What Is Retrieval-Augmented Generation?

Retrieval-Augmented Generation (RAG) is an AI architecture that combines document retrieval with language model generation.

Instead of relying only on the model’s internal knowledge, a RAG system retrieves relevant documents from a database and includes them in the prompt.

This approach has several benefits:

• answers can reference current information,

• responses can cite supporting documents,

• hallucination risk can be reduced,

• knowledge bases can be updated without retraining the model.

A typical RAG pipeline includes:

• document ingestion

• text chunking

• embedding generation

• vector search retrieval

• prompt construction

• language model generation

RAG is widely used for building knowledge assistants, document question-answering systems, and enterprise search tools.

However, retrieval quality and evaluation remain critical components of a reliable RAG system.