# import os
# import streamlit as st
# from dotenv import load_dotenv
# import google.generativeai as gen_ai
#
#
# # Load environvent variables
# load_dotenv()
#
# # Configure Streamlit page settings
# st.set_page_config(
#     page_title="Chat with Gemini-Pro!",
#     page_icon=":brain:", # Favicon emoji
#     layout="centered", # Page layout option
# )
#
# Google_API_Key = os.getenv("Google_API_Key")
#
# # Set up Google Gemni-Pro AI Model
# gen_ai.configure(api_key=Google_API_Key)
# model = gen_ai.GenerativeModel('gemini-pro')
#
# # Function to translate roles between Gemini-Pro and streamlit terminology
#
# def translate_role_for_streamlit(user_role):
#     if user_role == 'model':
#         return 'assistant'
#     else: return user_role
#
# # Initialize chat session in streamlit if not already present
# if "chat_session" not in st.session_state:
#     st.session_state.chat_session = model.start_chat(history=[])
#
# # Display the chatbot's title on the page
# st.title("🤖 Gemini Pro - ChatBot")
#
# # Display the chat history
# for message in st.session_state.chat_session.history:
#     with st.chat_message(translate_role_for_streamlit(message.role)):
#         st.markdown(message.parts[0].text)
#
#
# # Input field for user's message
# user_prompt = st.chat_input("Ask Gemini Pro...")
#
# if user_prompt:
#     # Add user's message to chat and display it
#     st.chat_message("user").markdown(user_prompt)
#
#     # Send user's message to chat and display it
#     gemini_response = st.session_state.chat_session.send_message(user_prompt)
#
#     # Display Gemini-Pro's response
#     with st.chat_message('assistant'):
#         st.markdown(gemini_response.text)






#
# import os
# import json
# import streamlit as st
# import google.generativeai as gen_ai
# from dotenv import load_dotenv
# import speech_recognition as sr
# import pyttsx3
#
# # Load environment variables
# load_dotenv()
# Google_API_Key = os.getenv("Google_API_Key")
#
# # Configure Streamlit page settings
# st.set_page_config(
#     page_title="Chat with Gemini-Pro!",
#     page_icon="🤖",
#     layout="wide",
# )
#
# # Set up Google Gemini-Pro AI Model
# gen_ai.configure(api_key=Google_API_Key)
# model = gen_ai.GenerativeModel('gemini-pro')
#
# # Initialize chatbot memory
# if "chat_history" not in st.session_state:
#     try:
#         with open("chat_history.json", "r") as f:
#             st.session_state.chat_history = json.load(f)
#     except FileNotFoundError:
#         st.session_state.chat_history = []
#
#
# # Save chat history
# def save_chat_history():
#     with open("chat_history.json", "w") as f:
#         json.dump(st.session_state.chat_history, f)
#
#
# # Sidebar settings
# with st.sidebar:
#     st.subheader("⚙️ Settings")
#
#     # Theme selection
#     theme = st.radio("Select Theme", ["🌞 Light", "🌙 Dark"])
#
#     # Clear chat history button
#     if st.button("🗑️ Clear Chat History"):
#         st.session_state.chat_history = []
#         save_chat_history()
#         st.experimental_rerun()
#
# # Apply dark mode styling
# if theme == "🌙 Dark":
#     st.markdown(
#         """
#         <style>
#         body {background-color: #333; color: white;}
#         .stChatMessage {background-color: #444; color: white;}
#         </style>
#         """,
#         unsafe_allow_html=True
#     )
#
# # Display chatbot title
# st.title("🤖 Gemini Pro - ChatBot")
#
# # Display chat history
# for message in st.session_state.chat_history:
#     with st.chat_message(message["role"]):
#         st.markdown(message["content"])
#
# # Speech recognition & text-to-speech setup
# recognizer = sr.Recognizer()
# engine = pyttsx3.init()
#
# # Voice input button
# if st.button("🎤 Speak"):
#     with sr.Microphone() as source:
#         st.write("Listening...")
#         audio = recognizer.listen(source)
#         try:
#             user_prompt = recognizer.recognize_google(audio)
#             st.chat_message("user").markdown(user_prompt)
#         except:
#             st.error("Could not understand. Try again.")
#
# # Text input
# user_prompt = st.chat_input("Ask Gemini Pro...")
#
# if user_prompt:
#     # Add user message to chat history
#     st.session_state.chat_history.append({"role": "user", "content": user_prompt})
#
#     # Display user message
#     st.chat_message("user").markdown(user_prompt)
#
#     # Get response from Gemini-Pro
#     gemini_response = model.generate_content(user_prompt)
#
#     # Add chatbot response to history
#     st.session_state.chat_history.append({"role": "assistant", "content": gemini_response.text})
#
#     # Display chatbot response
#     with st.chat_message("assistant"):
#         st.markdown(gemini_response.text)
#
#     # Save chat history
#     save_chat_history()
#
#     # Text-to-Speech response
#     engine.say(gemini_response.text)
#     engine.runAndWait()





