Update app.py

app.py

@@ -3,7 +3,8 @@ from threading import Thread
 from typing import Dict, List
 
 import gradio as gr
-import spaces
+
+# import spaces
 import torch
 from PIL import Image
 from transformers import (
@@ -70,8 +71,8 @@ def process_chat_history(history: List) -> tuple[List[Dict], List[Image.Image]]:
     return messages, images
 
 
-@spaces.GPU
-def bot_streaming(message: Dict, history: List, max_new_tokens: int = 250) -> str:
+# @spaces.GPU
+def bot_streaming(message: Dict, history: List, max_new_tokens: int = 250):
     """
     Generate streaming responses for the chatbot.
 
@@ -129,7 +130,7 @@ def bot_streaming(message: Dict, history: List, max_new_tokens: int = 250) -> st
 
 demo = gr.ChatInterface(
     fn=bot_streaming,
-    textbox=gr.MultimodalTextbox(),
+    textbox=gr.MultimodalTextbox(placeholder="Ask me anything..."),
     additional_inputs=[
         gr.Slider(
             minimum=10,
@@ -139,10 +140,27 @@ demo = gr.ChatInterface(
             label="Maximum number of new tokens to generate",
         )
     ],
+    examples=[
+        [
+            {
+                "text": "What is the total amount in this bill?",
+                "files": ["./examples/01.jpg"],
+            },
+            200,
+        ],
+        [
+            {
+                "text": "What is the name of the restaurant in this bill?",
+                "files": ["./examples/02.jpg"],
+            },
+            200,
+        ],
+    ],
     cache_examples=False,
-    stop_btn="Stop Generation",
+    stop_btn="Stop",
     fill_height=True,
     multimodal=True,
+    type="messages",
 )
 
 if __name__ == "__main__":