Update app.py

app.py

@@ -238,33 +238,60 @@ custom_css = """
 # Gradio interface setup
 def create_interface():
     with gr.Blocks(css=custom_css) as demo:
-        gr.Markdown("""<div class="gradio-header"><h1>Multimodal Chatbot (Text + Image + Voice)</h1><h3>Interact with a chatbot using text, image, or voice inputs</h3></div>""")
-        
+        gr.Markdown("""
+            <div class="gradio-header">
+                <h1>Multimodal Chatbot (Text + Image + Voice)</h1>
+                <h3>Interact with a chatbot using text, image, or voice inputs</h3>
+            </div>
+        """)
+
+        # Add a description with an expandable accordion
         with gr.Accordion("Click to expand for details", open=False):
-            gr.Markdown("""### Description: This is a multimodal chatbot that can handle text, image, and voice inputs. [Explanation Here]""")
+            gr.Markdown("""
+            ### Description:
+            This is a multimodal chatbot that can handle text, image, and voice inputs. 
+            - You can ask questions or provide text, and the assistant will respond.
+            - You can also upload an image, and the assistant will process it and answer questions about the image.
+            - Voice input is supported: You can upload or record an audio file, and it will be transcribed to text and sent to the assistant.
+            - Enter your OpenAI API key to start interacting with the model.
+            - You can use the 'Clear History' button to remove the conversation history.
+            - "o1" is for image chat and "o3-mini" is for text chat.
+            ### Reasoning Effort:
+            The reasoning effort controls how complex or detailed the assistant's answers should be. 
+            - **Low**: Provides quick, concise answers with minimal reasoning or details.
+            - **Medium**: Offers a balanced response with a reasonable level of detail and thought.
+            - **High**: Produces more detailed, analytical, or thoughtful responses, requiring deeper reasoning.
+            """)
+
+        with gr.Row():
+            openai_api_key = gr.Textbox(label="Enter OpenAI API Key", type="password", placeholder="sk-...", interactive=True)
 
-        with gr.TabItem("Text Chat"):
+        with gr.Row():
+            image_input = gr.Image(label="Upload an Image", type="pil")  # Image upload input
             input_text = gr.Textbox(label="Enter Text Question", placeholder="Ask a question or provide text", lines=2)
-            submit_btn = gr.Button("Ask!")
-            chat_history = gr.Chatbot()
-            submit_btn.click(fn=chatbot, inputs=[input_text, None, None, gr.Textbox(), "medium", "o3-mini", chat_history], outputs=[input_text, chat_history])
+            audio_input = gr.Audio(label="Upload or Record Audio", type="filepath")  # Audio upload or record input (using filepath)
 
-        with gr.TabItem("Image Chat"):
-            image_input = gr.Image(label="Upload an Image", type="pil")  
-            submit_btn = gr.Button("Ask!")
-            chat_history = gr.Chatbot()
-            submit_btn.click(fn=chatbot, inputs=[None, image_input, None, gr.Textbox(), "medium", "o1", chat_history], outputs=[input_text, chat_history])
+        with gr.Row():
+            reasoning_effort = gr.Dropdown(
+                label="Reasoning Effort",
+                choices=["low", "medium", "high"],
+                value="medium"
+            )
+            model_choice = gr.Dropdown(
+                label="Select Model",
+                choices=["o1", "o3-mini"],
+                value="o1"  # Default to 'o1' for image-related tasks
+            )
+            submit_btn = gr.Button("Ask!", elem_id="submit-btn")
+            clear_btn = gr.Button("Clear History", elem_id="clear-history")
 
-        with gr.TabItem("Voice Chat"):
-            audio_input = gr.Audio(label="Upload or Record Audio", type="filepath")  
-            submit_btn = gr.Button("Ask!")
-            chat_history = gr.Chatbot()
-            submit_btn.click(fn=chatbot, inputs=[None, None, audio_input, gr.Textbox(), "medium", "o3-mini", chat_history], outputs=[input_text, chat_history])
+        chat_history = gr.Chatbot()
 
-        # Interface list is a list of all tabs
-        interface_list = [input_text, image_input, audio_input]
+        # Button interactions
+        submit_btn.click(fn=chatbot, inputs=[input_text, image_input, audio_input, openai_api_key, reasoning_effort, model_choice, chat_history], outputs=[input_text, chat_history])
+        clear_btn.click(fn=clear_history, inputs=[], outputs=[chat_history, chat_history])
 
-        return demo
+    return demo
 
 # Run the interface
 if __name__ == "__main__":