# import os
# import json
# import streamlit as st
# import google.generativeai as gen_ai
# from dotenv import load_dotenv
# import speech_recognition as sr
# import pyttsx3
#
# # Load environment variables
# load_dotenv()
# Google_API_Key = os.getenv("Google_API_Key")
#
# # Configure Streamlit page settings
# st.set_page_config(
#     page_title="Chat with Gemini-Pro!",
#     page_icon="🤖",
#     layout="wide",
# )
#
# # Apply custom CSS for UI/UX improvements
# st.markdown(
#     """
#     <style>
#     .stChatMessage { padding: 10px; border-radius: 10px; margin: 5px 0; }
#     .user { background-color: #DCF8C6; }
#     .assistant { background-color: #E3E3E3; }
#     .sidebar .sidebar-content { background-color: #f0f2f6; }
#     .chat-container { max-width: 700px; margin: auto; }
#     </style>
#     """,
#     unsafe_allow_html=True
# )
#
# # Set up Google Gemini-Pro AI Model
# gen_ai.configure(api_key=Google_API_Key)
# model = gen_ai.GenerativeModel('gemini-pro')
#
# # Initialize chatbot memory
# if "chat_history" not in st.session_state:
#     try:
#         with open("chat_history.json", "r") as f:
#             st.session_state.chat_history = json.load(f)
#     except (FileNotFoundError, json.JSONDecodeError):
#         st.session_state.chat_history = []
#
#
# # Save chat history
# def save_chat_history():
#     with open("chat_history.json", "w") as f:
#         json.dump(st.session_state.chat_history, f)
#
#
# # Sidebar settings
# with st.sidebar:
#     st.subheader("⚙️ Settings")
#
#     # Theme selection
#     theme = st.radio("Select Theme", ["🌞 Light", "🌙 Dark"])
#
#     # Clear chat history button
#     if st.button("🗑️ Clear Chat History"):
#         st.session_state.chat_history = []
#         save_chat_history()
#         st.experimental_rerun()
#
# # Apply dark mode styling
# if theme == "🌙 Dark":
#     st.markdown(
#         """
#         <style>
#         body {background-color: #1e1e1e; color: white;}
#         .stChatMessage {background-color: #444; color: white;}
#         .sidebar .sidebar-content {background-color: #333;}
#         .stTextInput, .stButton, .stRadio {background-color: #333; color: white;}
#         </style>
#         """,
#         unsafe_allow_html=True
#     )
#
# # Display chatbot title
# st.title("🤖 Gemini Pro - AI ChatBot")
#
# # Chat container
# st.markdown('<div class="chat-container">', unsafe_allow_html=True)
#
# # Display chat history
# for message in st.session_state.chat_history:
#     role = message["role"]
#     avatar = "👤" if role == "user" else "🤖"
#     bg_color = "user" if role == "user" else "assistant"
#
#     with st.chat_message(role):
#         st.markdown(f'<div class="{bg_color} stChatMessage">{avatar} {message["content"]}</div>',
#                     unsafe_allow_html=True)
#
# # Speech recognition & text-to-speech setup
# recognizer = sr.Recognizer()
# # engine = pyttsx3.init()
# engine = pyttsx3.init()
# engine.setProperty('rate', 150)  # Adjust speech rate
# engine.setProperty('voice', engine.getProperty('voices')[0].id)  # Set a specific voice
#
# # Voice input button
# if st.button("🎤 Speak"):
#     with sr.Microphone() as source:
#         st.write("Listening...")
#         audio = recognizer.listen(source)
#         try:
#             user_prompt = recognizer.recognize_google(audio)
#             st.session_state.chat_history.append({"role": "user", "content": user_prompt})
#             st.chat_message("user").markdown(user_prompt)
#             # Trigger chatbot response
#             gemini_response = model.generate_content(user_prompt)
#             st.session_state.chat_history.append({"role": "assistant", "content": gemini_response.text})
#             st.chat_message("assistant").markdown(gemini_response.text)
#             save_chat_history()
#             engine.say(gemini_response.text)
#             engine.runAndWait()
#         except sr.UnknownValueError:
#             st.error("Sorry, I could not understand the audio.")
#         except sr.RequestError:
#             st.error("Could not request results from the speech recognition service.")
# # Text input
# user_prompt = st.chat_input("Ask Gemini Pro...")
#
# if user_prompt:
#     # Add user message to chat history
#     st.session_state.chat_history.append({"role": "user", "content": user_prompt})
#
#     # Display user message
#     st.chat_message("user").markdown(user_prompt)
#
#     # Get response from Gemini-Pro
#     # gemini_response = model.generate_content(user_prompt)
#     try:
#         gemini_response = model.generate_content(user_prompt)
#     except Exception as e:
#         st.error(f"An error occurred: {e}")
#         gemini_response = type('Object', (), {'text': 'Sorry, I could not generate a response.'})
#
#     # Add chatbot response to history
#     st.session_state.chat_history.append({"role": "assistant", "content": gemini_response.text})
#
#     # Display chatbot response
#     with st.chat_message("assistant"):
#         st.markdown(gemini_response.text)
#
#     # Save chat history
#     save_chat_history()
#
#     # Text-to-Speech response
#     engine.say(gemini_response.text)
#     engine.runAndWait()
#
# st.markdown('</div>', unsafe_allow_html=True)
#










