Home / Learn / What is RAG?

Definition

What is RAG?

Retrieval-Augmented Generation (RAG) is an AI architecture that retrieves relevant information from external data sources and provides that information to a language model before it generates an answer.

The model is not expected to memorise your policy PDF. It is expected to use the passages you retrieved. That is why RAG shows up in support, internal search, and document Q&A.

RAG is the default when facts change faster than you can retrain. Fine-tuning is a later choice. If there is no corpus or no data rights, RAG is not a bargain—it is a blocker.

Aarohii implements RAG as a product feature with source display and tests. RAG development · RAG vs fine-tuning · Architecture