# AI

A multi-modal AI web application. Users can choose between different AI models for text generation, text-to-image, text-to-video, and image-to-video generation, powered by [openrouter.ai](https://openrouter.ai).

## Components

| Component | Technology        | Description                                              |
| --------- | ----------------- | -------------------------------------------------------- |
| Backend   | FastAPI + uvicorn | REST API for auth, user management, and AI generation    |
| Database  | DuckDB            | Lightweight embedded storage for users and session data  |
| Frontend  | Flask + Jinja2    | Server-rendered UI served at <https://ai.allucanget.biz> |

## Getting Started

### Prerequisites

- Python 3.11+
- An [openrouter.ai](https://openrouter.ai) API key

### Setup

```bash
# Clone the repo
git clone https://git.allucanget.biz/allucanget/ai.allucanget.biz.git
cd ai.allucanget.biz

# Create and activate virtual environment
python -m venv .venv
# Windows
.venv\Scripts\activate
# Linux/macOS
source .venv/bin/activate

# Install dependencies
pip install -r requirements.txt

# Copy and fill in environment variables
cp .env.example .env
```

### Running the backend

```bash
cd backend
uvicorn app.main:app --reload --port 12000
```

### Running the frontend

```bash
cd frontend
flask --app app.main run --port 12001
```

### Running tests

```bash
pytest
```

## Project Structure

```txt
backend/          FastAPI backend
  app/
    routers/      API route handlers
    services/     Business logic
    models/       Pydantic models
  tests/
frontend/         Flask frontend
  app/
    templates/    Jinja2 HTML templates
    static/       CSS, JS, images
  tests/
data/             DuckDB database files (gitignored)
docs/             Architecture documentation
```

## Documentation

For the full architecture documentation see [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md), which links to all 12 arc42 sections.