app.py

import streamlit as st
from googletrans import Translator
from langdetect import detect
import time
import warnings
import os

# Suppress warnings
warnings.filterwarnings("ignore")

# Set page config
st.set_page_config(
    page_title="GUVI Multilingual Chatbot",
    page_icon="🤖",
    layout="wide",
    initial_sidebar_state="expanded"
)


# Initialize Google Translator
translator = Translator()

# Load GUVI dataset
@st.cache_resource
def load_guvi_dataset():
    qa_pairs = {}
    try:
        with open("GUVI dataset.txt", "r", encoding="utf-8") as file:
            lines = file.readlines()
            for i in range(0, len(lines), 2):
                if i+1 < len(lines):
                    question = lines[i].strip()
                    answer = lines[i+1].strip()
                    qa_pairs[question.lower()] = answer
    except FileNotFoundError:
        st.error("GUVI dataset (guvi.txt) not found. Using GPT-only responses.")
    return qa_pairs

# Initialize dataset
qa_pairs = load_guvi_dataset()

# Language mapping
language_map = {
    "English": "en",
    "Hindi": "hi",
    "Tamil": "ta",
    "Telugu": "te",
    "Kannada": "kn",
    "Malayalam": "ml",
    "Bengali": "bn",
    "Marathi": "mr"
}

# Function to detect language
def detect_language(text):
    try:
        return detect(text)
    except:
        return "en"

# Function to translate text using Google Translator
def translate_text(text, target_lang, source_lang='auto'):
    if source_lang == target_lang:
        return text
    
    try:
        translation = translator.translate(text, src=source_lang, dest=target_lang)
        return translation.text
    except Exception as e:
        st.warning(f"Translation error: {e}. Returning original text.")
        return text

# Function to generate response using GPT or GUVI dataset
def generate_response(prompt):
    # First check if the question exists in our GUVI dataset
    lower_prompt = prompt.lower()
    if lower_prompt in qa_pairs:
        return qa_pairs[lower_prompt]
    
    # If not found in dataset, use Hugging Face model
    inputs = models["chat_tokenizer"](prompt, return_tensors="pt", max_length=512, truncation=True)
    
    with torch.no_grad():
        outputs = models["chat_model"].generate(
            **inputs,
            max_length=200,
            num_beams=5,
            early_stopping=True,
            temperature=0.7
        )
    
    return models["chat_tokenizer"].decode(outputs[0], skip_special_tokens=True)


# Streamlit UI
def main():
    # Custom CSS
    st.markdown("""
    <style>
    .stApp {
        background-color: #f5f5f5;
    }
    .chat-container {
        background-color: white;
        border-radius: 10px;
        padding: 20px;
        box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
        margin-bottom: 20px;
    }
    .user-message {
        background-color: #e3f2fd;
        padding: 10px;
        border-radius: 10px;
        margin-bottom: 10px;
    }
    .bot-message {
        background-color: #f5f5f5;
        padding: 10px;
        border-radius: 10px;
        margin-bottom: 10px;
    }
    .stSelectbox > div > div {
        border: 1px solid #2196F3 !important;
    }
    .stTextInput > div > div > input {
        border: 1px solid #2196F3 !important;
    }
    </style>
    """, unsafe_allow_html=True)
    
    # Header
    st.title("GUVI Multilingual Chatbot 🤖")
    st.markdown("""
    Welcome to the GUVI Multilingual Chatbot! This assistant can help you with:
    - Course information and recommendations
    - Career guidance and mentorship
    - Technical support
    - General queries about GUVI platform
    
    **Available in multiple Indian languages!**
    """)
    
    # Sidebar
    st.sidebar.title("Settings")
    selected_language = st.sidebar.selectbox(
        "Select your preferred language:",
        list(language_map.keys()),
        index=0
    )
    
    st.sidebar.markdown("---")
    st.sidebar.markdown("### About")
    st.sidebar.markdown("""
    This chatbot is powered by:
    - OpenAI GPT
    - Google Translator
    - GUVI's custom knowledge base
    
    Developed for GUVI's multilingual learners.
    """)
    
    # Initialize chat history
    if "messages" not in st.session_state:
        st.session_state.messages = []
    
    # Display chat messages from history on app rerun
    for message in st.session_state.messages:
        with st.chat_message(message["role"]):
            st.markdown(message["content"])
    
    # Accept user input
    if prompt := st.chat_input("Type your message here..."):
        # Add user message to chat history
        st.session_state.messages.append({"role": "user", "content": prompt})
        
        # Detect language of input
        input_lang = detect_language(prompt)
        target_lang = language_map[selected_language]
        
        # Display user message in chat message container
        with st.chat_message("user"):
            st.markdown(prompt)
        
        # Show thinking indicator
        with st.spinner("Thinking..."):
            # Translate to English if needed
            if input_lang != "en":
                translated_prompt = translate_text(prompt, "en", input_lang)
            else:
                translated_prompt = prompt
            
            # Generate response
            response = generate_response(translated_prompt)
            
            # Translate back to user's language if needed
            if target_lang != "en":
                final_response = translate_text(response, target_lang, "en")
            else:
                final_response = response
            
            # Add a small delay for natural conversation flow
            time.sleep(0.5)
            
            # Display assistant response in chat message container
            with st.chat_message("assistant"):
                st.markdown(final_response)
            
            # Add assistant response to chat history
            st.session_state.messages.append({"role": "assistant", "content": final_response})

if __name__ == "__main__":
    main()