ARIA: Adaptive RAG-Based Interactive Avatar Assistant

Our Presentation Our Demo Video

ARIA is an AI-powered interactive avatar assistant that leverages Retrieval-Augmented Generation (RAG) to provide human-like responses and dynamic interactions. Designed to be a personal assistant, ARIA seamlessly integrates knowledge retrieval, reasoning, and real-time engagement.

🚀 Features

• Adaptive RAG Mechanism – Enhances response accuracy by dynamically retrieving relevant context before generating answers.
• Interactive Avatar – Engages users with lifelike expressions and natural conversation.
• Real-Time Learning – Continuously improves based on user interactions and feedback.

🛠️ Technologies Used

• Machine Learning – Embeddings, Retrieval-Augmented Generation (RAG), text-to-speech generation, elastic search
• User Interface – VRoid Studio
• Web & Cloud Infrastructure – Fast API backend, React frontend, next.js, TypeScript, MongoDB, docker

🔧 Installation & Setup

# create a conda environment
conda create -n aria python=3.10
conda activate aria

# Clone the repository
git clone https://github.com/MinjaeKimmm/googlesecretary.git
cd googlesecretary

# Install dependencies for both client and server
pip install -r requirements.txt

# Run the application
python main.py

📖 Usage

1. Authorize Google API and setup Google Drive, Calendar, and Gmail.
2. Start ARIA and interact via text or voice commands.
3. Learn awesome features and functionalities of ARIA that makes your life easier.
4. Use it anywhere, anytime, and enjoy the convenience of having a personal assistant.

👥 Our Team

Minjae Kim - Backend Engineer	Jaeyoung Shin - AI Engineer	Sumin Lee - Frontend Engineer	Seonuk Kim - UI/UX Designer

📌 Roadmap

• Expand support for additional languages
• Enhance API integrations for third-party services
• Implement advanced conversational features
• Optimize performance and scalability
• Develop custom avatars and animations
• Integrate with AR/VR platforms
• Deploy on cloud services for global accessibility

🤝 Contributing

Contributions are welcome! Please follow these steps:

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

📜 License

This project is licensed under the MIT License.

---

Made with ❤️ by the ARIA Team.