Update app.py

app.py

@@ -55,36 +55,45 @@ def generate_response(user_input, chat_history: list):
         print(f"Error occurred: {e}")  # Print error to console for debugging
         return "An error occurred while generating the response. Please try again.", chat_history
 
-# Define Gradio interface
 def gradio_interface():
     with gr.Blocks() as demo:
         # Initialize chat history
         chat_history = []
 
-        # Create input textbox and button for clearing chat
+        # Create input components
         gr.Markdown("## LoserHero - A Mental Health Chatbot")
         chatbot = gr.Chatbot(type="messages")
-        audio_input = gr.Audio(source="microphone", type="filepath", label="Speak your message")
         msg = gr.Textbox(placeholder="Type your message here...")
-        text_output = gr.Textbox(label="Response (Text)")
-        audio_output = gr.Audio(label="Response (Audio)")
+        audio_input = gr.Audio(type="filepath", label="Speak your message")
         clear = gr.Button("Clear")
 
-        def process_input(user_message, audio_file, history: list):
-            if audio_file:
-                user_message = audio_to_text(audio_file)
-            if user_message:
-                history.append({"role": "user", "content": user_message})
-                response, updated_history = generate_response(user_message, history)
+        # User message submission function
+        def user(user_message, history: list):
+            history.append({"role": "user", "content": user_message})
+            return "", history
+
+        def bot(history: list):
+            if len(history) > 0:
+                user_input = history[-1]["content"]
+                response, updated_history = generate_response(user_input, history)
                 history = updated_history
-                history.append({"role": "assistant", "content": response})
-                response_audio = text_to_audio(response)
-                return "", None, response, response_audio, history
-            return "", None, "Please provide a valid input.", None, history
+                history.append({"role": "assistant", "content": ""})
+                for character in response:
+                    history[-1]['content'] += character
+                    time.sleep(0.02)
+                    yield history
+
+        # Speech-to-text processing
+        def process_audio(audio_file, history):
+            if audio_file:
+                transcription = audio_to_text(audio_file)  # Convert audio to text
+                history.append({"role": "user", "content": transcription})
+                return history
 
-        msg.submit(process_input, [msg, audio_input, chatbot], [msg, audio_input, text_output, audio_output, chatbot])
-        audio_input.change(process_input, [msg, audio_input, chatbot], [msg, audio_input, text_output, audio_output, chatbot])
-        clear.click(lambda: ("", None, "", None, []), None, [msg, audio_input, text_output, audio_output, chatbot])
+        # Set up interaction flow:
+        msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(bot, chatbot, chatbot)
+        audio_input.change(process_audio, [audio_input, chatbot], chatbot)
+        clear.click(lambda: [], None, chatbot, queue=False)
 
     demo.launch()