Description

Retrieval Augmented Generation (RAG) is a method that enhances large language models (LLMs) by providing them with external knowledge. This is particularly useful in knowledge-intensive scenarios or domain-specific applications that require up-to-date information.

Prompt Engineering Guide highlight the main findings and practical insights from the recent survey titled Retrieval-Augmented Generation for Large Language Models: A Survey. They provide an overview of the existing approaches, state-of-the-art RAG, evaluation, applications and technologies surrounding the different components that make up a RAG system (retrieval, generation, and augmentation techniques). They also discuss various paradigms of RAG including Naive RAG, Advanced RAG, and Modular RAG.