NEXUS Restaurant - Full-Stack AI Application

A modern full-stack web application for restaurant management powered by AI. Converted from a terminal-based assistant to a production-ready web application.

Features

• AI Chat Interface: Conversational interface powered by LangChain + GPT-4 with streaming responses
• Table Reservations: Book tables with real-time availability checking
• Menu Browsing: View and search menu items by category with dietary filters
• Order Management: Place orders for delivery/pickup and track status
• JWT Authentication: Secure user authentication system
• Modern Premium UI: Dark theme with glassmorphism effects

Project Structure

nexus/
├── backend/                     # FastAPI Backend
│   ├── app/
│   │   ├── api/routes/         # API endpoints
│   │   │   ├── auth.py         # Authentication routes
│   │   │   ├── tables.py       # Table management
│   │   │   ├── reservations.py # Reservation endpoints
│   │   │   ├── orders.py       # Order & Menu endpoints
│   │   │   └── chat.py         # AI chat with streaming
│   │   ├── core/               # Config & Security (JWT)
│   │   ├── db/                 # Database session
│   │   ├── models/             # SQLAlchemy ORM models
│   │   ├── schemas/            # Pydantic request/response schemas
│   │   ├── services/           # Business logic layer
│   │   └── main.py             # FastAPI application entry
│   ├── requirements.txt
│   └── .env.example
├── frontend/                    # Next.js Frontend
│   ├── app/
│   │   ├── chat/               # AI Chat page with streaming
│   │   ├── menu/               # Menu browsing
│   │   ├── reservations/       # Reservation management
│   │   ├── orders/             # Order tracking
│   │   └── login/              # Authentication
│   ├── components/              # Reusable UI components
│   └── lib/                     # API client & state management
└── README.md

Quick Start

Backend Setup

cd backend
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate
pip install -r requirements.txt

# Configure environment
cp .env.example .env
# Edit .env and add your OPENAI_API_KEY

# Run server
uvicorn app.main:app --reload --port 8000

Frontend Setup

cd frontend
npm install
npm run dev

Access the app at http://localhost:3000

API Endpoints

Authentication

Method	Endpoint	Description
POST	/api/v1/auth/register	Register new user
POST	/api/v1/auth/login	Login (returns JWT)
GET	/api/v1/auth/me	Get current user

Menu

Method	Endpoint	Description
GET	/api/v1/menu	List all menu items
GET	/api/v1/menu/categories	Get all categories
GET	/api/v1/menu/search?q=	Search items

Reservations

Method	Endpoint	Description
GET	/api/v1/reservations	List user reservations
POST	/api/v1/reservations	Create reservation
PATCH	/api/v1/reservations/{id}	Update reservation
POST	/api/v1/reservations/{id}/cancel	Cancel reservation

Orders

Method	Endpoint	Description
GET	/api/v1/orders	List user orders
POST	/api/v1/orders	Create order
POST	/api/v1/orders/{id}/cancel	Cancel order

Chat (Streaming)

Method	Endpoint	Description
POST	/api/v1/chat/message	Send message (non-streaming)
POST	/api/v1/chat/stream	Send message (SSE streaming)

Tech Stack

Backend

• FastAPI - Modern Python web framework
• SQLAlchemy - ORM with SQLite database
• Pydantic - Data validation
• python-jose - JWT token handling
• LangChain + OpenAI - AI/LLM integration

Frontend

• Next.js 14 - React framework
• TailwindCSS - Utility-first styling
• Zustand - State management
• Lucide React - Icon library

Database Schema

Users

• id, email, username, hashed_password, full_name, phone, is_admin, created_at

Tables

• id, table_number, capacity, status, description

Reservations

• id, user_id, table_id, party_size, reservation_date, status, event_id, created_at

MenuItems

• id, name, description, category, price, is_available, is_vegetarian, is_vegan, is_gluten_free

Orders

• id, user_id, order_number, status, order_type, subtotal, delivery_fee, tax, total, payment_status

OrderItems

• id, order_id, menu_item_id, quantity, unit_price, subtotal

ChatSessions & ChatMessages

• Session tracking and message history

Original Terminal Version

This project was converted from a terminal-based AI assistant. The original main.py and mcp.py files are preserved in the root directory for reference.

License

MIT