Ollama WebUI

Ollama WebUI is a minimalist, easy-to-use web interface built with FastAPI and Vue.js, designed to interact with local AI models via Ollama.

Features

• Simple, responsive web interface.
• System prompts (custom instructions) to define AI behavior.
• FastAPI backend + Vue.js frontend.
• Seamless integration with local Ollama models.
• Docker support for quick deployment.

Installation

1. Clone the repository

git clone https://github.com/wilmerm/ollama-webui.git
cd ollama-webui

2. Backend setup

pip install -r requirements.txt

3. Frontend setup

cd frontend/vue-app
npm install
npm run build

4. Start the application

./start.sh

Running with Docker

docker compose build
docker compose up -d

Environment Variables (.env)

# Required:
DEFAULT_MODEL=llama3.1:latest     # See more models: https://ollama.com/library/
OLLAMA_BASE_URL=http://127.0.0.1:11434

# Optional:
DEFAULT_TIMEOUT=30                # Increase if model is heavy or system resources are limited.
DEFAULT_TEMPERATURE=0.5           # Controls creativity of AI responses.
GUNICORN_WORKERS=1                # Number of Gunicorn workers.
VITE_SERVER_BASE_URL=http://127.0.0.1:7000  # Only set if backend runs on a different URL/port.

Ollama Configuration

To allow the backend inside Docker to connect to Ollama, edit the Ollama systemd service file and add:

[Service]
Environment="OLLAMA_HOST=0.0.0.0"

Installing Ollama

Download from the official website: ➡️ https://ollama.com/download

Or install via shell:

curl -fsSL https://ollama.com/install.sh | sh

Useful Ollama Commands

Download a model:

ollama pull llama3.1:latest

Run a model:

ollama run llama3.1:latest

Note: You don’t need to run the model manually when using Ollama WebUI. The app will automatically start the model specified in .env if it’s not already running.

---

System Prompts (Custom Instructions)

Ollama WebUI supports system prompts to customize AI behavior. Click the "⚙️ Instrucciones del Sistema" section above the chat to:

• Define custom AI personality and behavior
• Set context that persists throughout the conversation
• Use preset examples or create your own instructions
• Enable/disable as needed during conversations

Example system prompts:

• "You are an IT security expert. Always answer from a cybersecurity perspective."
• "Always respond in Spanish and help me learn the language."
• "You are a helpful assistant who answers concisely and clearly."

For detailed documentation, see docs/SYSTEM_PROMPTS.md.

---

Contributing

Contributions are welcome!

1. Fork the repository.
2. Create a new branch (git checkout -b feature/your-feature).
3. Commit your changes (git commit -m 'Add feature').
4. Push to your fork (git push origin feature/your-feature).
5. Open a Pull Request.

License

This project is licensed under the MIT License — see the LICENSE file for details.

Credits

Wilmer Martinez Author & Maintainer