RAG

AIGP glossary · Last reviewed: 2026-07-08 · By Victor Humenhuk (AIGP certified)

RAG - Retrieval-augmented generation: pulls in external information to boost LLM accuracy and relevance.

In the AIGP body of knowledge, RAG comes up under Module 1: Foundations of AI · BoK IV.A.

RAG in context

• Governance pros must hold a credible conversation about architectures: transformer models (==process inputs in parallel==), multimodal models/LMMs (==WHO 2024 ethics guidance==), generative and specialised networks (CNN/RNN/GNN), and ==RAG== for pulling in external information. (Architectures and the buzzwords that matter)
• ==RAG== is defined by retrieving from a knowledge base ==beyond the training data sources== and grounding the answer in it. (Generative AI)

Where RAG is covered in the AIGP study notes

• Architectures and the buzzwords that matter

Related terms

• Transformer models
• Multimodal models (LMMs)
• CNN
• RNN
• GNN

Test yourself on RAG

Recognising a definition is not the same as applying it in an exam scenario. Work through the free AIGP practice questions, or read the full AIGP study guide - every study note is free.

← Back to the AIGP glossary