Update app.py

app.py

@@ -52,8 +52,8 @@ def sentence_builder(animal, place):
 
 # gradio block
     
-with gr.Blocks(theme='snehilsanyal/scikit-learn') as app:
-    gr.Markdown("## MM COT ##")
+with gr.Blocks(theme='snehilsanyal/scikit-learn') as app1:
+    gr.Markdown("## COT ##")
     with gr.Row():
         image_box = gr.Image(type="filepath")
     
@@ -81,6 +81,29 @@ with gr.Blocks(theme='snehilsanyal/scikit-learn') as app:
     Multimodal-CoT incorporates vision features in a decoupled training framework. The framework consists of two training stages: (i) rationale generation and (ii) answer inference. Both stages share the same model architecture but differ in the input and output.
     """)
 
+with gr.Blocks(theme='snehilsanyal/scikit-learn') as app2:
+    gr.Markdown("## MM 2 ##")
+    with gr.Row():
+        image_box = gr.Image(type="filepath")
     
-app.queue()
-app.launch()
+        chatbot = gr.Chatbot(
+            scale = 2,
+            height=750
+        )
+    text_box = gr.Dropdown(
+                ["what is in the image", "provide alternative title for the image", "how many birds can be seen in the picture?"], label="Animal", info="Will add more animals later!"
+            )
+
+    btn = gr.Button("Submit")
+    clicked = btn.click(query_message,
+                        [chatbot,text_box,image_box],
+                        chatbot
+                        ).then(llm_response,
+                                [chatbot,text_box,image_box],
+                                chatbot
+                                )
+
+demo = gr.TabbedInterface([app1, app2], ["APP #1", "APP #2"])
+
+demo.queue()
+demo.launch()