and create an account. Once you've signed up, log into your account.
Follow the account setup process and provide the necessary details and information.
Navigate to the menu on the left side. Select the GPU Nodes option, create a GPU Node in the Dashboard, click the Create GPU Node button, and create your first Virtual Machine deployment.
Step 3: Select a Model, Region, and Storage
In the "GPU Nodes" tab, select a GPU Model and Storage according to your needs and the geographical region where you want to launch your model.
.
After choosing the image, click the 'Create' button, and your Virtual Machine will be deployed.
Step 7: Connect to GPUs using SSH
NodeShift GPUs can be connected to and controlled through a terminal using the SSH key provided during GPU creation.
Once your GPU Node deployment is successfully created and has reached the 'RUNNING' status, you can navigate to the page of your GPU Deployment Instance. Then, click the 'Connect' button in the top right corner.
Now open your terminal and paste the proxy SSH IP or direct SSH IP.
Step 8: Install Pip and Python
Run the following command to update the package List:
sudo apt update
Run the following command to update the package list again:
sudo apt update
Run the following command to download and install pip specifically for Python 3.11:
curl -sS https://bootstrap.pypa.io/get-pip.py | sudo python3.11
python --version
pip --version
Ensure Python 3.11 and Pip 24.0 is installed, as it’s compatible with Open WebUI.
Step 10: Install Open WebUI
Run the following command to install Open WebUI:
pip install open-webui
If this error occurs, it may be due to an outdated version of SQLite3 on your system, which is required by the chromadb package used within Open WebUI. Here’s how you can upgrade SQLite3 to resolve this:
Steps to Upgrade SQLite3
Install the Latest SQLite3 from Source:
First, download, compile, and install the latest SQLite version from the official source.
Run the following command to download version 3.47.0:
wget https://www.sqlite.org/2024/sqlite-autoconf-3470000.tar.gz
Extract, Compile, and Install SQLite
If the file is present, proceed with these commands:
tar xzf sqlite-autoconf-3470000.tar.gz
cd sqlite-autoconf-3470000
./configure --prefix=/usr/local
make
sudo make install
Verify and Link SQLite Library Path
The newer version might not be in the default library path. Let's ensure it is correctly linked.
Update the Library Path
Run the following command to add the new SQLite location to your library path:
export LD_LIBRARY_PATH=/usr/local/lib:$LD_LIBRARY_PATH
Run the following command to Create a symbolic link to the new SQLite library:
sudo ln -sf /usr/local/lib/libsqlite3.so.0 /usr/lib/libsqlite3.so.0
or
Step 13: Logging In and Creating an Account
After installation, access Open WebUI by navigating to in your web browser.
Creating an Account:Click on the SignUp option on the login page.
Fill in your details:
- Username: Choose a unique username.
- Email: You can use any email address since all data is stored locally.
- Password: Create a secure password.
After submitting, your account will be marked as pending until approved by an administrator.
Admin Approval:The first account created during the installation has administrator privileges. Log in with this account to approve new user registrations.
Navigate to the users section in the admin panel to change the status of pending accounts to active.
Step 14: Additional Settings
Once logged in as an administrator, you can configure various settings:
User Management:
- In the admin panel, you can manage user roles (admin or regular user) and approve or deny pending accounts.
Privacy Settings:
- All data, including login details and user information, is stored locally to ensure privacy and security.
Step 17: Adding OpenAI API Keys
To integrate OpenAI services:
- In the admin panel, navigate to the connections tab.
- Locate the section for adding API keys.
- Enter your OpenAI API key in the designated field.
- Save your changes to establish a connection with OpenAI services.
Step 19: Accessing the Chat Interface
After successfully adding your OpenAI or ollama API keys and loading the models, you can begin interacting with them through Open WebUI.
From the main dashboard of Open WebUI, locate and click on the chat or models tab. This will take you to the interface where you can interact with the loaded models.
SOCIAL SHARE CARD GENERATOR