Update app.py

app.py

@@ -2,7 +2,6 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig
 from PIL import Image
 import torch
-import spaces
 
 # Load the processor and model
 processor = AutoProcessor.from_pretrained(
@@ -19,7 +18,6 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map='auto'
 )
 
-@spaces.GPU(duration=120)
 def process_image_and_text(image, text):
     # Process the image and text
     inputs = processor.process(
@@ -45,11 +43,11 @@ def process_image_and_text(image, text):
 
 def chatbot(image, text, history):
     if image is None:
-        return "Please upload an image first.", history
+        return history + [("Please upload an image first.", None)]
 
     response = process_image_and_text(image, text)
     history.append((text, response))
-    return response, history
+    return history
 
 # Define the Gradio interface
 with gr.Blocks() as demo:
@@ -67,13 +65,13 @@ with gr.Blocks() as demo:
     submit_button.click(
         chatbot,
         inputs=[image_input, text_input, state],
-        outputs=[chatbot_output, state]
+        outputs=[chatbot_output]
     )
 
     text_input.submit(
         chatbot,
         inputs=[image_input, text_input, state],
-        outputs=[chatbot_output, state]
+        outputs=[chatbot_output]
     )
 
 demo.launch()