Unleash the Power of AI: Installing Deepseek on Ollama with OpenWebUI

Deepseek is a cutting-edge AI model renowned for its prowess in natural language processing. Deploying it efficiently is now easier than ever with Ollama, especially when using the "Ubuntu 24.04 with Ollama" template. This template comes pre-installed with both Ollama and OpenWebUI, providing a user-friendly web interface for managing and interacting with AI models like Deepseek.

This guide provides a step-by-step walkthrough on how to install and run the Deepseek model on your Virtual Private Server (VPS) through OpenWebUI, eliminating the need for complex command-line configurations.

Note: If you don't already have a VPS, consider exploring LLM VPS hosting options to get started.

Accessing Ollama via OpenWebUI

First, you'll need to access the OpenWebUI interface.

1. Open your preferred web browser.
2. Navigate to the following address: https://[your-vps-ip]:8080
3. Replace [your-vps-ip] with the actual IP address of your VPS. If you are unsure how to find this, see how to find your VPS IP address.

Installing the Deepseek Model through OpenWebUI

Once you've successfully logged into OpenWebUI, follow these steps to install Deepseek:

1. Navigate to the Admin Panel: From the OpenWebUI dashboard, find and click on the "Admin Panel" section.
2. Access Settings and Models: Within the Admin Panel, select "Settings" and then "Models". This will display a list of all currently installed models on your instance.
3. Manage Models: Look for and click the "Manage Models" button, typically located in the top right corner of the screen.
4. Enter Model Tag: A new window will appear. In this window, enter the tag for the Deepseek model you wish to install.
5. Download Deepseek: After entering the model tag, click the "Download" button to initiate the installation process. OpenWebUI will automatically handle the download and setup of the Deepseek model, making it ready for use.

Selecting Deepseek as the Active Model

With Deepseek successfully installed, you need to select it as the active model for your AI interactions:

1. Go to the New Chat Page: Navigate to the section in OpenWebUI where you can start a new chat or conversation.
2. Choose Deepseek: In the list of available models, locate "Deepseek" and select it.
3. Set as Default: Click the "Set as Default" button next to the Deepseek model. This ensures that all subsequent requests and conversations will be processed using the Deepseek AI.

By following these instructions, you can easily install and configure the Deepseek model on your VPS using the intuitive OpenWebUI, entirely bypassing the need for direct SSH access or complicated command-line operations. This streamlined setup enables you to leverage the power of Deepseek through a user-friendly web interface, opening up a world of possibilities for natural language processing tasks.

Further Reading

• How to use the Ollama VPS template

This comprehensive guide empowers you to quickly integrate and utilize the Deepseek AI model within your projects, enhancing your capabilities in natural language understanding and generation.