🎓 Smart Roadmap Builder

AI-powered personalized learning roadmaps for college students with Google Calendar integration

🌟 Features

🌐 Complete Web Interface

• Interactive Form: Beautiful, responsive web interface for user input
• Real-time Validation: Instant feedback on form inputs with smart suggestions
• Visual Results: Stunning timeline view of your personalized learning roadmap
• Export Options: Download as Excel, PDF, or Calendar (.ics) files
• Mobile Responsive: Works perfectly on all devices and screen sizes

🤖 AI-Powered Generation

• Multi-Domain Learning Paths: Data Structures, AWS Cloud, Data Science, NLP, and AI
• Academic Year Support: Tailored content for 1st, 2nd, 3rd, and 4th year students
• Amazon Nova Micro Integration: Uses AWS Bedrock's latest model for intelligent content generation
• Progressive Difficulty: Tasks automatically scale from Beginner → Intermediate → Advanced
• Personalized Scheduling: Adapts to your weekly study hours and academic level

🔒 Privacy & Integration

• Google Calendar Integration: Seamless OAuth 2.0 integration with automatic event creation
• Privacy-First Design: In-memory processing without data persistence
• Secure Credentials: Comprehensive .gitignore for sensitive information
• Multi-Agent Architecture: Specialized agents for profile collection, roadmap generation, and calendar integration

🚀 Quick Start

Option 1: Simplified Version (Recommended for Demo)

Works immediately without any external dependencies!

# Clone the repository
git clone https://github.com/logesh4v/Pathway.git
cd Pathway/smart-roadmap-builder

# Install basic dependencies
pip install fastapi uvicorn jinja2 python-multipart

# Run the simplified web application
python run_web_simple.py

# Open your browser
# Go to: http://localhost:8000

Option 2: Full Version (with AI & Calendar Integration)

Requires AWS Bedrock and Google Calendar API setup

# Install all dependencies
pip install -r requirements.txt

# Configure credentials (see Setup Guide below)
cp .env.example .env
# Edit .env with your API credentials

# Run the full web application
python run_web.py

# Open your browser
# Go to: http://localhost:8000

📖 Complete Setup Guide

🔧 Prerequisites

• Python 3.9+
• Internet connection for API access

🌐 Web Interface Setup

1. Basic Version (No external APIs needed):

   pip install fastapi uvicorn jinja2 python-multipart
   python run_web_simple.py

2. Full Version (With AI and Calendar):

   pip install -r requirements.txt
   # Configure APIs (see below)
   python run_web.py

☁️ AWS Bedrock Setup (Optional - for AI generation)

1. Create AWS Account and enable Bedrock
2. Get AWS credentials:

   export AWS_ACCESS_KEY_ID=your_access_key
   export AWS_SECRET_ACCESS_KEY=your_secret_key
   export AWS_REGION=us-east-1

3. Enable Amazon Nova Micro model in Bedrock console

📅 Google Calendar Setup (Optional - for calendar integration)

1. Go to Google Cloud Console
2. Create project and enable Google Calendar API
3. Create OAuth 2.0 credentials
4. Set environment variables:

   export GOOGLE_CLIENT_ID=your_client_id
   export GOOGLE_CLIENT_SECRET=your_client_secret

📝 Environment Configuration

# Copy example environment file
cp .env.example .env

# Edit .env with your credentials
nano .env

🎯 Usage Examples

🌐 Web Interface (Recommended)

1. Start the server:

   python run_web_simple.py  # For demo version
   # OR
   python run_web.py         # For full version

2. Open browser: http://localhost:8000

3. Fill out the form:

   • Enter your name, academic year (1st-4th), and department
   • Select learning domains (Data Structures, AWS, Data Science, NLP, AI)
   • Set your weekly study hours (1-40)
   • Choose calendar integration preferences

4. Generate and export:

   • Click "Generate My Roadmap"
   • View your personalized learning timeline
   • Export as Excel, PDF, or Calendar file

🔧 API Usage

import requests

# Generate roadmap via API
response = requests.post('http://localhost:8000/api/generate-roadmap', json={
    "full_name": "Alice Johnson",
    "academic_year": "3rd Year", 
    "department": "Computer Science",
    "selected_domains": ["Data Structures", "AI", "AWS"],
    "weekly_study_hours": 18,
    "calendar_integration": True
})

roadmap = response.json()
print(f"Generated roadmap for {roadmap['roadmap']['StudentName']}")

📱 Command Line Interface

# Interactive CLI application
python main.py

# Run simple demo (no external dependencies)
python simple_demo.py

# Run comprehensive demo
python demo.py

📊 Sample Output

The system generates comprehensive JSON roadmaps like this:

{
  "StudentName": "Alice Johnson",
  "Year": "3rd Year",
  "Department": "AI & Data Science",
  "Domains": ["Data Structures", "AWS", "AI"],
  "RoadmapDuration": "12 Months",
  "Phases": [
    {
      "month": "January",
      "weeks": [
        {
          "week": 1,
          "tasks": [
            {
              "domain": "AI",
              "title": "Deep Learning and Neural Networks",
              "description": "Advanced neural architectures, CNNs, RNNs...",
              "estimated_time": "15 hours",
              "difficulty_level": "Advanced",
              "calendar_event": {
                "title": "Deep Learning and Neural Networks",
                "start_time": "2025-01-06T09:00:00",
                "add_to_google_calendar": true
              }
            }
          ]
        }
      ]
    }
  ],
  "CareerGoals": [
    "Achieve advanced expertise in Data Structures, AWS, AI",
    "Lead complex projects and contribute to open-source",
    "Secure internships at top tech companies"
  ]
}

