Open WebUI1. Environmental requirements2. Docker construction2.1. Official installation of Docker2.2. Add access permissions3. Open WebUI installation4. Open WebUI and run4.1. Administrator account4.2. Register and log in4.3 User Interface5. Model dialogue5.1. Switch model5.2. Demonstration: LLaVA6. Common Problems6.1. Close Open WebUI6.2. Common ErrorsUnable to start Open WebUIService connection timeout
Demo Environment
Development board: Jetson Orin series motherboard
SSD: 128G
Tutorial Scope
Motherboard Model | Supported |
---|---|
Jetson Orin NX 16GB | √ |
Jetson Orin NX 8GB | √ |
Jetson Orin Nano 8GB | √ |
Jetson Orin Nano 4GB | √ |
Open WebUI is an open source project that aims to provide a simple and easy-to-use user interface (UI) for managing and monitoring open source software and services.
When using Open WebUI, there is a high probability that the dialogue will be unresponsive or timeout. You can try restarting Open WebUI or using the Ollama tool to run the model!
Host and Conda installation of Open WebUI: Node.js >= 20.10, Python = 3.11:
Environment construction method | Difficulty (relatively) |
---|---|
Host | High |
Conda | Medium |
Docker | Low |
Tutorial demonstrates Docker installation of Open WebUI.
If Docker is not installed, you can use the script to install Docker in one click.
xxxxxxxxxx
sudo apt update
xxxxxxxxxx
sudo apt upgrade
Download the get-docker.sh file and save it in the current directory.
xxxxxxxxxx
sudo apt install curl
xxxxxxxxxx
curl -fsSL https://get.docker.com -o get-docker.sh
Run the get-docker.sh script file with sudo privileges.
xxxxxxxxxx
sudo sh get-docker.sh
Add system current user access rights to Docker daemon: You can use Docker commands without using sudo command
xxxxxxxxxx
sudo usermod -aG docker $USER
newgrp docker
For systems with Docker installed, you can directly enter the following command in the terminal: The image is the result of the pull
xxxxxxxxxx
docker pull ghcr.io/open-webui/open-webui:main
Enter the following command in the terminal to start the specified Docker:
xxxxxxxxxx
docker run --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
After successful startup, use the following URL to access the browser:
xxxxxxxxxx
http://localhost:8080/
The same LAN can use the motherboard IP:8080 to access:
xxxxxxxxxx
Assuming the motherboard IP: 192.168.2.105, we can access it through 192.168.2.105:8080
You need to register an account for the first time. This account is an administrator account. You can fill in the information as required!
xxxxxxxxxx
Since all the contents of our mirror have been set up and tested, users can directly log in with our registered account:
Username: yahboom
Email: yahboom@163.com
Password: yahboom
Using Open WebUI for dialogue will be slower than using the Ollama tool directly, and may even cause timeout service connection failure. This is related to the memory of the Jetson motherboard and cannot be avoided!
xxxxxxxxxx
Users with ideas can switch to other Linux environments to build the Ollama tool and Open WebUI tool for dialogue
Click Select a model
to select a specific model for dialogue.
xxxxxxxxxx
The model pulled by ollama will be automatically added to the Open WebUI model option. Refresh the web page and the new model will appear!
The LLaVA case demonstrated requires 8G or even more than 8G to run. Users can use other cases to test the Open WebUI dialogue function!
xxxxxxxxxx
What's in this image?
Close the automatically started Open WebUI.
xxxxxxxxxx
docker ps
xxxxxxxxxx
docker stop [CONTAINER ID] # Example docker stop 5f42ee9cf784
xxxxxxxxxx
docker ps -a
xxxxxxxxxx
docker rm [CONTAINER ID] # Example docker rm 5f42ee9cf784
Clean up all stopped containers:
xxxxxxxxxx
docker container prune
Solution: Close Open WebUI once and restart!
Close Open WebUI once and restart, then ask again or run the model with the Ollama tool to ask questions!