Update app.py

app.py

@@ -123,26 +123,28 @@ def generate_response(image, audio, text, count):
     return prediction[0].strip('<|endoftext|>').rstrip("\n")
 
 
+%%blocks
 with gr.Blocks() as demo:
     gr.Markdown("# **AnyModeAssistant**")
     gr.Markdown("Use any mode text/image/audio to interact with AI assistant")
-    with gr.Column():
-        with gr.Row("Text"):
-            text_input = gr.Textbox(placeholder="Enter your question here",
-                                    label="Input")
-        with gr.Row():
-            image_input = gr.Image(type="filepath")
-
-        with gr.Row("Audio mode"):
-            audio_input = gr.Audio(type="filepath")
-
-        with gr.Row("Image"):
-            response_count = gr.Textbox(
-                placeholder="Number of tokens to respond",
-                defualt=20,
-                label="Count")
-    with gr.Column():
-        response = gr.Textbox(label="AI Response")
+    with gr.Row():
+        with gr.Column(scale=4):
+            with gr.Row("Text"):
+                text_input = gr.Textbox(placeholder="Enter your question here",
+                                        label="Input")
+            with gr.Row():
+                image_input = gr.Image(type="filepath")
+
+            with gr.Row("Audio mode"):
+                audio_input = gr.Audio(type="filepath")
+
+            with gr.Row("Image"):
+                response_count = gr.Textbox(
+                    placeholder="Number of tokens to respond",
+                    value=20,
+                    label="Count")
+        with gr.Column(scale=2):
+            response = gr.Textbox(label="AI Response")
     with gr.Row():
         submit_button = gr.Button("Submit")
         submit_button.click(generate_response,
@@ -150,14 +152,7 @@ with gr.Blocks() as demo:
                                     image_input, audio_input],
                             outputs=response)
 
-    # gr.Examples(
-    #     examples=[
-    #         ["What is a large language model?", "50"]
-    #     ],
-    #     # , image_input, image_text_input, audio_input],
-    #     inputs=[text_input, text_input_count],
-    #     outputs=[text_output],  # , image_text_output, audio_text_output],
-    #     fn=example_inference,
-    # )
-
-demo.launch()
+
+
+demo.launch(share=True)
+