README.md

Configuring Chatbot with Llama 3.1:8B on Local Machine

This document provides a step-by-step guide to install and run the Llama 3.1:8B model on your local machine and configure a chatbot which can read document file and answer questions.

Prerequisites

Before you begin, ensure you have the following installed:

• Python (version 3.8 or higher)
• Pip (Python package installer)
• Git (for cloning repositories)
• VSCode (recommended for editing and debugging code)

Installation Steps

1. Download Ollama Toolkit

Ollama is required to run Llama models. Follow these steps based on your OS:

1. Download the Ollama installer from the official Ollama website.
2. Run the installer and follow the on-screen instructions.
3. Verify installation by opening Terminal / PowerShell and running:

   ollama --version 

2. Install & run Llama 3.1:8B

Check here before proceeding it require 4.7gb of internet data download and disk space

https://ollama.com/library/llama3.1:8b

1. Open Terminal or Command Prompt based on your OS.
2. Run the following command to install and run the Llama 3.1:8B model locally:

   ollama run llama3.1:8b

3. Clone this repository

git clone [email protected]:VinayRajput/Chatbot-with-llama3.1-8b.git

Required Python Packages

Install using pip

langchain

pip install --upgrade --quiet langchain-openai langchain
pip install streamlit

langchain_community

pip install python-dotenv langchain-community

langchain_chroma

pip install -U langchain_chroma

langchain_ollama

pip install -U langchain-ollama

callbacks

pip install langchain-community

PyPDFLoader

pip install pypdf

Run Python Code

streamlit run app.py