Chat Locally with you Docs Using RAG

Introduction

This project leverages open-source models such as LangChain, Llama, and EmbeddingModel to create a flexible local chatting notebook. The models used in this project can be replaced with any open-source models, providing flexibility and adaptability. Additionally, this project is built upon the RAG (Retrieval-Augmented Generation) technique which enhances the performance and efficiency of the models.

Features

• Flexible Notebook: The notebook can be easily modified to incorporate different open-source models.
• LangChain and Llama: These models are used to facilitate the creation of the local chatting notebook.
• EmbeddingModel: This model is used to create embeddings for the data.
• ChromaDB: Used for efficient data storage and retrieval.
• RAG Technique: The Retrieval-Augmented Generation technique is used to enhance the performance and efficiency of the models.

Usage

The notebook provide step by step guide on how to create your own local chat docs. you can change the embedding and LLM models to the one you like from hugging face.