# import os
# import streamlit as st
# import google.generativeai as gen_ai
# import pyttsx3
# import threading
# from dotenv import load_dotenv
#
# # Load environment variables
# load_dotenv()
#
# # Configure Streamlit page settings
# st.set_page_config(
#     page_title="Gemini-Pro ChatBot",
#     page_icon="🤖",  # Favicon emoji
#     layout="centered",  # Page layout option
# )
#
# # Retrieve Google API Key
# Google_API_Key = os.getenv("Google_API_Key")
#
# # Set up Google Gemini-Pro AI Model
# gen_ai.configure(api_key=Google_API_Key)
# model = gen_ai.GenerativeModel('gemini-pro')
#
# # Function to translate roles between Gemini-Pro and Streamlit terminology
# def translate_role_for_streamlit(user_role):
#     return "assistant" if user_role == "model" else user_role
#
# # Function to handle text-to-speech (TTS) in a separate thread
# def speak_text(text):
#     engine = pyttsx3.init()
#     engine.say(text)
#     engine.runAndWait()
#
# # Initialize chat session in Streamlit if not already present
# if "chat_session" not in st.session_state:
#     st.session_state.chat_session = model.start_chat(history=[])
#
# # Display chatbot title and description
# st.markdown("<h1 style='text-align: center; color: #4A90E2;'>🤖 Gemini-Pro ChatBot</h1>", unsafe_allow_html=True)
# st.markdown("<p style='text-align: center; font-size: 16px;'>Ask me anything! I'm powered by Gemini-Pro AI.</p>", unsafe_allow_html=True)
#
# # Display chat history
# for message in st.session_state.chat_session.history:
#     with st.chat_message(translate_role_for_streamlit(message.role)):
#         st.markdown(message.parts[0].text)
#
# # User input field
# user_prompt = st.chat_input("Ask Gemini Pro...")
#
# # If user enters a prompt
# if user_prompt:
#     # Display user's message
#     st.chat_message("user").markdown(user_prompt)
#
#     # Show a loading indicator while waiting for a response
#     with st.spinner("Thinking..."):
#         gemini_response = st.session_state.chat_session.send_message(user_prompt)
#
#     # Display Gemini-Pro's response
#     with st.chat_message("assistant"):
#         st.markdown(gemini_response.text)
#
#     # Run text-to-speech in the background
#     threading.Thread(target=speak_text, args=(gemini_response.text,), daemon=True).start()






