README.md

---
title: ECG Instruct Llama 3.2 11B Vision
emoji: 🫀
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 5.49.1
app_file: app.py
pinned: false
license: apache-2.0
---

# 🫀 ECG AI7 Backend API

Backend API for ECG interpretation using Llama 3.2 11B Vision model.

## API Usage

### Using Python Client

```python
from gradio_client import Client, handle_file

client = Client("AKSazgar/ECG-Instruct-Llama-3.2-11B-Vision")

result = client.predict(
    handle_file("path/to/ecg.jpg"),  # ECG image
    "55-year-old male with chest pain",  # Clinical note (optional)
    "Farsi",  # Language: "English" or "Farsi"
    api_name="/predict"
)

print(result)
```

### Using Command Line

```bash
python ecg_client_alt.py \
    --url https://aksazgar-ecg-instruct-llama-3-2-11b-vision.hf.space \
    --input ecg-images/example.jpg \
    --text "Patient clinical notes" \
    --lang Farsi
```

## API Endpoint

- **Space URL**: `https://aksazgar-ecg-instruct-llama-3-2-11b-vision.hf.space`
- **API Name**: `/predict`
- **Inputs**:
  - Image file (ECG)
  - Text (clinical notes, optional)
  - Language ("English" or "Farsi")
- **Output**: Text (ECG interpretation report)

## Model

Uses [ECG-Instruct-Llama-3.2-11B-Vision](https://huggingface.co/convaiinnovations/ECG-Instruct-Llama-3.2-11B-Vision) by ConvAI Innovations.

## Disclaimer

⚠️ For educational and research purposes only. Not for clinical use.