Technology

Deploying Ollama + WebUI on Nebula Block Instance

Nebula Block

— 3 min read
Deploying Ollama + WebUI on Nebula Block Instance

This tutorial will guide you through the process of deploying Ollama with a web-based interface (WebUI) on a Nebula Block instance. By following these steps, you will have a fully operational Ollama service running on a GPU-powered instance, accessible via a web browser.

1. Setting Up a Serverless Instance on Nebula Block

Nebula Block provides a serverless environment that allows you to deploy and manage instances without worrying about the underlying infrastructure. Follow these steps to set up your instance:

1.1 Sign Up & Create an Instance

Create an Account:

Visit Nebula Block and sign up for a new account if you don’t already have one. New users receive initial credits to explore the platform.

Deploy an Instance:

  • Navigate to the Instances section in the left panel.
  • Click on the Deploy button to create a new instance.

1.2 Configure the Instance

GPU Selection:

Choose a GPU instance type based on your model’s requirements. If you plan to run larger models, select a GPU with sufficient memory.

Operating System:

Select Ubuntu Server 22.04 LTS R550 CUDA 12.4 with Docker as the operating system. This ensures compatibility with GPU-accelerated workloads.

SSH Public Key:

Add your SSH public key for secure access to the instance. If you don’t have one, you can generate it using tools like ssh-keygen and then use the “+” button to save it.

Instance Name:

Assign a name to your instance for easy identification.

Deploy:

Once all fields are filled, click Deploy. Ensure your account has sufficient credits to proceed.

2. Accessing the Instance

After deployment, you can view the instance details in the Instances section.

Use the provided Public IP and your SSH key to log into the instance via a terminal:

ssh -i /path/to/your/private_key.pem username@PUBLIC_IP

Replace:

  • /path/to/your/private_key.pem with the actual path to your SSH private key.
  • username with the appropriate username for your instance (e.g., ubuntu for Ubuntu instances).
  • PUBLIC_IP with the Public IP address of your instance.

3. Checking GPU Drivers and Docker Service

Once logged in, verify that the GPU drivers and Docker service are running correctly:

Check GPU Status

nvidia-smi

If the output displays GPU details, the drivers are correctly installed.

Check Docker Status

systemctl status docker

Ensure that the Docker service is active and running.

4. Deploying Ollama with WebUI

We’ll use a pre-built Docker image to deploy Ollama along with a web-based interface.

4.1 Run the following Docker command to start the service:

docker run -dit — name ollama — restart=always — gpus all -p 80:8080 swanchain254/ollama-webui

Explanation of the command:

  • -dit: Runs the container in detached mode with an interactive terminal.
  • — name ollama: Assigns the container the name “ollama”.
  • — restart=always: Ensures the container restarts automatically if it stops.
  • — gpus all: Grants the container access to all available GPUs.
  • -p 80:8080: Maps port 8080 inside the container to port 80 on the server.
  • swanchain254/ollama-webui: Uses the pre-built Docker image.

4.2 Verify the Running Container

To check if the Ollama container is running properly, use:

docker ps

To view logs and ensure the service is running:

docker logs -f ollama

5. Accessing the WebUI

Once the container is running, you can access Ollama’s WebUI by opening a browser and navigating to:

http://PUBLIC_IP

Replace PUBLIC_IP with your instance’s actual public IP address.

On the WebUI, you can download and run models such as:

  • DeepSeek-R1-Distill-Qwen-1.5B
  • Llama 2
  • Mistral

Conclusion

You have successfully deployed Ollama with a WebUI on a Nebula Block instance. The model is now accessible via a web interface, making it easy to interact with and integrate into your applications. Enjoy your AI-powered experience!

Follow Us for the latest updates via our official channels:

Read more

Unlocking Advanced NLP with Nebula Block Embeddings: A Technical Deep Dive

Unlocking Advanced NLP with Nebula Block Embeddings: A Technical Deep Dive

Introduction Nebula Block’s Embeddings Endpoint empowers developers to harness state-of-the-art text representation models for tasks like semantic search, RAG (Retrieval Augmented Generation), and content classification. This article explores its architecture, integration workflows, and practical applications, with a focus on bridging the gap between research and production. What Are Embeddings?

By Nebula Block