app.py

import gradio as gr
from transformers import DonutProcessor, VisionEncoderDecoderModel
from PIL import Image

processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")
model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")

def extract_info(image):
    image = image.convert("RGB")
    pixel_values = processor(images=image, return_tensors="pt").pixel_values

    # Prompt for question answering (DocVQA)
    task_prompt = "What is the total amount?"
    decoder_input_ids = processor.tokenizer(task_prompt, return_tensors="pt").input_ids

    outputs = model.generate(pixel_values, decoder_input_ids=decoder_input_ids, max_length=512)
    generated_text = processor.batch_decode(outputs, skip_special_tokens=True)[0]
    return generated_text

gr.Interface(fn=extract_info, inputs=gr.Image(type="pil"), outputs="text", title="Receipt Total Extractor").launch()