quyanh2005/rag-llamaindex

RAG System Building Guide with LlamaIndex

RAG System Building Guide with LlamaIndex

This repository provides step-by-step instructions to create a custom RAG (Retrieval-Augmented Generation) system, leveraging the power of large language models (LLMs) and specifically focusing on VinaLLaMA for the Vietnamese language.

Introduction

The RAG System is a powerful natural language processing model that combines the capabilities of retrieval-based and generative approaches. This guide will walk you through the process of building a custom RAG system using OpenAI API, and specifically integrating LlamaIndex for enhanced performance.

Requirements

Before you begin, ensure that you have the following prerequisites installed and configured:

• Python 3.x
• OpenAI API key
• LlamaIndex library

Features

• Building a RAG System using OpenAI API
• Building a Custom RAG System using Starling-7B
• Building a Custom RAG System using VinaLLaMA for Vietnamese Language
• Building an advanced RAG System with
  • Sentence Window Retrieval
  • Auto-merging Retrieval
• How to evaluate a RAG System

Notebooks are available on colab

• RAG_with_LlamaIndex.ipynb
• Build_and_Evaluate_Advanced_RAG.ipynb

License

This project is licensed under the Apache License 2.0. Feel free to use and modify the code according to the terms of the license.