RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
  1. >
  2. Home
  3. /Learn
  4. /Courses
  5. /Local AI on Windows
  6. /Ch. 14
Local AI on Windows

14. Open WebUI on Windows

Chapter 14 of 15 · 20 min
KEY INSIGHT

Open WebUI running inside Docker connects to Ollama through `host.docker.internal`, which routes to the Windows host. If Ollama runs natively on Windows, the connection succeeds without additional configuration.

Open WebUI is a web-based chat interface for Ollama. It runs as a Docker container and provides a web UI with conversation history, model switching, and RAG capabilities.

Install Open WebUI:

docker run -d \
  -p 3000:8080 \
  -v open-webui:/app/backend/data \
  -e OLLAMA_BASE_URL="http://host.docker.internal:11434" \
  --name open-webui \
  --restart unless-stopped \
  ghcr.io/open-webui/open-webui:main

The key variable is OLLAMA_BASE_URL. host.docker.internal resolves to the Windows host's IP from inside the container. If Ollama runs natively on Windows at port 11434, this URL routes correctly. If Ollama runs inside a separate Docker container, replace host.docker.internal with the container name or the WSL2 IP address.

Access the UI at http://localhost:3000. On first launch, create an admin account. The interface shows available Ollama models in the model selector dropdown.

Common failure: The UI loads but models do not appear in the dropdown. This means Open WebUI cannot reach Ollama. Check the OLLAMA_BASE_URL value. Inside WSL2, verify the URL resolves:

curl http://host.docker.internal:11434/api/tags

If this returns a JSON list of models, the connection is fine. If it times out, Ollama is not accessible from Docker's network. Fix by restarting Ollama with explicit host binding:

# For Ollama inside WSL2 (native install)
OLLAMA_HOST=0.0.0.0 ollama serve

# For Ollama Docker container, add -p 11434:11434 to the docker run command

Reverse proxy with authentication:

To add HTTPS and basic auth in front of Open WebUI, use nginx-proxy with a docker-compose file:

version: '3.8'
services:
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    ports:
      - "3000:8080"
    environment:
      - OLLAMA_BASE_URL=http://host.docker.internal:11434
    volumes:
      - open-webui-data:/app/backend/data
    restart: unless-stopped

  nginx-proxy:
    image: nginx:alpine
    ports:
      - "443:443"
    volumes:
      - ./nginx.conf:/etc/nginx/nginx.conf:ro
      - ./htpasswd:/etc/nginx/.htpasswd:ro
    depends_on:
      - open-webui
    restart: unless-stopped

volumes:
  open-webui-data:
EXERCISE

Start Open WebUI, create an admin account, select a model, and have a five-message conversation. Then verify the conversation is stored by running docker exec open-webui ls /app/backend/data/backend/models.

← Chapter 13
Performance Optimization
Chapter 15 →
Windows AI Tools Ecosystem