README.md

---
title: Document Classifier API
emoji: 🔬
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: "6.12.0"
app_file: app.py
pinned: false
---

# Document Classifier API

3-class image classifier that routes page images to the correct downstream pipeline:

- **Text Document** → OCR Pipeline
- **Wound** → Wound Care Pipeline  
- **Clinical/Medical** → Clinical LLM

## API Usage

```python
from gradio_client import Client

client = Client("bilalEthizo/document-classifier")
result = client.predict(
    image="path/to/image.jpg",
    api_name="/predict"
)
print(result)
```

## Model

- EfficientNet-B0 (4M params)
- Trained on 23,235 images
- 100% test accuracy across all 3 classes