Retrieval-Augmented-Generation

RAG Implementations: Langchain & Llamaindex

This repository contains two implementations of Retrieval Augmented Generation (RAG):

1. RAG using Langchain Library
2. RAG using Llamaindex Library

Introduction

Retrieval Augmented Generation (RAG) combines the strengths of information retrieval and natural language generation. It first retrieves relevant documents and then generates a response based on both the retrieved documents and the original query. This approach leverages the vast knowledge contained in large text corpora to improve the quality of generated responses.

This repository provides two implementations of RAG:

1. Langchain Library: A flexible framework for building applications with LLMs using a modular approach.
2. Llamaindex Library: An index-centric approach tailored for efficient retrieval and generation.

Installation

Prerequisites

• Python 3.7 or higher
• Git

Clone the Repository

git clone https://github.com/pheonixdev/Retrieval-Augmented-Generation.git