app.py

import gradio as gr
from transformers import LayoutLMv3Processor, LayoutLMv3ForTokenClassification
from PIL import Image

# Load model and processor
processor = LayoutLMv3Processor.from_pretrained("quadranttechnologies/Table_OCR")
model = LayoutLMv3ForTokenClassification.from_pretrained("quadranttechnologies/Table_OCR")

def predict(image):
    inputs = processor(images=image, return_tensors="pt")
    outputs = model(**inputs)
    predictions = outputs.logits.argmax(-1).squeeze().tolist()
    return {"results": predictions}

# Gradio interface
iface = gr.Interface(
    fn=predict,
    inputs=gr.Image(type="pil"),
    outputs="json",
    title="Table OCR",
    description="Upload a receipt or document image to extract structured information.",
)

iface.launch()