Deploy Deepseek‑R1 with Ollama and Open‑WebUI on a Linux Server

Step 1: Install Ollama

Download and install Ollama on a Linux host: curl -fsSL https://ollama.com/install.sh | sh Edit the systemd service file to expose the service on all interfaces and allow any origin:

vi /etc/systemd/system/ollama.service
# add or modify the following lines
Environment="OLLAMA_HOST=0.0.0.0"
Environment="OLLAMA_ORIGINS=*"

Reload the daemon, restart the service, and verify that port 11434 is listening:

systemctl daemon-reload
systemctl restart ollama
ss -anlp | grep 11434

Open a browser and navigate to http://YOUR_SERVER_IP:11434; the page should display “Ollama is running”.

Step 2: Deploy Deepseek‑R1 model

Pull the desired Deepseek‑R1 model (e.g., the 7B variant) using Ollama: ollama run deepseek-r1:7b Verify that the model has been downloaded: ollama list Start an interactive chat session with the model:

ollama run deepseek-r1

Step 3: Set up a visual interface (Open‑WebUI)

Install Docker CE (example for CentOS 7):

wget http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo
yum install -y docker-ce-20.10.9-3.el7 docker-ce-cli-20.10.9-3.el7 containerd.io
systemctl start docker
docker --version
docker info

Run the Open‑WebUI container, pointing it to the Ollama endpoint:

docker run -d -p 3000:8080 \
  -e OLLAMA_BASE_URL=http://YOUR_SERVER_IP:11434 \
  -v open-webui:/app/backend/data \
  --name open-webui \
  --restart always \
  ghcr.io/open-webui/open-webui:main

Access the UI at http://YOUR_SERVER_IP:3000. The interface allows uploading files to create a private knowledge base for the model.

After completing these steps, Deepseek‑R1 runs on the Linux host and can be accessed through the Open‑WebUI for both chat and knowledge‑base queries.