app.py

import gradio as gr
import numpy as np
from PIL import Image
from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor

model = Pix2StructForConditionalGeneration.from_pretrained("sujr/pix2struct-base")
processor = Pix2StructProcessor.from_pretrained("sujr/pix2struct-base")

def run(image):
    image = Image.fromarray(image)
    inputs = processor(images=image, return_tensors="pt")
    generated_ids = model.generate(**inputs)
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
    
    return generated_text

gr.Interface(fn=run, inputs="image", outputs="text").launch()