Skip to content

rag-process.md

Latest commit

 

History

History
24 lines (13 loc) · 749 Bytes

rag-process.md

File metadata and controls

24 lines (13 loc) · 749 Bytes
description The Retrieval-Augmented Generation Process

Retrieval-Augmented Generation

{% hint style="info" %} This page is currently in draft {% endhint %}

What is Retrieval-Augmented Generation (RAG) ?

Retrieval-Augmented Generation (RAG) is a method for improving the accuracy and reliability of generative AI models by applying facts fetched from authoratitive sources.

The key difference betweem the general AI of Large Language Models is that data retrival is augmented (or supplemented) by local or contextual data and rules.

{% hint style="info" %} The term RAG was coined in a 2020 paper entitled - "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks" {% endhint %}