RAG (Retrieval-Augmented Generation)

What is Retrieval-Augmented Generation (RAG)?
Retrieval-Augmented Generation (RAG) is an AI architecture in which a large language model retrieves relevant, up-to-date information from an external data source before generating its answer, instead of relying only on what it memorized during training. The retrieved documents are injected into the model's context, grounding the output in current facts.

RAG matters for commerce because pricing and availability change far faster than any model's training data. A pricing assistant built with RAG can query a live competitor-price feed or product database at question time and answer "what is the cheapest matched offer for this SKU today?" accurately — something a static model cannot do.

The quality ceiling of a RAG system is its data layer: retrieval over stale or mismatched product data produces confident but wrong answers, which is why structured, continuously refreshed market data feeds are the foundation of commercial RAG applications.