VIT University Data Query via Retrieval-Augmented Generation - LangChain and Mistral LLM

This project is designed to query data about VIT University using Retrieval-Augmented Generation (RAG) techniques with LangChain and the Mistral LLM.

Overview

This project leverages the power of LangChain and Mistral LLM to efficiently query and retrieve data about VIT University, including its national and world rankings, scores, and other relevant information.

Features

• Retrieval-Augmented Generation (RAG): Enhances the querying process by combining retrieval-based and generation-based approaches.
• LangChain Integration: Utilizes the LangChain library for seamless data handling and querying.
• Mistral LLM: Employs the Mistral language model for generating accurate and comprehensive responses.

Getting Started

To get started with this project, follow these steps:

Prerequisites

• Python 3.x
• Jupyter Notebook
• Required Python libraries (listed in requirements.txt)

Google Colaboratory

1. Navigate to the provided Colab notebook link:

   VIT University Data Query Notebook

Usage

1. Open Colab link.
2. Follow the instructions in the notebook to run the data query process.
3. Input your queries related to VIT University to retrieve relevant data.