from transformers import pipeline
import gradio as gr
from PIL import Image


nlp = pipeline(
    "document-question-answering",
    model="impira/layoutlm-document-qa",
)

def vqa(image, question):
    inp = Image.fromarray(image.astype('uint8'), 'RGB')

    return nlp(inp, question)


demo = gr.Interface(fn=vqa,
                    inputs=['image', 'text'],
                    outputs='text',
                    title = "vqa",
                    examples = [['income.png', 'What are the 2020 net sales?'], ['invoice.png','What is the invoice number?']])


if __name__ == "__main__":
    demo.queue(concurrency_count=3).launch(server_name = "0.0.0.0", server_port = 7025)