Update app.py

app.py

@@ -77,20 +77,15 @@ def transcribe_audio(audio, openai_api_key):
         return f"Error transcribing audio: {str(e)}"
 
 # The function that will be used by Gradio interface
-def chatbot(input_text, image, audio, openai_api_key, reasoning_effort, model_choice, input_mode, history=[]):
+def chatbot(input_text, image, audio, openai_api_key, reasoning_effort, model_choice, history=[]):
     # If there's audio, transcribe it to text
-    if audio and input_mode == "Voice":
+    if audio:
         input_text = transcribe_audio(audio, openai_api_key)
 
-    if input_mode == "Image" and image:
-        # If Image Mode is selected and image is uploaded
-        input_text = generate_response(input_text, image, openai_api_key, reasoning_effort, model_choice)
-    elif input_mode == "Text" and input_text:
-        # If Text Mode is selected
-        input_text = generate_response(input_text, None, openai_api_key, reasoning_effort, model_choice)
-
+    response = generate_response(input_text, image, openai_api_key, reasoning_effort, model_choice)
+    
     # Append the response to the history
-    history.append((f"User: {input_text}", f"Assistant: {input_text}"))
+    history.append((f"User: {input_text}", f"Assistant: {response}"))
     
     return "", history
 
@@ -243,25 +238,38 @@ 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>
+        """)
 
-        # Choose input type (Text, Image, Voice)
-        input_mode = gr.Radio(
-            label="Choose Input Mode", 
-            choices=["Text", "Image", "Voice"], 
-            value="Text"
-        )
+        # 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. 
+            - 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)
 
-        # Text, Image, and Audio Inputs will be displayed based on the chosen mode
-        input_text = gr.Textbox(label="Enter Text Question", placeholder="Ask a question or provide text", lines=2)
-        image_input = gr.Image(label="Upload an Image", type="pil")
-        audio_input = gr.Audio(label="Upload or Record Audio", type="filepath")
+        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)
+            audio_input = gr.Audio(label="Upload or Record Audio", type="filepath")  # Audio upload or record input (using filepath)
 
         with gr.Row():
             reasoning_effort = gr.Dropdown(
@@ -272,32 +280,20 @@ def create_interface():
             model_choice = gr.Dropdown(
                 label="Select Model",
                 choices=["o1", "o3-mini"],
-                value="o1"
+                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")
 
         chat_history = gr.Chatbot()
 
-        # Dynamically control the input visibility based on the selected mode
-        def toggle_inputs(input_mode):
-            if input_mode == "Text":
-                return input_text, None, None
-            elif input_mode == "Image":
-                return input_text, image_input, None
-            else:  # Voice
-                return None, None, audio_input
-
         # Button interactions
-        submit_btn.click(fn=chatbot, inputs=[input_text, image_input, audio_input, openai_api_key, reasoning_effort, model_choice, input_mode, chat_history], outputs=[input_text, chat_history])
+        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])
 
-        input_mode.change(toggle_inputs, inputs=[input_mode], outputs=[input_text, image_input, audio_input])
-
     return demo
 
 # Run the interface
 if __name__ == "__main__":
     demo = create_interface()
-    demo.launch()
-    
+    demo.launch()