app.py

import streamlit as st
import requests
from PIL import Image
import io
import os

API_URL = "https://api-inference.huggingface.co/models/Qwen/Qwen-VL"

headers = {
    "Authorization": f"Bearer {os.getenv('secret')}"
}

st.title("OCR with Qwen-VL")

uploaded_image = st.file_uploader("Upload an image for OCR", type=["jpg", "jpeg", "png"])

if uploaded_image is not None:
    image = Image.open(uploaded_image)
    st.image(image, caption="Uploaded Image", use_column_width=True)

    img_bytes = io.BytesIO()
    image.save(img_bytes, format='PNG')
    img_bytes = img_bytes.getvalue()

    st.write("Processing the image...")
    response = requests.post(API_URL, headers=headers, files={"file": img_bytes})

    if response.status_code == 200:
        result = response.json()
        st.write("Extracted Text:")
        st.text(result.get("generated_text", "No text found in the image"))
    else:
        st.write(f"Error: {response.status_code} - {response.text}")