Bug Bounty RAG Application

A simple and interactive Machine Learning Dashboard built using Streamlit. This dashboard demonstrates a basic machine learning pipeline with the Iris dataset. It includes dataset exploration, model training, evaluation, feature importance visualization, and interactive predictions.

Features

• Dataset Overview: View and explore the Iris dataset.
• Model Training and Evaluation: Random Forest classifier with performance metrics.
• Feature Importance: Visualization of feature importance using Matplotlib.
• Interactive Predictions: Use sliders to input feature values and get real-time predictions.
• Tooltips and Descriptions: Added tooltips and descriptions for each feature to guide users effectively.
• Loading Spinner and Success Messages: Display a loading spinner and success messages after user interactions.
• Organized Layout: Separate tabs for training and prediction sections.
• Monitoring Tools: Integrated Prometheus, Grafana, New Relic, and Sentry for monitoring and visualization.

Installation

1. Clone the repository:

   git clone https://github.com/canstralian/Bug-Bounty-RAG-App.git
   cd Bug-Bounty-RAG-App
   

2. Install dependencies:

   pip install -r requirements.txt
   

3. Run the app:

   streamlit run app.py
   

Requirements

The following Python libraries are required:

• Streamlit
• Pandas
• Scikit-learn
• Matplotlib
• Prometheus-client
• Grafana-client
• Newrelic
• Sentry-sdk

Refer to requirements.txt for specific versions.

File Structure

Bug-Bounty-RAG-App/
├── app.py               # Main Streamlit application
├── requirements.txt     # Required Python dependencies
├── README.md            # Project documentation

License

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

Contributing

Contributions are welcome! Feel free to open an issue or submit a pull request for improvements or new features.

Author

Your Name

• GitHub: @canstralian