DeepSeek V4 Pro in OpenWebUI on BigLinux laptop

Estimated reading time at 200 wpm: 2 minutes

Previously, I showed the setup for Windows 11. As my laptop is fully run by BigLinux it was important to setup there as well. This is running well. For long form text-based analyses. DSV4Pro is the one. See: DSV4 Pro on W11.

Step 1: Update your system

sudo pacman -Syu

Step 2: Install Docker and Docker Compose

sudo pacman -S docker docker-compose

Step 3: Enable and start Docker service

sudo systemctl enable --now docker

Add your user to the docker group (so you don’t need sudo every time):

sudo usermod -aG docker $USER

Log out and log back in (or reboot) for the group change to take effect.

Step 4: Create a folder for OpenWebUI

mkdir -p ~/openwebui && cd ~/openwebui

Step 5: Create the docker-compose.yml file

Run this command to create the file:

cat > docker-compose.yml << 'EOF'
version: '3.8'
​
services:
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    restart: unless-stopped
    ports:
      - "3000:8080"
    volumes:
      - open-webui:/app/backend/data
    environment:
      - OLLAMA_BASE_URL=http://host.docker.internal:11434   # Only needed if you also run local models
​
volumes:
  open-webui:
EOF

Step 6: Start OpenWebUI

docker compose up -d

Step 7: Access OpenWebUI

Open your browser and go to:

http://localhost:3000

You should see the OpenWebUI login/create account screen.

Step 8: Add DeepSeek V4 Pro (API)

1. Log in / create your account.
2. Go to Settings → Connections → OpenAI API.
3. Add a new connection:
   • API Base URL: https://api.deepseek.com/v1
   • API Key: Paste your DeepSeek API key
4. Save.
5. Go to Workspace → Models and add/select deepseek-v4-pro.

Step 9: Create Workspace + Link Knowledge Base (Important)

This is the step we missed last time:

1. Go to Workspace → create or enter your Workspace.
2. Go to Models tab → edit your model (DSV4(KNS) or whichever name you use).
3. In the Knowledge section, click Select Knowledge and choose your Knowledge Base (KNS-TAE).
4. Save.

Quick Commands Summary (for reference)