#
#
#
#
#
#
#
#
#
#
# import os
# import streamlit as st
# import google.generativeai as gen_ai
# import pyttsx3
# import threading
# from dotenv import load_dotenv
#
# # Load environment variables
# load_dotenv()
#
# # Configure Streamlit page settings
# st.set_page_config(
#     page_title="Gemini-Pro ChatBot",
#     page_icon="🤖",
#     layout="centered",
# )
#
# # Retrieve Google API Key
# Google_API_Key = os.getenv("Google_API_Key")
#
# # Set up Google Gemini-Pro AI Model
# gen_ai.configure(api_key=Google_API_Key)
# model = gen_ai.GenerativeModel('gemini-pro')
#
# # Function to translate roles between Gemini-Pro and Streamlit terminology
# def translate_role_for_streamlit(user_role):
#     return "assistant" if user_role == "model" else user_role
#
# # Initialize text-to-speech engine
# if "tts_engine" not in st.session_state:
#     st.session_state.tts_engine = pyttsx3.init()
#
# def stop_speech():
#     """Stop the current speech if running."""
#     st.session_state.tts_engine.stop()
#
# def speak_text(text):
#     """Stop previous speech and start speaking new text."""
#     stop_speech()  # Stop any ongoing speech
#     st.session_state.tts_engine.say(text)
#     st.session_state.tts_engine.runAndWait()
#
# # Initialize chat session in Streamlit if not already present
# if "chat_session" not in st.session_state:
#     st.session_state.chat_session = model.start_chat(history=[])
#
# # Display chatbot title and description
# st.markdown("<h1 style='text-align: center; color: #4A90E2;'>🤖 Gemini-Pro ChatBot</h1>", unsafe_allow_html=True)
# st.markdown("<p style='text-align: center; font-size: 16px;'>Ask me anything! I'm powered by Gemini-Pro AI.</p>", unsafe_allow_html=True)
#
# # Display chat history
# for message in st.session_state.chat_session.history:
#     with st.chat_message(translate_role_for_streamlit(message.role)):
#         st.markdown(message.parts[0].text)
#
# # User input field
# user_prompt = st.chat_input("Ask Gemini Pro...")
#
# # If user enters a prompt
# if user_prompt:
#     # Display user's message
#     st.chat_message("user").markdown(user_prompt)
#
#     # Show a loading indicator while waiting for a response
#     with st.spinner("Thinking..."):
#         gemini_response = st.session_state.chat_session.send_message(user_prompt)
#
#     # Display Gemini-Pro's response
#     with st.chat_message("assistant"):
#         st.markdown(gemini_response.text)
#
#     # Run text-to-speech in the background (stopping previous speech first)
#     threading.Thread(target=speak_text, args=(gemini_response.text,), daemon=True).start()


