AI-powered registration system built with FastAPI, React, LangGraph, DSPy, Guardrails AI, and MLflow. The system guides users through a structured conversation, collecting registration details while leveraging AI validation to ensure input accuracy.

/project-root
│── /app          # FastAPI backend
│── /app/docker-compose.yml  # Docker setup
│── /frontend     # React frontend
│── .venv         # Python virtual environment
│── README.md     # This file

• Python 3.9+
• Poetry or pip (for dependency management)
• SQLite

1. Navigate to the backend directory:

   cd app

2. Activate the Python virtual environment:

   source ../.venv/bin/activate  # macOS/Linux
   ../.venv/Scripts/activate     # Windows (PowerShell)

3. Install dependencies:

   pip install -r requirements.txt

4. Start the FastAPI server:

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

5. Access the API docs in the browser:

   • Open http://localhost:8000/docs (Swagger UI)
   • Open http://localhost:8000/redoc (ReDoc)

• Docker & Docker Compose installed

1. Navigate to the project root:

   cd /path/to/project-root/app

2. Run Docker Compose:

   docker-compose up --build

3. Check if the backend is running:

   docker logs -f <backend-container-name>

4. Stop the containers when done:

   docker-compose down

• Node.js 16+
• Yarn or npm

1. Navigate to the frontend directory:

   cd frontend

2. Install dependencies:

   yarn install  # or npm install

3. Start the development server:

   yarn dev  # or npm run dev

4. Open the frontend in your browser:

   • http://localhost:5173

Create a .env file in both /app and /frontend and configure as needed:

OPENAI_API_KEY=your-api-key
MLFLOW_ENABLED=True
MLFLOW_EXPERIMENT_NAME=your-experiment
DATABASE_URL=sqlite:///./database.db  # or Snowflake credentials

VITE_API_URL=http://localhost:8000