Ollama + WebUI

Ollama with Open WebUI is a ready-to-use solution for local and cloud deployment of modern language models with a user-friendly web UI. The product includes fully configured Docker containers:

• Ollama: Platform for downloading, running, and managing open-source LLMs on your own hardware without relying on cloud services.
• Open WebUI: Extensible and user-friendly web interface for working with models that supports Ollama and compatible APIs.

When installing the product, you need to specify the model to preload, e.g., deepseek‑r1:8b. Additionally, you can download any other models from the Ollama catalog, both during product installation and while using it.

Benefits

• Seamless deployment through Marketplace.
• Support for various LLMs in one interface.
• Offline mode and full data control.
• User-friendly web UI for working with models.

1. Get an SSH key pair for connection to a virtual machine (VM).

2. Create a service account without a role.

3. Create a VM from a public image:

   1. Under Boot disk image, navigate to the Marketplace tab and select Ollama + WebUI.

   2. Under Product configuration, specify a model name from the Ollama catalog, e.g., deepseek-r1:8b.

   3. Under Network settings, make sure the selected security group allows inbound traffic on port TCP/22.

   4. Under Access:

      • Enter the username in the Login field.
      • Paste the contents of the public SSH key file in the SSH key field.

   5. Under Additional, select the service account you created earlier.

   6. Click Create VM and wait for the deployment process to complete.

4. To connect to the web UI, create an SSH tunnel:

   ssh -L 8080:localhost:8080 <username>@<VM_public_IP_address>
   

Ollama WebUI will be available at http://localhost:8080 after loading the model selected during installation. This may a few minutes.

• Text generation: From stories and articles to posts and descriptions.
• Summarization: Brief summary of long documents, articles, or reports.
• Data analysis: Extracting key insights and identifying patterns.
• Programming assistance: Code examples, algorithm explanations, and bug fixing.
• Translation and language work: Translating text, adapting style, and improving phrasing.
• Productivity assistant: Creating notes, plans, ideas, and drafts.

Yandex Cloud technical support is available 24/7. The types of requests you can submit and the relevant response times depend on your pricing plan. You can switch to the paid support plan in the management console. You can learn more about the technical support terms and conditions here.