# import os
# import streamlit as st
# import google.generativeai as gen_ai
# import pyttsx3
# import threading
# from dotenv import load_dotenv
#
# # Load environment variables
# load_dotenv()
#
# # Configure Streamlit page settings
# st.set_page_config(
#     page_title="Gemini-Pro ChatBot",
#     page_icon="🤖",
#     layout="centered",
# )
#
# # Retrieve Google API Key
# Google_API_Key = os.getenv("Google_API_Key")
#
# # Set up Google Gemini-Pro AI Model
# gen_ai.configure(api_key=Google_API_Key)
# model = gen_ai.GenerativeModel('gemini-pro')
#
# # Function to translate roles between Gemini-Pro and Streamlit terminology
# def translate_role_for_streamlit(user_role):
#     return "assistant" if user_role == "model" else user_role
#
# # Initialize text-to-speech engine
# if "tts_engine" not in st.session_state:
#     st.session_state.tts_engine = pyttsx3.init()
#
# # Initialize threading event for speech control
# if "speech_event" not in st.session_state:
#     st.session_state.speech_event = threading.Event()
#
# def stop_speech():
#     """Stop the current speech if running."""
#     st.session_state.speech_event.set()  # Set the event to stop speech
#     st.session_state.tts_engine.stop()
#
# def speak_text(text):
#     """Stop previous speech and start speaking new text."""
#     stop_speech()  # Stop any ongoing speech
#     st.session_state.speech_event.clear()  # Clear the event for new speech
#     st.session_state.tts_engine.say(text)
#     st.session_state.tts_engine.runAndWait()
#
# # Initialize chat session in Streamlit if not already present
# if "chat_session" not in st.session_state:
#     st.session_state.chat_session = model.start_chat(history=[])
#
# # Display chatbot title and description
# st.markdown("<h1 style='text-align: center; color: #4A90E2;'>🤖 Gemini-Pro ChatBot</h1>", unsafe_allow_html=True)
# st.markdown("<p style='text-align: center; font-size: 16px;'>Ask me anything! I'm powered by Gemini-Pro AI.</p>", unsafe_allow_html=True)
#
# # Display chat history
# for message in st.session_state.chat_session.history:
#     with st.chat_message(translate_role_for_streamlit(message.role)):
#         st.markdown(message.parts[0].text)
#
# # User input field
# user_prompt = st.chat_input("Ask Gemini Pro...")
#
# # If user enters a prompt
# if user_prompt:
#     # Display user's message
#     st.chat_message("user").markdown(user_prompt)
#
#     # Show a loading indicator while waiting for a response
#     with st.spinner("Thinking..."):
#         gemini_response = st.session_state.chat_session.send_message(user_prompt)
#
#     # Display Gemini-Pro's response
#     with st.chat_message("assistant"):
#         st.markdown(gemini_response.text)
#
#     # Run text-to-speech in the background (stopping previous speech first)
#     threading.Thread(target=speak_text, args=(gemini_response.text,), daemon=True).start()






