AI & ML Engineering · Unit 12 · AI Engineering
Retrieval-Augmented Generation
Grounding a model in your own documents so it answers from sources.
- 12.1
The RAG Pipeline
Ingestion, retrieval and generation, end to end.
- 12.2
Document Parsing and Chunking
Getting text out of real documents and splitting it sensibly.
- 12.3
Embeddings and Vector Databases
Turning text into vectors and searching them by similarity.
- 12.4
Hybrid Search and Reranking
Combining keyword and vector search, then reordering the results.
- 12.5
Query Transformation
Rewriting and expanding questions before searching.
- 12.6
Evaluating RAG
Measuring retrieval quality, faithfulness and answer relevance.
Unit project
A question-answering system over a real document set that cites its sources and has a measured retrieval score.
Paid learners get the full brief, submit it from their dashboard and have it reviewed. It goes in your portfolio.
Open every unit
Enrol once to open every unit, its videos and a reviewed project for your portfolio.