Technique that combines retrieving relevant information from an external source (vector database, documents) with generation from a language model, enabling answers grounded in up-to-date or private data without retraining the model.
A central topic of AIF-C01 Domain 3 and GENAI-L Domain 3. On AWS it's implemented with Amazon Bedrock Knowledge Bases (managed RAG). Typical question: answer questions about internal company documents without fine-tuning → RAG.
RAG (Retrieval-Augmented Generation) is a concept that can show up on the exam. Check the full guide to see it in context.