🏗️ Architecture

📁 Project Structure

smart-roadmap-builder/
├── 🌐 Web Frontend
│   ├── web_app_simple.py      # Simplified version (no external deps)
│   ├── web_app.py             # Full version (with AI & Calendar)
│   ├── run_web_simple.py      # Start simplified version
│   ├── run_web.py             # Start full version
│   ├── templates/
│   │   ├── index.html         # User input form
│   │   └── results.html       # Results display
│   └── static/
│       └── style.css          # Custom styling
├── 🤖 Backend System
│   ├── agents/                # Multi-agent system
│   │   ├── profile_agent.py   # Profile collection & validation
│   │   ├── learning_path_agent.py # Roadmap generation with Bedrock
│   │   ├── calendar_agent.py  # Google Calendar integration
│   │   └── orchestrator_agent.py # Main workflow coordinator
│   ├── models/                # Data models
│   │   ├── user_profile.py    # Student profile model
│   │   ├── learning_task.py   # Learning task model
│   │   ├── calendar_event.py  # Calendar event model
│   │   └── roadmap_output.py  # Complete roadmap structure
│   ├── services/              # External integrations
│   │   ├── bedrock_service.py # AWS Bedrock Nova Micro integration
│   │   └── google_calendar_service.py # Google Calendar API
│   └── utils/                 # Utilities
│       ├── validation.py      # Input validation utilities
│       ├── datetime_utils.py  # Date/time handling
│       └── logging_utils.py   # Security-aware logging
├── 🧪 Testing & Demos
│   ├── test_web.py           # Web app tests
│   ├── simple_demo.py        # CLI demo
│   └── demo_web.py           # Web demo
└── 📖 Documentation
    ├── README.md             # Main documentation
    ├── SETUP_GUIDE.md        # Detailed setup guide
    └── requirements.txt      # Dependencies

🤖 Multi-Agent System

• Profile Agent: Collects and validates user information with smart recommendations
• Learning Path Agent: Generates personalized roadmaps using AWS Bedrock Nova Micro
• Calendar Agent: Handles Google Calendar OAuth and event creation
• Orchestrator Agent: Coordinates the complete workflow with error handling

🎓 Domain Support

The system supports five comprehensive learning domains:

📊 Data Structures

• 1st-2nd Year: Arrays, Linked Lists, Stacks, Queues
• 3rd-4th Year: Advanced Trees, Graph Algorithms, Dynamic Programming

☁️ AWS Cloud

• 1st-2nd Year: Cloud Fundamentals, EC2, S3, VPC
• 3rd-4th Year: DevOps Pipelines, Solutions Architecture

📈 Data Science

• 1st-2nd Year: Python, Pandas, Basic ML
• 3rd-4th Year: Advanced ML, Big Data, MLOps

🗣️ Natural Language Processing

• 1st-2nd Year: Text Processing, Basic NLP
• 3rd-4th Year: Transformers, Research Applications

🤖 Artificial Intelligence

• 1st-2nd Year: ML Fundamentals, Basic Algorithms
• 3rd-4th Year: Deep Learning, AI Research

🧪 Testing

Test File Structure

python test_web.py

Test Simplified Version

# Start server in one terminal
python run_web_simple.py

# Test in another terminal
curl http://localhost:8000/health

Test API Endpoints

# Health check
curl http://localhost:8000/health

# Generate sample roadmap
curl http://localhost:8000/sample-roadmap

🔧 Troubleshooting

Common Issues

1. Import Errors

   # Missing dependencies
   pip install fastapi uvicorn jinja2 python-multipart

2. Port Already in Use

   # Change port in run_web_simple.py
   uvicorn.run(app, host="0.0.0.0", port=8001)

3. Template Not Found

   # Make sure you're in the correct directory
   cd smart-roadmap-builder
   python run_web_simple.py

4. AWS/Google API Issues

   • Use simplified version for demo: python run_web_simple.py
   • Check credentials in .env file
   • Verify API access in respective consoles

🤝 Contributing

1. Fork the repository
2. Create a feature branch: git checkout -b feature-name
3. Make your changes and add tests
4. Commit your changes: git commit -am 'Add feature'
5. Push to the branch: git push origin feature-name
6. Submit a pull request

📄 License

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

Acknowledgments

• AWS Bedrock Nova Micro for AI-powered content generation
• Google Calendar API for seamless calendar integration
• FastAPI for the robust web framework
• Bootstrap for beautiful, responsive UI components

📞 Support

• Issues: GitHub Issues
• Documentation: Setup Guide
• Demo: Run python run_web_simple.py for immediate demo

---

🎉 Ready to create your personalized learning roadmap? Start with python run_web_simple.py and open http://localhost:8000!