#
# import os
# import streamlit as st
# import google.generativeai as gen_ai
# import pyttsx3
# import threading
# from dotenv import load_dotenv
#
# # Load environment variables
# load_dotenv()
#
# # Configure Streamlit page settings
# st.set_page_config(
#     page_title="Gemini-Pro ChatBot",
#     page_icon="🤖",
#     layout="centered",
# )
#
# # Retrieve Google API Key
# Google_API_Key = os.getenv("Google_API_Key")
#
# # Set up Google Gemini-Pro AI Model
# gen_ai.configure(api_key=Google_API_Key)
# model = gen_ai.GenerativeModel('gemini-pro')
#
# # Function to translate roles between Gemini-Pro and Streamlit terminology
# def translate_role_for_streamlit(user_role):
#     return "assistant" if user_role == "model" else user_role
#
# # Initialize text-to-speech engine
# if "tts_engine" not in st.session_state:
#     st.session_state.tts_engine = pyttsx3.init()
#
# def stop_speech():
#     """Stop the current speech if running."""
#     st.session_state.tts_engine.stop()
#
# def speak_text(text):
#     """Stop previous speech and start speaking new text."""
#     stop_speech()  # Stop any ongoing speech
#     st.session_state.tts_engine.say(text)
#     st.session_state.tts_engine.runAndWait()
#
# # Initialize chat session in Streamlit if not already present
# if "chat_session" not in st.session_state:
#     st.session_state.chat_session = model.start_chat(history=[])
#
# # Display chatbot title and description
# st.markdown("<h1 style='text-align: center; color: #4A90E2;'>🤖 Gemini-Pro ChatBot</h1>", unsafe_allow_html=True)
# st.markdown("<p style='text-align: center; font-size: 16px;'>Ask me anything! I'm powered by Gemini-Pro AI.</p>", unsafe_allow_html=True)
#
# # Display chat history
# for message in st.session_state.chat_session.history:
#     with st.chat_message(translate_role_for_streamlit(message.role)):
#         st.markdown(message.parts[0].text)
#
# # User input field
# user_prompt = st.chat_input("Ask Gemini Pro...")
#
# # If user enters a prompt
# if user_prompt:
#     # Display user's message
#     st.chat_message("user").markdown(user_prompt)
#
#     # Show a loading indicator while waiting for a response
#     with st.spinner("Thinking..."):
#         gemini_response = st.session_state.chat_session.send_message(user_prompt)
#
#     # Display Gemini-Pro's response
#     with st.chat_message("assistant"):
#         st.markdown(gemini_response.text)
#
#     # Run text-to-speech in the background (stopping previous speech first)
#     threading.Thread(target=speak_text, args=(gemini_response.text,), daemon=True).start()
#
#
#
#













#
#
# import os
# import streamlit as st
# import google.generativeai as gen_ai
# import pyttsx3
# import threading
# from dotenv import load_dotenv
# import speech_recognition as sr
#
# # Load environment variables
# load_dotenv()
#
# # Configure Streamlit page settings
# st.set_page_config(
#     page_title="Gemini-Pro ChatBot",
#     page_icon="🤖",  # Favicon emoji
#     layout="centered",  # Page layout option
# )
#
# # Retrieve Google API Key
# Google_API_Key = os.getenv("Google_API_Key")
#
# # Set up Google Gemini-Pro AI Model
# gen_ai.configure(api_key=Google_API_Key)
# model = gen_ai.GenerativeModel('gemini-pro')
#
# # Initialize text-to-speech engine
# if "tts_engine" not in st.session_state:
#     st.session_state.tts_engine = pyttsx3.init()
#
# # Speech-to-text function
# def listen_for_input():
#     recognizer = sr.Recognizer()
#     with sr.Microphone() as source:
#         print("Listening...")
#         audio = recognizer.listen(source)
#         try:
#             return recognizer.recognize_google(audio)
#         except sr.UnknownValueError:
#             return "Sorry, I did not catch that."
#         except sr.RequestError:
#             return "Sorry, there was an error with the speech recognition service."
#
# # Stop previous speech and speak the new text
# def speak_text(text):
#     stop_speech()  # Stop any ongoing speech
#     st.session_state.tts_engine.say(text)
#     st.session_state.tts_engine.runAndWait()
#
# # Stop ongoing speech
# def stop_speech():
#     st.session_state.tts_engine.stop()
#
# # Function to translate roles between Gemini-Pro and Streamlit terminology
# def translate_role_for_streamlit(user_role):
#     return "assistant" if user_role == "model" else user_role
#
# # Initialize chat session in Streamlit if not already present
# if "chat_session" not in st.session_state:
#     st.session_state.chat_session = model.start_chat(history=[])
#
# # Display chatbot title and description
# st.markdown("<h1 style='text-align: center; color: #4A90E2;'>🤖 Gemini-Pro ChatBot</h1>", unsafe_allow_html=True)
# st.markdown("<p style='text-align: center; font-size: 16px;'>Ask me anything! I'm powered by Gemini-Pro AI.</p>", unsafe_allow_html=True)
#
# # Display chat history
# for message in st.session_state.chat_session.history:
#     with st.chat_message(translate_role_for_streamlit(message.role)):
#         st.markdown(message.parts[0].text)
#
# # User input field (with optional speech-to-text input)
# user_prompt = st.chat_input("Ask Gemini Pro...")
#
# if st.button("Use Voice Input"):
#     user_prompt = listen_for_input()
#
# # If user enters a prompt
# if user_prompt:
#     # Display user's message
#     st.chat_message("user").markdown(user_prompt)
#
#     # Show a loading indicator while waiting for a response
#     with st.spinner("Thinking..."):
#         gemini_response = st.session_state.chat_session.send_message(user_prompt)
#
#     # Display Gemini-Pro's response
#     with st.chat_message("assistant"):
#         st.markdown(gemini_response.text)
#
#     # Run text-to-speech in the background
#     threading.Thread(target=speak_text, args=(gemini_response.text,), daemon=True).start()








