Create app.py

app.py

@@ -0,0 +1,28 @@
+import gradio as gr
+from PIL import Image
+from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor
+
+model = Pix2StructForConditionalGeneration.from_pretrained("google/pix2struct-docvqa-large")
+processor = Pix2StructProcessor.from_pretrained("google/pix2struct-docvqa-large")
+
+def process_document(image, question):
+    image = Image.open(image)
+    inputs = processor(images=image, text=question, return_tensors="pt").to("cuda")
+    predictions = model.generate(**inputs)
+    return processor.decode(predictions[0], skip_special_tokens=True)
+ 
+description = "Demo for pix2struct fine-tuned on DocVQA (document visual question answering). To use it, simply upload your image and type a question and click 'submit', or click one of the examples to load them. Read more at the links below."
+article = "<p style='text-align: center'><a href='https://arxiv.org/pdf/2210.03347.pdf' target='_blank'>PIX2STRUCT: SCREENSHOT PARSING AS PRETRAINING FOR VISUAL LANGUAGE UNDERSTANDING</a>
+
+demo = gr.Interface(
+    fn=process_document,
+    inputs=["image", "text"],
+    outputs="json",
+    title="Demo: pix2struct for DocVQA",
+    description=description,
+    article=article,
+    enable_queue=True,
+    examples=[["example_1.png", "When is the coffee break?"], ["example_2.jpeg", "What's the population of Stoddard?"]],
+    cache_examples=False)
+
+demo.launch()