aibilly_backend_code/RUNNING.md

Running the AI-Detection Project

This project is a FastAPI-based AI application for detection and RAG (Retrieval-Augmented Generation).

Prerequisites

• Python 3.11+ (for local setup)
• Docker and Docker Compose (for containerized setup - Recommended)
• PostgreSQL and Redis (if running locally)

---

🚀 Option 1: Running with Docker (Recommended)

The easiest way to run the project is using Docker Compose, which sets up the application, database, and Redis automatically.

1. Configure Environment Variables: Copy the example environment file and fill in your keys:

   cp .env.example .env
   

   Note: Open .env and provide your OPENAI_API_KEY or ANTHROPIC_API_KEY if using AI features.

2. Start the Services:

   docker-compose up --build
   

3. Access the API:

   • API Documentation (Swagger UI): http://localhost:8000/docs
   • Health Check: http://localhost:8000/health

---

🛠️ Option 2: Running Locally

If you prefer to run the application directly on your machine:

1. Create a Virtual Environment:

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate
   

2. Install Dependencies:

   pip install -r requirements.txt
   

3. Configure Environment Variables: Copy .env.example to .env and update the settings:

   • Set DATABASE_URL to point to your local PostgreSQL instance (e.g., postgresql://user:pass@localhost:5432/dbname).
   • Set REDIS_HOST to localhost.

4. Run the Application:

   uvicorn main:app --host 0.0.0.0 --port 8000 --reload
   

---

📂 Project Structure Highlights

• main.py: Entry point of the FastAPI application.
• src/config/: Configuration management and startup migrations.
• src/services/: Core business logic (RAG, JWT, etc.).
• src/migrations/: Database schema definitions.
• docker-compose.yml: Multi-container orchestration.

🧪 Testing

To run tests, ensure dependencies are installed and run:

pytest