import os
import streamlit as st
import google.generativeai as gen_ai
import pyttsx3
import threading
from dotenv import load_dotenv

# Load environment variables
load_dotenv()

# Configure Streamlit page settings
st.set_page_config(
    page_title="Gemini-Pro ChatBot",
    page_icon="🤖",  # Favicon emoji
    layout="centered",  # Page layout option
)

# Retrieve Google API Key
Google_API_Key = os.getenv("Google_API_Key")

# Set up Google Gemini-Pro AI Model
gen_ai.configure(api_key=Google_API_Key)
model = gen_ai.GenerativeModel('gemini-pro')

# Function to translate roles between Gemini-Pro and Streamlit terminology
def translate_role_for_streamlit(user_role):
    return "assistant" if user_role == "model" else user_role

# Initialize the TTS engine if not already present in session state
if "tts_engine" not in st.session_state:
    st.session_state.tts_engine = pyttsx3.init()

# Function to stop speech if any ongoing speech is happening
def stop_speech():
    if hasattr(st.session_state, "tts_engine"):
        st.session_state.tts_engine.stop()

# Function to handle text-to-speech (TTS) in a separate thread
def speak_text(text):
    try:
        stop_speech()  # Stop any ongoing speech
        st.session_state.tts_engine.say(text)
        st.session_state.tts_engine.runAndWait()
    except Exception as e:
        st.error(f"Error in TTS: {e}")

# Initialize chat session in Streamlit if not already present
if "chat_session" not in st.session_state:
    st.session_state.chat_session = model.start_chat(history=[])

# Display chatbot title and description
st.markdown("<h1 style='text-align: center; color: #4A90E2;'>🤖 Gemini-Pro ChatBot</h1>", unsafe_allow_html=True)
st.markdown("<p style='text-align: center; font-size: 16px;'>Ask me anything! I'm powered by Gemini-Pro AI.</p>", unsafe_allow_html=True)

# Display chat history
for message in st.session_state.chat_session.history:
    with st.chat_message(translate_role_for_streamlit(message.role)):
        st.markdown(message.parts[0].text)

# User input field
user_prompt = st.chat_input("Ask Gemini Pro...")

# If user enters a prompt
if user_prompt:
    # Display user's message
    st.chat_message("user").markdown(user_prompt)

    # Show a loading indicator while waiting for a response
    with st.spinner("Thinking..."):
        gemini_response = st.session_state.chat_session.send_message(user_prompt)

    # Display Gemini-Pro's response
    with st.chat_message("assistant"):
        st.markdown(gemini_response.text)

    # Run text-to-speech in the background
    threading.Thread(target=speak_text, args=(gemini_response.text,), daemon=True).start()