AI Glossary
Retrieval-Augmented Generation (RAG)
A technique that combines information retrieval with AI generation to produce more accurate and context-aware responses.
Retrieval-Augmented Generation (RAG)
Overview
One challenge facing many AI systems is that their knowledge is often limited to the information available during training.
If new information becomes available after training, the model may not automatically know about it.
Retrieval-Augmented Generation, commonly called RAG, helps address this problem.
RAG combines a language model with an external knowledge source. Instead of relying entirely on what was learned during training, the system first retrieves relevant information and then uses that information to generate a response.
A helpful way to think about RAG is an employee answering a question. Rather than relying entirely on memory, the employee first checks company documents, retrieves the relevant information, and then provides an answer.
Modern RAG systems often rely on technologies such as Vector Databases to efficiently find relevant information.
Because of its ability to improve accuracy and incorporate current information, RAG has become one of the most important techniques in enterprise AI applications.
Why It Matters
RAG helps AI systems provide more accurate, current, and context-aware responses.
Real-World Example
A company chatbot may use RAG to search internal documentation before answering employee questions.