Open WebUI: ChatGPT-Style Interface for Ollama

Ollama's terminal interface is functional but basic. Open WebUI gives you a full browser-based chat interface — conversation history, model switching, document upload, system prompts, and more. It takes about 5 minutes to set up.

Prerequisites

• Ollama installed and running (Windows guide / Linux guide)
• Docker Desktop (Windows/macOS) or Docker Engine (Linux)
• At least one model pulled: ollama pull llama3.1:8b

Install Docker

Windows/macOS: Download Docker Desktop from docker.com and run the installer.

Linux (Ubuntu):

curl -fsSL https://get.docker.com | sh
sudo usermod -aG docker $USER
# Log out and back in

Install Open WebUI

Windows (PowerShell):

docker run -d `
  -p 3000:8080 `
  --add-host=host.docker.internal:host-gateway `
  -v open-webui:/app/backend/data `
  --name open-webui `
  --restart always `
  ghcr.io/open-webui/open-webui:main

Linux/macOS:

docker run -d \
  -p 3000:8080 \
  --add-host=host.docker.internal:host-gateway \
  -v open-webui:/app/backend/data \
  --name open-webui \
  --restart always \
  ghcr.io/open-webui/open-webui:main

Wait about 30 seconds for the container to start, then open:

http://localhost:3000

First Setup

1. Click Sign up and create an admin account (local only — not sent anywhere)
2. The first account automatically becomes admin
3. Select your model from the dropdown at the top
4. Start chatting

Key Features

Model switching — dropdown at the top of any conversation lets you switch models mid-chat or compare responses from multiple models side by side.

System prompts — click the settings icon in a conversation to set a persistent system prompt. Use the System Prompt Library for ready-made prompts.

Document upload — drag and drop PDFs, text files, or code into the chat. The model reads the document and answers questions about it.

Conversation history — all conversations are saved locally in the Docker volume. They persist across restarts.

Model management — pull new Ollama models directly from the Open WebUI interface without using the terminal.

Connecting to Ollama

Open WebUI auto-detects Ollama at http://host.docker.internal:11434. If it doesn't connect:

1. Go to Settings → Admin → Connections
2. Set Ollama API URL to http://host.docker.internal:11434
3. Click Save

If you're on Linux and host.docker.internal doesn't resolve:

# Stop and remove existing container
docker stop open-webui && docker rm open-webui

# Re-run with host network mode
docker run -d \
  --network=host \
  -v open-webui:/app/backend/data \
  --name open-webui \
  --restart always \
  -e OLLAMA_BASE_URL=http://127.0.0.1:11434 \
  ghcr.io/open-webui/open-webui:main

Then access at http://localhost:8080.

Updating Open WebUI

docker pull ghcr.io/open-webui/open-webui:main
docker stop open-webui
docker rm open-webui
# Re-run the original docker run command

Your conversations and settings are stored in the open-webui volume and survive the update.

Useful Docker Commands

# Check if running
docker ps

# View logs
docker logs open-webui

# Restart
docker restart open-webui

# Stop
docker stop open-webui

# Start again
docker start open-webui

Network Access (access from other devices)

To access Open WebUI from your phone or another computer on your network:

1. Find your machine's local IP: ipconfig (Windows) or ip addr (Linux)
2. Access from other devices at http://YOUR_LOCAL_IP:3000

Note: Open WebUI has no authentication by default beyond the initial signup. Only expose it on trusted networks.

Next Steps

• Ollama API Guide — connect apps directly to Ollama
• Modelfile Guide — create custom model personalities
• Abliterated Models Guide — run uncensored models