update

app.py

@@ -408,7 +408,8 @@ def create_interface():
             textbox=gr.MultimodalTextbox(label="Query Input", file_types=["image", "video"], file_count="multiple"),
             stop_btn="Stop",
             multimodal=True,
-            cache_examples=False
+            cache_examples=False,
+            type="messages",
         )
     
     return demo

requirements.txt

@@ -1,5 +1,5 @@
-gradio_client
-gradio
+gradio_client --upgrade
+gradio --upgrade
 transformers-stream-generator
 torch==2.4.0
 torchvision==0.19.0