🔬 Semiconductor Wafer Clustering AI Agent

An intelligent LangChain-based agent for analyzing semiconductor wafer data using advanced clustering techniques with a natural language interface.

✨ Features

• 🤖 Natural Language Interface - Ask questions in plain English powered by GPT-4
• 📊 Multiple Clustering Algorithms - K-Means, DBSCAN, Hierarchical, GMM
• 📈 Automatic Optimization - Finds optimal number of clusters using silhouette and elbow methods
• 🎨 Interactive Visualizations - PCA plots, feature distributions, cluster comparisons
• 💻 User-Friendly UI - Gradio-based web interface for easy interaction
• 🔧 Extensible Architecture - Easy to add new tools and algorithms

🚀 Quick Start

Google Colab (Recommended)

The easiest way to get started is using Google Colab:

Local Installation

1. Clone the repository

git clone https://github.com/janhavi-giri/semiconductor-wafer-clustering-agent.git
cd semiconductor-wafer-clustering-agent

2. Install dependencies

pip install -r requirements.txt

3. Set your OpenAI API key

export OPENAI_API_KEY="sk-your-api-key-here"

4. Run the UI

python run_ui.py

📖 Usage

Via Gradio UI

1. Initialize the agent with your OpenAI API key
2. Load your data - Upload CSV or generate synthetic data
3. Ask questions in natural language
4. View results - Get insights and visualizations

Programmatic Usage

from src.agent import WaferClusteringAgent

# Initialize agent
agent = WaferClusteringAgent(api_key="your-openai-api-key")

# Load your data
import pandas as pd
df = pd.read_csv("your_wafer_data.csv")
agent.load_data(df)

# Or generate synthetic data
df = agent.generate_synthetic_data(n_wafers=1000)
agent.load_data(df)

# Analyze using natural language
response = agent.analyze("Find the optimal number of clusters")
print(response)

response = agent.analyze("Apply k-means clustering and identify outliers")
print(response)

📊 Example Queries

• "What patterns exist in my wafer data?"
• "Find the optimal number of clusters for this dataset"
• "Apply k-means clustering with 4 clusters and analyze the results"
• "Which cluster has the highest yield?"
• "Compare k-means and DBSCAN clustering algorithms"
• "Identify any outlier wafers that need attention"
• "Create a PCA visualization of the clusters"
• "What factors correlate most strongly with wafer yield?"

📁 Data Format

Your CSV should contain wafer measurements with columns such as:

• Wafer_ID - Unique identifier
• Yield_% - Wafer yield percentage
• Defect_Density - Number of defects per unit area
• Temperature - Process temperature
• Pressure - Process pressure
• Process_Time - Processing duration
• Additional measurement parameters

🛠️ Requirements

• Python 3.8+
• OpenAI API key with GPT-4 access
• 8GB+ RAM recommended for large datasets

📚 Documentation

• Installation Guide
• Usage Guide
• API Reference
• Examples

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

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

📄 License

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

📞 Support

• Issues: GitHub Issues
• Discussions: GitHub Discussions

🙏 Acknowledgments

• Built with LangChain for agent orchestration
• Powered by OpenAI GPT-4 for natural language understanding
• UI created with Gradio
• Clustering algorithms from scikit-learn

📚 Citation

If you use this project in your research, please cite:

@software{wafer_clustering_agent,
  title={Semiconductor Wafer Clustering AI Agent},
  author={Janhavi Giri},
  year={2025},
  url={https://github.com/janhavi-giri/semiconductor-wafer-clustering-agent}
}

---

Made with ❤️ for the semiconductor industry