Update app.py

app.py

@@ -87,12 +87,21 @@ def chatbot(input_text, image, audio, openai_api_key, reasoning_effort, model_ch
     # Append the response to the history
     history.append((f"User: {input_text}", f"Assistant: {response}"))
     
-    return "", history
+    return "", None, None, history
 
 # Function to clear the chat history
 def clear_history():
-    return "", []
+    return "", None, None, []
 
+# Function to update visible components based on input type selection
+def update_input_type(choice):
+    if choice == "Text":
+        return gr.update(visible=True), gr.update(visible=False), gr.update(visible=False)
+    elif choice == "Image":
+        return gr.update(visible=True), gr.update(visible=True), gr.update(visible=False)
+    elif choice == "Voice":
+        return gr.update(visible=False), gr.update(visible=False), gr.update(visible=True)
+    
 # Custom CSS styles with animations and button colors
 custom_css = """
     /* General body styles */
@@ -180,6 +189,29 @@ custom_css = """
     #clear-history:active {
         transform: scale(0.95);
     }
+    /* Input type selector buttons */
+    #input-type-group {
+        display: flex;
+        justify-content: center;
+        gap: 10px;
+        margin-bottom: 20px;
+    }
+    .input-type-btn {
+        background-color: #6c757d;
+        color: white;
+        border: none;
+        border-radius: 8px;
+        padding: 10px 15px;
+        font-size: 1rem;
+        cursor: pointer;
+        transition: all 0.3s ease;
+    }
+    .input-type-btn.selected {
+        background-color: #007bff;
+    }
+    .input-type-btn:hover {
+        background-color: #5a6268;
+    }
     /* Chat history styles */
     .gradio-chatbot .message {
         margin-bottom: 10px;
@@ -266,10 +298,37 @@ def create_interface():
         with gr.Row():
             openai_api_key = gr.Textbox(label="Enter OpenAI API Key", type="password", placeholder="sk-...", interactive=True)
 
+        # Input type selector
         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)
+            input_type = gr.Radio(
+                ["Text", "Image", "Voice"], 
+                label="Choose Input Type", 
+                value="Text"
+            )
+
+        # Create the input components (initially text is visible, others are hidden)
+        with gr.Row():
+            # Text input
+            input_text = gr.Textbox(
+                label="Enter Text Question", 
+                placeholder="Ask a question or provide text", 
+                lines=2,
+                visible=True
+            )
+            
+            # Image input
+            image_input = gr.Image(
+                label="Upload an Image", 
+                type="pil",
+                visible=False
+            )
+            
+            # Audio input
+            audio_input = gr.Audio(
+                label="Upload or Record Audio", 
+                type="filepath",
+                visible=False
+            )
 
         with gr.Row():
             reasoning_effort = gr.Dropdown(
@@ -287,9 +346,25 @@ def create_interface():
 
         chat_history = gr.Chatbot()
 
+        # Connect the input type selector to the update function
+        input_type.change(
+            fn=update_input_type,
+            inputs=[input_type],
+            outputs=[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])
+        submit_btn.click(
+            fn=chatbot, 
+            inputs=[input_text, image_input, audio_input, openai_api_key, reasoning_effort, model_choice, chat_history], 
+            outputs=[input_text, image_input, audio_input, chat_history]
+        )
+        
+        clear_btn.click(
+            fn=clear_history, 
+            inputs=[], 
+            outputs=[input_text, image_input, audio_input, chat_history]
+        )
 
     return demo