This course explains retrieval in simple terms: chunking, search, and answering from your own notes or docs.
Includes practical lessons, exercises, and a clear next step after you enroll.
About this course
Curriculum
Lessons are listed in order. Each one has a goal, a walkthrough, practice, and a short check before you continue.
- 01Why retrieval existsThe model does not have your docs unless you fetch them.
- 02Chunking without destroying meaningSplit on structure, overlap a little, keep citations.
- 03Embeddings and similarity in plain languageClose vectors mean similar meaning, not truth.
- 04The generate step with citationsAnswer only from retrieved text and show sources.
- 05Failure modes: wrong chunk, empty, and conflictWhat users should see in each case.
- 06A smallest useful retrieval demoTen docs, one question box, citations on screen.
- 07Workshop: a complete pass on a real taskCombine the earlier lessons into one working example you can keep.
- 08Quality bar, common mistakes, and a 30-day planLock in a checklist so the skill survives after the course ends.