🤖 Makoto AI Operations Analyst

An advanced AI-powered warehouse operations analyst system featuring real-time IoT sensor monitoring, intelligent data analysis, and conversational AI interface.

🌟 Features

• 🏭 Real-time IoT Simulation: 12 warehouse devices generating realistic sensor data
• 🤖 AI-Powered Analysis: Intelligent warehouse operations insights and recommendations
• 📊 RESTful API: Professional-grade .NET 8 Web API with comprehensive endpoints
• 💾 Database Integration: Entity Framework Core with in-memory database
• 📝 Enterprise Logging: Structured logging with Serilog
• 🔄 Real-time Data Flow: Live sensor data streaming and processing
• 🌐 CORS Enabled: Ready for frontend integration
• 📚 API Documentation: Interactive Swagger/OpenAPI documentation

🏗️ Architecture

makto/
├── Backend/MakotoAPI/          # .NET 8 Web API
│   ├── Controllers/            # API endpoints
│   ├── Models/                 # Data models
│   ├── Services/               # Business logic
│   └── Data/                   # Database context
├── IoTSimulator/               # Python IoT simulator
├── Database/                   # Database scripts
└── docs/                       # Documentation

🚀 Quick Start

Prerequisites

• .NET 8 SDK
• Python 3.11+
• Git

1. Clone the Repository

git clone https://github.com/sivaadityacoder/Japanese-English-AI-Chatbot-.git
cd makto

2. Start the Backend API

cd Backend/MakotoAPI
dotnet restore
dotnet run

The API will be available at http://localhost:5000

3. Start the IoT Simulator

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

4. Access the System

• API Documentation: http://localhost:5000/swagger
• Health Check: http://localhost:5000/api/sensors/status
• AI Chat: POST to http://localhost:5000/api/makoto/ask

📡 API Endpoints

Sensor Data Management

• POST /api/sensors/data - Receive IoT sensor data
• GET /api/sensors/latest - Get latest sensor readings
• GET /api/sensors/device/{deviceId} - Get specific device data

AI Operations Analyst

• POST /api/makoto/ask - Ask questions about warehouse operations
• GET /api/makoto/insights - Get operational insights

🔧 IoT Devices Simulated

Device Type	Count	Purpose
Cold Storage (COLD-01, 02, 03)	3	Temperature monitoring
Freezer (FREEZER-01)	1	Frozen goods monitoring
Inventory Shelves (SHELF-01-04)	4	Stock level tracking
Loading Docks (DOCK-01, 02)	2	Activity monitoring
HVAC System (HVAC-01)	1	Climate control
Security System (SECURITY-01)	1	Access monitoring

💬 AI Chat Examples

# Check inventory levels
curl -X POST "http://localhost:5000/api/makoto/ask" \
-H "Content-Type: application/json" \
-d '{"question": "How many items are on shelf 3?"}'

# Temperature analysis
curl -X POST "http://localhost:5000/api/makoto/ask" \
-H "Content-Type: application/json" \
-d '{"question": "Is the warehouse temperature normal?"}'

# Operational insights
curl -X POST "http://localhost:5000/api/makoto/ask" \
-H "Content-Type: application/json" \
-d '{"question": "Give me a summary of warehouse operations"}'

🛠️ Technology Stack

Backend (.NET 8)

• ASP.NET Core - Web API framework
• Entity Framework Core - Database ORM
• Serilog - Structured logging
• Swagger/OpenAPI - API documentation

IoT Simulator (Python)

• aiohttp - Async HTTP client
• asyncio - Asynchronous programming
• datetime - Time-based data generation

Database

• In-Memory Database - Development/Demo
• Entity Framework Core - Data access layer

📊 Data Flow

1. IoT Devices generate realistic sensor data every 5 seconds
2. Python Simulator sends data to API endpoints
3. Backend API processes and stores data in database
4. AI Service analyzes data for intelligent insights
5. Chat Interface provides conversational access to data

🎯 Use Cases

• Warehouse Management: Monitor inventory, temperature, and security
• Predictive Maintenance: Analyze sensor trends for equipment health
• Operations Optimization: AI-powered insights for efficiency improvements
• Real-time Monitoring: Live dashboard capabilities for warehouse status

🔮 Future Enhancements

• React.js frontend dashboard
• Real OpenAI/GPT integration
• PostgreSQL database support
• Docker containerization
• Kubernetes deployment
• Machine learning predictions
• Mobile app interface

📝 License

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

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

👨‍💻 Developer

Siva Aditya

• GitHub: @sivaadityacoder
• Portfolio: [Your Portfolio Link]

🌟 Acknowledgments

• Built for Hitachi job application demonstration
• Inspired by Industry 4.0 and IoT warehouse solutions
• Designed with enterprise-grade architecture patterns

---

⭐ Star this repository if you found it helpful!

Architecture

Phase 1: Smart Warehouse Foundation

• IoT Simulator: Python script generating realistic warehouse sensor data
• Backend API: C# .NET Core with RESTful endpoints
• Database: PostgreSQL for real-time data storage
• Data Flow: IoT → API → Database

Phase 2: AI Brain Integration

• RAG System: Retrieval-Augmented Generation for truthful responses
• LLM Integration: Google Gemini or OpenAI GPT-4 API
• Chat Interface: React-based conversational UI
• Query Engine: Natural language to SQL translation

Technology Stack

• Backend: C# .NET 8, Entity Framework Core
• Database: PostgreSQL
• Frontend: React 18, TypeScript, Tailwind CSS
• IoT Simulation: Python 3.11+
• AI/ML: Google Gemini API / OpenAI GPT-4
• DevOps: Docker, Docker Compose

Features

Core Capabilities

• Real-time IoT data collection and storage
• Natural language query processing
• Contextual AI responses based on live data
• Multi-device warehouse monitoring
• Temperature, humidity, and inventory tracking

AI Features

• Conversational analytics interface
• Complex query understanding
• Data-driven insights and warnings
• Historical trend analysis
• Predictive maintenance alerts

Getting Started

Prerequisites

• .NET 8 SDK
• Node.js 18+
• Python 3.11+
• PostgreSQL 15+
• Docker (optional)

Quick Start

1. Clone the repository
2. Set up the database: cd Backend && dotnet ef database update
3. Start the IoT simulator: cd IoTSimulator && python warehouse_simulator.py
4. Launch the backend: cd Backend && dotnet run
5. Start the frontend: cd Frontend && npm start

Project Structure

makto/
├── Backend/                 # C# .NET API
├── Frontend/               # React Chat Interface  
├── IoTSimulator/          # Python Sensor Simulation
├── Database/              # SQL Scripts
├── Docker/                # Container Configuration
└── Documentation/         # Technical Docs

Demo Scenarios

Ask Makoto questions like:

• "How many items are on shelf 3 and is the temperature normal?"
• "Which areas have temperature alerts today?"
• "Show me inventory levels for the cold storage section"
• "What's the humidity trend in warehouse zone A?"

Innovation Highlights

• Beyond Traditional Dashboards: Conversational analytics interface
• RAG Implementation: Ensures truthful, data-backed responses
• Real-time Integration: Live IoT data processing
• Scalable Architecture: Enterprise-ready design patterns
• AI-First Approach: Natural language as primary interface

This project demonstrates the future of Digital Transformation - making complex data accessible through intuitive AI interactions.