Artificial Intelligence (AI) · Intermediate level

Intermediate level · Module 4 of 6 · 16 guided hours

Retrieval-Augmented Generation

Ground AI answers in an organisation's own documents using embeddings, search and cited generation.

Learning objectives

  • Explain embeddings and semantic search
  • Build a retrieval-augmented generation pipeline
  • Evaluate retrieval quality and grounding

Topics

  • why grounding is needed
  • embeddings and similarity
  • chunking documents
  • vector search
  • building the RAG pipeline
  • citations and grounding checks

Lessons

  1. Lesson 1 Embeddings and Semantic Search

    Represent text as vectors and find passages by meaning rather than exact words.

    embeddingvectorcosine similaritysemantic search

  2. Lesson 2 Building a RAG Pipeline

    Split documents into chunks, index them and generate answers from retrieved passages with citations.

    chunkingvector indexcontext assemblycitations

  3. Lesson 3 Evaluating Retrieval and Grounding

    Measure whether the right passages are found and whether answers stay faithful to them.

    retrieval hit rategroundingcitation accuracyunanswerable questions

Practical activity

Build the retrieval pipeline for the FAQ assistant over the provided official documents and measure how often the right passage is retrieved.

Expected outcomes

  • Assistants that answer from trusted sources
  • Measurable retrieval quality

Assessment

Practical: retrieval accuracy on a question set and a demonstration of cited answers.

Taught live by an instructor — online or in person. Free course lessons are for self-study and do not lead to a certificate — see registration options.