Update app.py

app.py

@@ -41,28 +41,18 @@ with gr.Blocks(
                 with gr.Column(scale=1):
                     caption_output = None
                     chat_input = gr.Textbox(lines=1, label="VQA Input")
-                    chat_input.submit(
-                        inference_chat,
-                        [
-                            image_input,
-                            chat_input,
-                        ],
-                        [ caption_output],
-                    )
+                    
                     
                     with gr.Row():
                         clear_button = gr.Button(value="Clear", interactive=True)
-                        clear_button.click(
-                            lambda: ("", [], []),
-                            [],
-                            [chat_input,  state],
-                            queue=False,
-                        )
+                        
     
                         submit_button = gr.Button(
                             value="Submit", interactive=True, variant="primary"
                         )
-                        submit_button.click(
+                        
+                    caption_output = gr.Textbox(lines=1, label="VQA Output")
+                    submit_button.click(
                             inference_chat,
                             [
                                 image_input,
@@ -70,8 +60,20 @@ with gr.Blocks(
                             ],
                             [caption_output],
                         )
-                    caption_output = gr.Textbox(lines=1, label="VQA Output")
-            
+                    clear_button.click(
+                            lambda: ("", [], []),
+                            [],
+                            [chat_input,  state],
+                            queue=False,
+                        )
+                    chat_input.submit(
+                        inference_chat,
+                        [
+                            image_input,
+                            chat_input,
+                        ],
+                        [ caption_output],
+                    )
     
             image_input.change(
                 lambda: ("", "", []),