Syllaro Academy

AWS Certified AI Practitioner

Retrieval Augmented Generation (RAG)

Give a model access to your private, current data without retraining it: how RAG retrieves relevant passages at query time, how Amazon Bedrock Knowledge Bases automates it, and where the boundary with fine-tuning sits.

Intermediate 20 minutes 5 Learning Objectives
  1. Explain the problem RAG solves that a base model cannot
  2. Describe the two phases of RAG: ingestion and retrieval at query time
  3. Explain what Amazon Bedrock Knowledge Bases automates
  4. Distinguish RAG from fine-tuning and from pasting everything into a long context window
  5. Identify business applications where RAG is the right fit