app.py

# app.py
import streamlit as st
from model import CodeTeachingAssistant
import time

@st.cache_resource
def init_model():
    """Initialize model with caching to prevent reloading."""
    with st.spinner("Loading AI model (this will be faster on subsequent runs)..."):
        model = CodeTeachingAssistant()
    return model

def main():
    st.title("🚀 Advanced AI Programming Teacher")
    st.write("Programming assistant with real-time analysis")

    # Initialize model with caching
    try:
        model = init_model()
    except Exception as e:
        st.error(f"Error loading model: {str(e)}")
        return

    # Simplified interface with fewer tabs
    tab1, tab2 = st.tabs([
        "💻 Code Analysis",
        "🎯 Learning Path"
    ])

    with tab1:
        st.header("Code Analysis")
        code = st.text_area(
            "Enter your code for analysis:",
            height=200,
            help="Paste your code here for analysis"
        )
        
        if st.button("Analyze Code", type="primary"):
            if code:
                with st.spinner("Analyzing code..."):
                    analysis = model.analyze_code_quality(code)
                    
                    if analysis:
                        st.metric("Complexity Score", f"{analysis.complexity:.2f}")
                        
                        with st.expander("View Suggestions"):
                            for suggestion in analysis.suggestions:
                                st.write(f"• {suggestion}")
                        
                        with st.expander("View Security Issues"):
                            for issue in analysis.security_issues:
                                st.warning(issue)

    with tab2:
        st.header("Learning Path")
        user_level = st.select_slider(
            "Select your expertise level:",
            options=["Beginner", "Intermediate", "Advanced"]
        )
        
        if code:
            with st.spinner("Generating learning path..."):
                learning_path = model.learning_path_generator(code, user_level)
                
                st.write(f"**Current Level:** {learning_path['current_level']}")
                
                with st.expander("View Learning Path"):
                    st.write("**Concepts to Master:**")
                    for concept in learning_path['concepts_to_learn']:
                        st.write(f"• {concept}")
                    
                    st.write("**Estimated Timeline:**")
                    st.write(learning_path['estimated_timeline'])

if __name__ == "__main__":
    main()