What is Retrieval-Augmented Generation (RAG)?
A technique that enhances the accuracy and reliability of generative AI models with facts fetched from external sources.
Short answer
A technique that combines the capabilities of Large Language Models (LLMs) with an external knowledge retrieval system. It allows the AI to reference specific, up-to-date data (like company documents) before generating an answer, reducing hallucinations.
RAG addresses the knowledge cutoff and hallucination issues of LLMs. Instead of relying solely on training data, a RAG system first retrieves relevant documents from a knowledge base (like a company's internal wiki) and provides them to the LLM as context for generating an answer.
Build your own AI Agent
Ready to put this concept into action? Create your own custom AI agent with Agent One in minutes. No coding required.
Start Building FreeFrequently Asked Questions
Related Terms
Prompt Engineering
The practice of designing inputs for AI models to produce optimal outputs.
Fine-tuning
The process of training a pre-trained model on a smaller, specific dataset to adapt it for a particular task.
Zero-shot Learning
The ability of a model to perform a task without having seen any specific examples of that task during training.