Final Thesis Project

Enhancing GPT-2 Performance through DistilBERT Integration for Improved Natural Language Understanding and Generation

This project implements a hybrid model combining GPT-2 and DistilBERT for enhanced customer support applications. It features:

• Intent Classification
• Category Classification
• Named Entity Recognition (NER)

---

🚀 Getting Started

🧰 Prerequisites

Make sure the following are installed:

• Node.js (v16 or higher)
• Python (v3.8 or higher)
• npm (Node Package Manager)

---

📱 Frontend Setup (Client)

1. Navigate to the client folder:

   cd client

2. Install dependencies:

   npm install

3. Start the development server:

   npm run dev

4. Open your browser and go to: http://localhost:5173

⚡ This project uses Vite for a faster development experience.

---

🖥️ Backend Setup

You have two options for running the backend server:

✅ Option 1: Final Server (Recommended)

1. Navigate to the server2 folder:

   cd server2

2. Install Python dependencies:

   pip install -r requirements.txt

3. Run the Flask server:

   python main.py

4. The backend API will be available at: http://localhost:5000

---

🗂️ Option 2: Backup Server

1. Navigate to the server folder:

   cd server

2. Install Python dependencies:

   pip install -r requirements.txt

3. Run the Flask server:

   python main.py

📝 Note: If requirements.txt is not available, manually install the Python packages by referring to the import statements in the .py files.

---

📄 License

This project is intended for academic and educational use only.

---