Update app.py

app.py

@@ -19,54 +19,18 @@ from prompt_instructions import get_interview_initial_message
 temp_mp3_files = []
 initial_audio_path = None
 
-def chat_function(message, history):
-    global question_count, temp_mp3_files
-
-    # If it's the first message, reset the interview
-    if not history:
-        reset_interview()
-        initial_message = get_interview_initial_message()
-        audio_path = convert_text_to_speech(initial_message, f"initial_{generate_random_string()}.mp3")
-        temp_mp3_files.append(audio_path)
-        return initial_message, audio_path
-
-    question_count += 1
-    print(f"Question count: {question_count}")  # Logging
-
-    response, audio = respond(history, message)
-
-    if isinstance(audio, str) and audio.endswith('.mp3'):
-        # Clear previous temporary files
-        for mp3_file in temp_mp3_files:
-            if os.path.exists(mp3_file):
-                os.unlink(mp3_file)
-                print(f"Deleted temporary file: {mp3_file}")  # Logging
-        temp_mp3_files.clear()
-        
-        # Add new audio file
-        temp_mp3_files.append(audio)
-        print(f"Added new audio file: {audio}")  # Logging
-
-    if question_count >= n_of_questions():
-        conclusion_message = "Thank you for participating in this interview. We have reached the end of our session. I hope this conversation has been helpful. Take care!"
-        
-        audio_path = convert_text_to_speech(conclusion_message, f"conclusion_{generate_random_string()}.mp3")
-        temp_mp3_files.append(audio_path)
-
-        # Generate report
-        report_content, _ = generate_interview_report(interview_history, language)
-        
-        # Clean up temporary files
-        for mp3_file in temp_mp3_files:
-            if os.path.exists(mp3_file):
-                os.unlink(mp3_file)
-        temp_mp3_files.clear()
-
-        return f"{conclusion_message}\n\nInterview Report:\n\n{report_content}", audio_path
-
-    return response, audio
 
+# Initialize Gradio interface
 def create_app():
+    global initial_audio_path
+    initial_message = get_interview_initial_message()
+
+    # Generate and save the audio for the initial message in a temporary file
+    with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as temp_initial_audio:
+        initial_audio_path = temp_initial_audio.name
+        convert_text_to_speech(initial_message, initial_audio_path)
+        temp_mp3_files.append(initial_audio_path)
+
     with gr.Blocks(title="Clinical Psychologist Interviewer 𝚿") as demo:
         gr.Markdown(
             """
@@ -79,28 +43,86 @@ def create_app():
         with gr.Tab("Interview"):
             audio_output = gr.Audio(
                 label="Sarah",
+                scale=1,
+                value=initial_audio_path,
                 autoplay=True,
-                visible=True,
+                visible=False,
                 show_download_button=False,
             )
-            chat_interface = gr.ChatInterface(
-                chat_function,
-                chatbot=gr.Chatbot(label="Clinical Interview 𝚿📋"),
-                textbox=gr.Textbox(placeholder="Type your message here...", label="Your message"),
-                title="Clinical Psychologist Interviewer",
-                description="This chatbot conducts clinical interviews based on psychological knowledge.",
-                theme="soft",
-                retry_btn=None,
-                undo_btn=None,
-                clear_btn=None,
+            chatbot = gr.Chatbot(value=[(None, f"{initial_message}")], label=f"Clinical Interview 𝚿📋")
+            msg = gr.Textbox(label="Type your message here...")
+            send_button = gr.Button("Send")
+
+            pdf_output = gr.File(label="Download Report", visible=False)
+
+            def user(user_message, history):
+                return "", history + [[user_message, None]]
+
+            def bot_response(chatbot, message):
+                global question_count, temp_mp3_files
+                question_count += 1
+
+                # Use the last user message from the chatbot history
+                last_user_message = chatbot[-1][0] if chatbot else message
+
+                response, audio = respond(chatbot, last_user_message)
+
+                # Add all bot responses to the chatbot history
+                for bot_message in response:
+                    chatbot.append((None, bot_message[1]))
+
+                if isinstance(audio, str) and audio.endswith('.mp3'):
+                    temp_mp3_files.append(audio)
+
+                if question_count >= n_of_questions():
+                    conclusion_message = "Thank you for participating in this interview. We have reached the end of our session. I hope this conversation has been helpful. Take care!"
+                    chatbot.append((None, conclusion_message))
+
+                    with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as temp_audio:
+                        audio_path = temp_audio.name
+                        convert_text_to_speech(conclusion_message, audio_path)
+                        audio = audio_path
+                        temp_mp3_files.append(audio_path)
+
+                    # Generate report automatically
+                    report_content, _ = generate_interview_report(interview_history, language)
+                    with tempfile.NamedTemporaryFile(mode='w', suffix=".txt", delete=False,
+                                                     encoding='utf-8') as temp_report:
+                        temp_report.write(report_content)
+                        temp_report_path = temp_report.name
+
+                    _, pdf_path = generate_report_from_file(temp_report_path, language)
+
+                    # Add report to the chat
+                    chatbot.append((None, f"Interview Report:\n\n{report_content}"))
+
+                    # Clean up temporary files
+                    os.unlink(temp_report_path)
+
+                    # Clean up all MP3 files
+                    for mp3_file in temp_mp3_files:
+                        if os.path.exists(mp3_file):
+                            os.unlink(mp3_file)
+                    temp_mp3_files.clear()
+
+                    return chatbot, audio, gr.File(visible=True, value=pdf_path), gr.Textbox(visible=False)
+
+                return chatbot, audio, gr.File(visible=False), gr.Textbox(visible=True)
+
+            msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
+                bot_response, [chatbot, msg], [chatbot, audio_output, pdf_output, msg]
+            )
+
+            send_button.click(user, [msg, chatbot], [msg, chatbot], queue=False).then(
+                bot_response, [chatbot, msg], [chatbot, audio_output, pdf_output, msg]
             )
-            chat_interface.load_event(lambda: (chat_function("", []), None))
 
         with gr.Tab("Upload Document"):
             file_input = gr.File(label="Upload a TXT, PDF, or DOCX file")
-            language_input = gr.Textbox(label="Preferred Language for Report", placeholder="Enter language")
+            language_input = gr.Textbox(label="Preferred Language for Report",
+                                        placeholder="Enter language")
             generate_button = gr.Button("Generate Report")
-            report_output = gr.Textbox(label="Generated Report", lines=20)
+            report_output = gr.Textbox(label="Generated Report", lines=100)
             pdf_output = gr.File(label="Download Report", visible=True)
 
             def generate_report_and_pdf(file, language):
@@ -115,6 +137,7 @@ def create_app():
 
     return demo
 
+
 # Clean up function
 def cleanup():
     global temp_mp3_files, initial_audio_path
@@ -126,6 +149,11 @@ def cleanup():
     if initial_audio_path and os.path.exists(initial_audio_path):
         os.unlink(initial_audio_path)
 
+def cleanup_audio(audio_path):
+    if audio_path and os.path.exists(audio_path):
+        os.remove(audio_path)
+        print(f"Removed audio file: {audio_path}")
+
 if __name__ == "__main__":
     app = create_app()
     try: