Local Chatgpt setup

readme.md

Local ChatGPT Setup with LLaMA 3.2

This guide helps you set up a local instance of ChatGPT with LLaMA 3.2 for macOS or tablet access.

Requirements

1. Docker is installed on your machine.
2. Ollama is installed.

Installation Steps

1. Pull the LLaMA 3.2 Model using Ollama

   Open a terminal and run:

   ollama pull llama3.2

2. Stop Ollama Service

   If Ollama is running, stop it before proceeding:

   ollama serve

3. Run the Open WebUI Docker Container

   Now, start the container with the following command:

   docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

4. Find Your Local IP Address

   Once the container is running, get your local IP address by running this command:

   echo "https://$(ipconfig getifaddr en0):3000"

   This will display a link to access your local ChatGPT instance. Open the link in your browser or on your tablet.

5. Register

   Follow the on-screen instructions to register and start using your local ChatGPT with LLaMA 3.2.