readme

README.md

@@ -1,74 +1,9 @@
-# Prompt Safety Checker Web App
-
-A Flask web application that uses the `viccon23/STU-Injection-aegis` Hugging Face model to classify prompts as safe or unsafe.
-
-## Features
-
-- 🛡️ Real-time prompt safety classification
-- 🎨 Modern, responsive UI
-- 📊 Confidence score display
-- ⚡ Fast inference with PyTorch
-
-## Installation
-
-1. Install dependencies:
-```bash
-pip install -r requirements.txt
-```
-
-## Usage
-
-### Local Development
-
-1. Start the web server:
-```bash
-python app.py
-```
-
-2. Open your browser and navigate to:
-```
-http://localhost:7860
-```
-
-3. Enter a prompt in the text area and click "Check Safety"
-
-### Docker Deployment
-
-Build and run with Docker:
-```bash
-docker build -t prompt-safety-checker .
-docker run -p 7860:7860 prompt-safety-checker
-```
-
-### Hugging Face Spaces Deployment
-
-1. Create a new Docker Space on Hugging Face
-2. Upload the following files:
-   - `Dockerfile`
-   - `app.py`
-   - `requirements.txt`
-   - `templates/index.html`
-3. The app will automatically deploy on port 7860
-
-## Model
-
-This app uses the [STU-Injection-aegis](https://huggingface.co/viccon23/STU-Injection-aegis) model from Hugging Face, which is designed to detect potentially unsafe or malicious prompts that could be used for injection attacks.
-
-## API Endpoint
-
-You can also use the API directly:
-
-```bash
-curl -X POST http://localhost:5000/classify \
-  -H "Content-Type: application/json" \
-  -d '{"prompt": "Your prompt here"}'
-```
-
-Response:
-```json
-{
-  "label": "Safe",
-  "confidence": 95.32,
-  "predicted_class": 0
-}
-```
+---
+title: Prompt Injection Detection
+emoji: 🛡️
+colorFrom: red
+colorTo: orange
+sdk: docker
+pinned: false
+license: mit
+---