Learn RAG
Retrieval places external evidence in the prompt. It does not guarantee a correct answer.
Read each short explanation, work through the example, then answer a pop quiz. Every answer explains the reasoning. Incorrect answers unlock a fresh question on the same idea; the full lesson contains ten questions.
01Understand the basics
Ready to learnRetrieval-augmented generation (RAG) searches external material and includes selected evidence in a model prompt. It can make relevant information available, but retrieval can miss useful sources and a model can still misread them.
02Choose chunks deliberately
Ready to learnChunks are searchable pieces of a document. Overlap repeats some content to preserve context across boundaries, increasing storage and processing. Test chunking against real questions.
Try a different value
03Evaluate evidence and answers
Ready to learnMeasure whether retrieval finds relevant authorised evidence, then whether the answer is supported by it. Keep source text separate from trusted instructions and provide a fallback when evidence is missing.
You’ve practised all three sections.
First-attempt understanding and later practice are shown separately. Keep practising with the related tools or continue through the suggested path.
Put it to work
Apply what you’ve learned using the related tools.