Create components/ai_tutor.py

src/components/ai_tutor.py

@@ -0,0 +1,161 @@
+import streamlit as st
+from src.services.ai_service import AITutorService
+from src.utils.session import get_tutor_context
+from datetime import datetime
+import speech_recognition as sr
+import pyttsx3
+import threading
+import queue
+import time
+
+class AITutor:
+    def __init__(self):
+        self.service = AITutorService()
+        self.initialize_speech_components()
+
+    def initialize_speech_components(self):
+        """Initialize text-to-speech and speech recognition"""
+        # Initialize text-to-speech engine
+        if 'tts_engine' not in st.session_state:
+            st.session_state.tts_engine = pyttsx3.init()
+            # Configure voice properties
+            st.session_state.tts_engine.setProperty('rate', 150)
+            st.session_state.tts_engine.setProperty('volume', 0.9)
+            
+            # Get available voices and set a female voice if available
+            voices = st.session_state.tts_engine.getProperty('voices')
+            female_voice = next((voice for voice in voices if 'female' in voice.name.lower()), voices[0])
+            st.session_state.tts_engine.setProperty('voice', female_voice.id)
+
+        # Initialize speech recognition
+        if 'speech_recognizer' not in st.session_state:
+            st.session_state.speech_recognizer = sr.Recognizer()
+            st.session_state.speech_recognizer.energy_threshold = 4000
+            st.session_state.audio_queue = queue.Queue()
+
+    def speak(self, text: str):
+        """Make the AI tutor speak the given text"""
+        def speak_text():
+            st.session_state.tts_engine.say(text)
+            st.session_state.tts_engine.runAndWait()
+
+        # Run speech in a separate thread to avoid blocking
+        thread = threading.Thread(target=speak_text)
+        thread.start()
+
+    def listen(self):
+        """Listen for user speech input"""
+        try:
+            with sr.Microphone() as source:
+                st.write("🎤 Listening...")
+                audio = st.session_state.speech_recognizer.listen(source, timeout=5)
+                text = st.session_state.speech_recognizer.recognize_google(audio)
+                return text
+        except sr.WaitTimeoutError:
+            st.warning("No speech detected. Please try again.")
+        except sr.UnknownValueError:
+            st.warning("Could not understand audio. Please try again.")
+        except sr.RequestError:
+            st.error("Could not access speech recognition service. Please try typing instead.")
+        return None
+
+    def display_chat_interface(self):
+        """Display the enhanced chat interface with avatar and speech"""
+        st.header("AI Tutor")
+
+        # Voice interaction controls
+        col1, col2 = st.columns(2)
+        with col1:
+            voice_enabled = st.toggle("Enable Voice", value=False, key="voice_enabled")
+        with col2:
+            if voice_enabled:
+                if st.button("🎤 Start Speaking"):
+                    user_input = self.listen()
+                    if user_input:
+                        self.handle_user_input(user_input)
+
+        # Display avatar
+        self.service.display_avatar(state='neutral')
+
+        # Topic selection
+        topics = [None, 'Physics', 'Mathematics', 'Computer Science', 'Artificial Intelligence']
+        selected_topic = st.selectbox(
+            "Select Topic",
+            topics,
+            format_func=lambda x: 'All Topics' if x is None else x,
+            key="topic_selector"
+        )
+
+        context = get_tutor_context()
+        if selected_topic != context['current_topic']:
+            context['current_topic'] = selected_topic
+
+        # Display chat container
+        chat_container = st.container()
+        with chat_container:
+            # Display chat history with avatar states
+            for message in context['chat_history']:
+                with st.chat_message(message["role"]):
+                    st.write(message["content"])
+                    if message["role"] == "assistant":
+                        self.service.display_avatar(state='happy')
+                        if voice_enabled and message.get('speak', True):
+                            self.speak(message["content"])
+                            message['speak'] = False  # Prevent speaking the same message again
+
+        # Chat input
+        if prompt := st.chat_input("Ask your question or click the microphone to speak"):
+            self.handle_user_input(prompt)
+
+    def handle_user_input(self, user_input: str):
+        """Process user input and generate response"""
+        # Show thinking avatar
+        self.service.display_avatar(state='thinking')
+        
+        # Add user message
+        context = get_tutor_context()
+        context['chat_history'].append({
+            "role": "user",
+            "content": user_input
+        })
+        
+        # Generate and display AI response
+        response = self.service.generate_response(user_input)
+        
+        # Add AI response
+        context['chat_history'].append({
+            "role": "assistant",
+            "content": response,
+            "speak": True  # Mark for speaking
+        })
+        
+        # Show happy avatar and rerun
+        self.service.display_avatar(state='happy')
+        st.rerun()
+
+    def display_learning_metrics(self):
+        """Display learning progress and engagement metrics"""
+        with st.sidebar:
+            st.subheader("Learning Metrics")
+            
+            context = get_tutor_context()
+            # Engagement score
+            metrics = context['engagement_metrics']
+            if metrics:
+                avg_sentiment = sum(m['sentiment_score'] for m in metrics) / len(metrics)
+                st.metric(
+                    "Engagement Score",
+                    f"{avg_sentiment:.2f}",
+                    delta="0.1" if avg_sentiment > 0.5 else "-0.1"
+                )
+            
+            # Interaction stats
+            if context['chat_history']:
+                st.metric(
+                    "Questions Asked",
+                    len([m for m in context['chat_history'] if m['role'] == 'user'])
+                )
+            
+            # Topic focus
+            if context['current_topic']:
+                st.info(f"Current focus: {context['current_topic']}")