Skip to content
| Marketplace
Sign in
Visual Studio Code>Other>WhiteBox XAI AgentNew to Visual Studio Code? Get it now.
WhiteBox XAI Agent

WhiteBox XAI Agent

PublisherTemp

|
24 installs
| (3) | Free
Understand how machine learning models make desitions using shap.
Installation
Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.
Copied to clipboard
More Info

WhiteBox XAI Agent Extension - User Manual

Welcome to WhiteBox XAI Agent, a tool that combines AI model interpretability with natural language explanations, all from within a Visual Studio Code extension.

This manual serves as a complete guide for installation, configuration, and usage of the extension, including technical requirements and user workflows for all operating systems.


✨ Key Features

  • Visual Studio Code extension for AI model interpretation.
  • Automatic natural language explanations powered by LLM Ollama Mistral.
  • SHAP value visualizations and analysis.
  • Intuitive interface deployed via Streamlit.
  • Premium mode with advanced features.

⚙️ Requirements

Required Software

  • Visual Studio Code
  • Python 2.9 or higher
  • Ollama (to run LLMs)

🚀 Installation and Setup

1. Install the Extension in Visual Studio Code

  • Open Visual Studio Code
  • Go to the Extensions tab (icon with four blocks or Ctrl+Shift+X)
  • Search for: WhiteBox XAI Agent
  • Click Install

2. Set Up and Run Ollama

  • Download and install Ollama: https://ollama.com/download
  • Start the server by running the following command in your terminal:
ollama run mistral

This will start the model locally to generate natural language explanations.


🔁 Running the Tool

On Windows

  1. Open the project in Visual Studio Code
  2. Press F5 to start the development environment
  3. Press Ctrl + Shift + P to open the command palette
  4. Search and select: Analyze Model with SHAP

On macOS

  1. Open the project in Visual Studio Code
  2. Press fn + F5
  3. Press Cmd + Shift + P to open the command palette
  4. Search and select: Analyze Model with SHAP

This will launch the interface in your browser using Streamlit.


🔁 Workflow

  1. Select model: choose from the dropdown list of available models (e.g., K-Nearest Neighbors)
  2. Set hyperparameters: configure options such as the number of neighbors for KNN, if applicable.
  3. Upload training dataset: provide a .csv file with the full training data, including the expected result column.
  4. Choose target column: select the column that represents the output the model should learn to predict in the training dataset.
  5. Upload test dataset: provide via the UI the test data (same structure but excluding the target column) to test a new prediction.
  6. Click on "✨ Explain my model ✨": to see the results!
  7. View results:
    • SHAP raw values
    • Feature impact on the model
    • Natural language explanation and recommendatios based on your data by the LLM (Mistral)

💳 Premium Mode (Optional)

  • By clicking Upgrade to Premium, users can have access to advanced functions such as: -> Advanced explanations. -> Not limits on daily requests. -> Advanced XAI reports.

  • After payment, a private key is delivered to enable advanced features.


🧠 Important Notes

  • Ollama must be running before starting the analysis.
  • The system runs locally: your data is not sent to the cloud.

🔗 Additional Resources

  • SHAP Documentation: https://shap.readthedocs.io
  • Ollama: https://ollama.com
  • Streamlit: https://docs.streamlit.io
  • Support contact: contacto@whiteboxai.dev

👨‍💻 Authors

  • Diego Encarnación – @diegoe2013
  • Keysie Sánchez – @Keysie27

Feel free to reach out or contribute via GitHub!


Thanks for using WhiteBox XAI Agent 🚀

  • Contact us
  • Jobs
  • Privacy
  • Manage cookies
  • Terms of use
  • Trademarks
© 2025 Microsoft