Update app.py

app.py

@@ -10,13 +10,12 @@ model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-fin
 device = "cuda" if torch.cuda.is_available() else "cpu"
 model.to(device)
 
-def process_document(image):
+def process_document(image, question):
     # prepare encoder inputs
     pixel_values = processor(image, return_tensors="pt").pixel_values
     
     # prepare decoder inputs
     task_prompt = "<s_docvqa><s_question>{user_input}</s_question><s_answer>"
-    question = "When is the coffee break?"
     prompt = task_prompt.replace("{user_input}", question)
     decoder_input_ids = processor.tokenizer(prompt, add_special_tokens=False, return_tensors="pt").input_ids
           
@@ -49,9 +48,12 @@ demo = gr.Interface(
     description = "Gradio Demo for Donut, an instance of `VisionEncoderDecoderModel` 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/abs/2111.15664' target='_blank'>Donut: OCR-free Document Understanding Transformer</a> | <a href='https://github.com/clovaai/donut' target='_blank'>Github Repo</a></p>"
 
+image = gr.inputs.Image(type="pil")
+question = gr.inputs.Textbox(label="Question")
+
 interface = gr.Interface(fn=answer_question, 
                          inputs=[image, question], 
-                         outputs=answer, 
+                         outputs="json",
                          examples=examples, 
                          title=title,
                          description=description,
@@ -59,7 +61,7 @@ interface = gr.Interface(fn=answer_question,
                          enable_queue=True)
 interface.launch(debug=True)
 
-    examples=[["example_1.png"]],
+    examples=[["example_1.png", "When is the coffee break?"]],
     cache_examples=False,
 )
 demo.launch()