RAG (RAG): definition | Xpand Media

GEO / AI Search

RAG

Definition

What is RAG?

Retrieval-Augmented Generation. Pattern where an LLM first retrieves relevant passages from a knowledge base, then generates an answer grounded in those passages. Underpins Perplexity, AI Overviews, and most enterprise AI search products.

Related terms

Cross-linked concepts

Embedding

Numerical vector representation of a piece of text, image, or other content. Two embeddings that are close in vector space represent semantically similar content. Foundation of vector search and RAG.

Vector Search

Search that compares query and document embeddings rather than keywords. Returns semantically similar passages even when no exact word overlap exists. Powers most modern AI retrieval stacks.

Same category

More GEO / AI Search terms

Generative Engine OptimizationGEO
Answer Engine OptimizationAEO
Answer Capsule
Atomic Fact
Entity Authority
llms.txt

Browse all 121 glossary terms →

Want to put RAG to work?

We run GEO / AI Search-led engagements every week. A 20-minute call gets you a read on whether rag is the right next move for your stack.

Book a strategy call →

Spinning up