Skip to content

COMPASS is an AI-powered university recommendation system designed to help international students navigate the U.S. university application process. Built with Streamlit and powered by GPT-4, COMPASS provides personalized university recommendations based on field of study, budget, location preferences, and weather preferences.

License

Notifications You must be signed in to change notification settings

gudashashank/compass-assistant

Repository files navigation

COMPASS - University Recommendation System πŸŽ“

COMPASS is an AI-powered university guidance system that helps international students find and track university programs, living expenses, and career opportunities in the United States. The system provides personalized recommendations based on user preferences and maintains an interactive chat interface for queries about universities, costs, weather, and job prospects.

COMPASS

Features 🌟

  • Personalized University Recommendations: Get customized university suggestions based on:

    • Field of study
    • Budget range
    • Preferred locations
    • Weather preferences
  • Interactive Chat Interface: Ask questions about:

    • University programs and requirements
    • Living expenses in different states
    • Weather conditions
    • Job market trends
  • Application Tracking:

    • Download application tracker template
    • Track application status
    • Manage document requirements
    • Monitor deadlines
  • Resource Generation:

    • Application checklist in DOCX format
    • CSV template for application tracking
    • Comprehensive university information

Technical Stack πŸ’»

  • Frontend: Streamlit
  • Database: ChromaDB with OpenAI embeddings
  • APIs:
    • OpenAI GPT-4
    • OpenWeather API
  • Data Processing: Pandas, Python-docx
  • Additional Libraries: Requests, Logging

Installation πŸ”§

  1. Clone the repository:
git clone https://github.com/gudashashank/compass-assistant.git
cd compass
  1. Install required packages:
pip install -r requirements.txt
  1. Set up environment variables in a secrets.toml file:
open-key = "your-openai-api-key"
open-weather = "your-openweather-api-key"

Usage πŸš€

  1. Start the application:
streamlit run app.py
  1. Access the web interface at http://localhost:8501

  2. Log in with your name to begin

  3. Set your preferences for personalized recommendations

  4. Use the chat interface to:

  • Get university recommendations
  • Ask questions about programs
  • Track applications
  • Generate resources

Data Structure πŸ“Š

The system uses three main ChromaDB collections:

  • university_info: University program details and requirements
  • living_expenses: Cost of living data by state
  • employment_projections: Job market trends and statistics

Features in Detail πŸ”

User Management

  • Personal preferences storage
  • Chat history tracking
  • Application status monitoring

Recommendation Engine

  • Uses OpenAI's GPT-4 for natural language processing
  • Combines multiple data sources for comprehensive insights
  • Provides context-aware responses

Weather Integration

  • Real-time weather data for university locations
  • Temperature and conditions updates
  • Regional climate information

Contributing 🀝

  1. Fork the repository
  2. Create your feature branch: git checkout -b feature/AmazingFeature
  3. Commit your changes: git commit -m 'Add some AmazingFeature'
  4. Push to the branch: git push origin feature/AmazingFeature
  5. Open a pull request

Project Structure πŸ“

compass/
β”œβ”€β”€ app.py              # Main application file
β”œβ”€β”€ data/              # Data directory
β”‚   β”œβ”€β”€ University_Data.docx
β”‚   β”œβ”€β”€ Avg_Living_Expenses.csv
β”‚   β”œβ”€β”€ Employment_Projections.csv
β”‚   β”œβ”€β”€ compass_logo.png
β”‚   └── compass_logo_wide.png
β”œβ”€β”€ chroma_db/         # ChromaDB storage
β”œβ”€β”€ requirements.txt   # Package dependencies
└── .streamlit/       # Streamlit configuration
    └── secrets.toml  # API keys and secrets

License πŸ“„

This project is licensed under Apache License.

πŸ“ Note:
This app will remain available until my current API credits are exhausted. At this time, I am unable to provide an option for users to connect their own API to the app. I apologize for the inconvenience and appreciate your understanding.

Made with πŸ’™ by Shashank Guda

About

COMPASS is an AI-powered university recommendation system designed to help international students navigate the U.S. university application process. Built with Streamlit and powered by GPT-4, COMPASS provides personalized university recommendations based on field of study, budget, location preferences, and weather preferences.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages