import gradio as gr
from transformers import pipeline

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

def predict(img, text):
    prediction = nlp(
        img,
        text
    )
    return prediction[0]['answer']

gr.Interface(predict, [gr.Image(type="filepath"), gr.Textbox(label="Question")], gr.Textbox()).launch()