 35 min · Exercise

  7. End-to-end RAG evaluation

    Intermediate · Technical · 30 min · Exercise

Next track: Agentic AI

Educational content only. This material teaches methods; it is not clinical advice. Code, models and examples here are not validated medical devices and must not be used to make decisions about real patients without proper clinical validation, governance and any required regulatory approval. Examples use synthetic or openly licensed de-identified data only. Never paste identifiable patient information into public AI tools. Mentions of models, tools or vendors are for identification, not endorsement.