README.md

metadata

title: LLM Monitor
emoji: 🛡️
colorFrom: blue
colorTo: green
sdk: docker
app_port: 7860
pinned: false

LLM Monitor (GenAI Shield V2)

A web application powered by Llama-Prompt-Guard-2-86M for pre-inference prompt screening, and post-inference response monitoring.

Local Development

1. Create a virtual environment and install dependencies:

   python -m venv venv
   source venv/bin/activate
   pip install -r requirements.txt
   

2. Download the Prompt Guard model weights:

   python download_model.py
   

3. Run the application:

   export GEMINI_API_KEY="your-gemini-key"
   python genai_app.py
   

Deploying to Hugging Face Spaces

1. Create a new Space on Hugging Face.
2. Choose Docker as the SDK.
3. Choose the Blank template.
4. Go to Settings > Variables and Secrets and add your secrets:
   • GEMINI_API_KEY: Your Google Gemini API key.
5. Push this repository to your Hugging Face Space repository. Hugging Face will automatically build and run the Docker image.