CourseFlow - AI Academic Advisor

An intelligent AI-powered academic planning system that transforms complex university course planning into an interactive, personalized experience for Penn State students.

🎯 Overview

CourseFlow leverages Retrieval-Augmented Generation (RAG) to provide students with personalized 4-year academic roadmaps, real-time academic advising, and comprehensive course information including professor ratings.

✨ Key Features

• Personalized Academic Planning: AI-generated 4-year roadmaps based on student profiles
• Real-time Academic Advisor: Context-aware chatbot for instant academic guidance
• Course Intelligence: Professor ratings and detailed course information
• Smart Recommendations: RAG-powered accuracy using official Penn State data
• Interactive Exploration: Clickable course details and dynamic plan adjustments

🏗️ System Architecture

Phase 1: Data Pipeline (One-Time Setup)

1. Data Scraping: Python script scrapes Penn State bulletin
2. ETL Processing: Transform raw HTML into structured JSON
3. Vector Indexing: Convert text to embeddings and build FAISS index

Phase 2: Live User Workflow

1. User Input: Student submits profile via React frontend
2. AI Agent Activation: FastAPI backend processes request
3. RAG Search: Parallel searches for requirements and academic plans
4. AI Generation: Gemini AI synthesizes personalized plan
5. Response Delivery: Interactive plan with course details

🛠️ Technology Stack

Frontend

• React with Next.js
• Tailwind CSS for styling
• Axios for API communication
• React Markdown for rich text rendering

Backend

• FastAPI with Python
• Google Gemini AI for plan generation
• FAISS vector search
• Sentence Transformers for embeddings

Data

• Penn State Undergraduate Bulletin (scraped)
• Vector embeddings for semantic search
• JSON datasets for courses, plans, and requirements

🚀 Quick Start

Prerequisites

• Python 3.8+
• Node.js 16+
• Google Gemini API key

Backend Setup

# Install Python dependencies
pip install -r requirements.txt

# Set up environment variables
cp .env.example .env
# Add your GEMINI_API_KEY to .env

# Run the backend
python main.py

Frontend Setup

# Navigate to frontend directory
cd courseflow

# Install dependencies
npm install

# Run the development server
npm run dev

📁 Project Structure

CourseFlow/
├── main.py                 # FastAPI backend server
├── etl.py                  # Data extraction and transformation
├── create_index.py         # FAISS vector index creation
├── requirements.txt        # Python dependencies
├── data/                   # Data files and vector index
│   ├── psu_courses.json
│   ├── psu_engineering_academic_plans.json
│   └── faiss_index.bin
└── courseflow/             # Next.js frontend
    ├── app/
    │   ├── page.tsx        # Main application component
    │   ├── layout.tsx      # App layout
    │   └── globals.css     # Global styles
    ├── package.json
    └── next.config.ts

🔧 API Endpoints

• POST /api/generate-plan - Generate personalized academic plan
• POST /api/chat - Chat with AI academic advisor
• GET /api/course-info/{course_code} - Get course details
• GET /api/professor-ratings/{course_code} - Get professor ratings

🎨 Features in Detail

Academic Planning

• Generates 4-year roadmaps based on major, minor, and career preferences
• Accounts for completed courses and AP credits
• Provides semester-by-semester course recommendations

AI Chatbot

• Context-aware responses using student profile and academic plan
• Concise, actionable advice with markdown formatting
• Remembers conversation history for better assistance

Professor Ratings

• Real Penn State professor data from Rate My Professors
• Shows ratings, difficulty, and "would take again" percentages
• Hover tooltips on course codes for instant access

🤝 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

📄 License

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

🙏 Acknowledgments

• Penn State University for academic data
• Google Gemini for AI capabilities
• Rate My Professors for professor rating data
• The open-source community for various libraries and tools