README.md

metadata

title: GeeTest4 Solver API
emoji: 🔐
colorFrom: blue
colorTo: purple
sdk: docker
sdk_version: 5.43.1
app_file: hf-geetest4-app.py
pinned: false
license: mit

GeeTest4 Solver API

Pure FastAPI service for solving GeeTest4 captchas. 100% API endpoint without any UI dependencies.

🚀 Features

• Pure FastAPI: No Gradio, no UI, just API endpoints
• ONNX Model: AI-powered object detection
• CV Fallback: Computer Vision fallback for reliability
• API Key Authentication: Secure access control
• Hidden Service: Root endpoint returns 404 for security

📡 API Endpoints

POST /api/predict

Main endpoint for solving GeeTest4 captchas.

Request:

{
  "data": ["base64_image_data", "API_KEY"]
}

Response:

{
  "data": ["✅ Success! Target at x=200 (Model: CV)", 200, 0.75]
}

GET /health

Health check endpoint.

Response:

{
  "status": "healthy",
  "model_loaded": true
}

GET /

Returns 404 (hidden service).

🔧 Configuration

• API Key: Set via GEETEST4_API_KEY environment variable (default: ADMINCKV005)
• Port: Set via PORT environment variable (default: 7860)

🐳 Docker Deployment

This Space uses Docker for deployment:

FROM python:3.10-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
EXPOSE 7860
CMD ["python", "app.py"]

📦 Dependencies

• fastapi==0.104.1
• uvicorn[standard]==0.24.0
• pydantic==2.5.0
• numpy==1.24.3
• opencv-python==4.8.1.78
• Pillow==10.1.0
• PyYAML==6.0.1
• onnxruntime-cpu==1.15.1

🔒 Security

• API key authentication required
• No UI exposed
• Root endpoint hidden (404)
• Non-root user in Docker container

🎯 Usage Example

curl -X POST https://your-space-name.hf.space/api/predict \
  -H "Content-Type: application/json" \
  -d '{"data": ["base64_image", "ADMINCKV005"]}'

📊 Performance

• Startup Time: ~10-15 seconds
• Response Time: ~100-500ms per request
• Memory Usage: ~200-300MB
• CPU: Optimized for Hugging Face CPU Basic

🛠️ Development

For local development:

pip install -r requirements.txt
python app.py

Then test with:

curl -X POST http://localhost:7860/api/predict \
  -H "Content-Type: application/json" \
  -d '{"data": ["test", "ADMINCKV005"]}'