A FastAPI application with endpoints to chat with Google's Gemini AI. Flutter is used to create a cross-platform application to interact with this API.

• Prerequisites
• Quick Start
  • Installation
  • Configuration
  • Managing the Container
• Links
• Flutter Application
• License

• Docker and Docker Compose installed

Download the latest release from GitHub Releases.

Rename .env.example to .env and edit it to configure the server.

• HOST: Server host address (default: localhost)
• PORT: Server port (default: 443)
• API_TOKEN_HASH: Leave blank to auto-generate on first run, or provide your own token hash
• GEMINI_API_KEY: API key from Google AI Studio

# Start the container
docker compose up -d

# Stop the container
docker compose down

# Update to the latest version
docker compose pull && docker compose up -d

# View the logs
docker compose logs -f rpi-ai

Note: You may need to add your user to the Docker group and log out/in for permission changes to take effect:

sudo usermod -aG docker ${USER}

• Access the web application: https://localhost:443
• Server runs at: https://localhost:443/api
• Swagger UI: https://localhost:443/api/docs
• Redoc: https://localhost:443/api/redoc

A Flutter application is created in the /ui directory. This provides a GUI for interacting with the API. See the README.md in the /ui directory for more details.

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