Set up ChatGPT locally using Ollama and open webui

Set up ChatGPT Locally Using Ollama and Open Webui

Introduction

In this guide, we will set up ChatGPT locally using Ollama and open webui.

Install WSL2 and Ubuntu 20.04

• Use this command to install WSL2 and Ubuntu 20.04

  wsl --install
  

• After installation, open Ubuntu 20.04 and set up your username and password.

• Update and upgrade the system

  sudo apt update && sudo apt upgrade -y
  

Install Ollama

• Use this command to install Ollama

  curl -fsSL https://ollama.com/install.sh | sh
  

  or visit Ollama and follow the instructions.

• After installation, you can check that Ollama is installed by opening browser and visiting http://localhost:11434/

• Now download the AI model from Ollama
• Then run the following command to install the model

  ollama install <model-name>
  

• Now your AI model is installed and running. You can stop the model by running the following command

  /bye
  

Installing Docker

• Use this command to install Docker

sudo apt-get update
sudo apt-get install ca-certificates curl
sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc

echo \
  "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
  $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
  sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
sudo apt-get update

• Install Docker

  sudo apt-get install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
  

• or visit Docker and follow the instructions.

Install Open Webui

• Use this command to install Open Webui

  sudo docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main
  

• Now you can check that Open Webui is installed by opening browser and visiting
  • http://localhost:3000/
  • http://localhost:8080/
• Create a new user and login to Open Webui

• Now you can click on the settings icon and add the Ollama API URL

• Now you can start chatting with your AI model by selecting the model and clicking on the chat icon

Additional Models Installation

• You can click on the settings and click on the models tab
• Then enter the model name and click on the install button

• You can change the model by clicking on the top left corner and selecting the model

More Information

• To stop the Open Webui container, use this command

  sudo docker stop open-webui
  

• To start the Open Webui container, use this command

  sudo docker start open-webui
  

• To remove the Open Webui container, use this command

  sudo docker rm open-webui
  

• To stop wsl2, use this command

  wsl --shutdown
  

• To uninstall Unbuntu, use this command

  wsl --unregister Ubuntu
  

• To uninstall WSL2, use this command

  wsl --uninstall
  

My Links

• GitHub
• Twitter
• LinkedIn