app.py

import streamlit as st
import json
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import time

# Page configuration
st.set_page_config(
    page_title="Portfolio Chatbot Test",
    page_icon="🤖",
    layout="wide"
)

# Initialize session state
if 'messages' not in st.session_state:
    st.session_state.messages = []

def load_knowledge_base():
    """Load the knowledge base from JSON file"""
    try:
        with open('knowledge_base.json', 'r', encoding='utf-8') as f:
            return json.load(f)
    except Exception as e:
        st.error(f"Error loading knowledge base: {str(e)}")
        return {}

def get_context(query: str, knowledge_base: dict) -> str:
    """Get relevant context from knowledge base based on query"""
    query_lower = query.lower()
    contexts = []
    
    # Project context
    if "project" in query_lower:
        if "projects" in knowledge_base:
            contexts.extend([
                f"{name}: {desc}"
                for name, desc in knowledge_base["projects"].items()
            ])
            
    # Skills context
    elif any(keyword in query_lower for keyword in ["skill", "experience", "capability"]):
        if "personal_details" in knowledge_base and "skills" in knowledge_base["personal_details"]:
            contexts.extend([
                f"{skill}: {desc}"
                for skill, desc in knowledge_base["personal_details"]["skills"].items()
            ])
            
    # Default context
    else:
        contexts = [
            f"Name: {knowledge_base.get('personal_details', {}).get('full_name', 'Manyue')}",
            "Summary: I am an aspiring AI/ML engineer with experience in Python, Machine Learning, and Data Analysis."
        ]
    
    return "\n".join(contexts)

def initialize_model():
    """Initialize the model and tokenizer"""
    try:
        # For testing, use a smaller model
        model_name = "meta-llama/Llama-2-7b-chat-hf"  # You'll need to adjust this
        
        tokenizer = AutoTokenizer.from_pretrained(model_name)
        model = AutoModelForCausalLM.from_pretrained(
            model_name,
            torch_dtype=torch.float16,
            device_map="auto"
        )
        return tokenizer, model
    except Exception as e:
        st.error(f"Error initializing model: {str(e)}")
        return None, None

def main():
    st.title("Portfolio Chatbot Testing Interface")
    st.write("Test the chatbot's responses and interaction patterns")
    
    # Load knowledge base
    knowledge_base = load_knowledge_base()
    
    # Create two columns for layout
    col1, col2 = st.columns([2, 1])
    
    with col1:
        st.subheader("Chat Interface")
        # Display chat messages from history
        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("What would you like to know?"):
            # Add user message to chat history
            st.session_state.messages.append({"role": "user", "content": prompt})
            
            # Get context for the query
            context = get_context(prompt, knowledge_base)
            
            # For now, just echo back a response (replace with actual model response later)
            response = f"Test Response: Let me tell you about that based on my experience..."
            
            # Display assistant response in chat message container
            with st.chat_message("assistant"):
                st.markdown(response)
            
            # Add assistant response to chat history
            st.session_state.messages.append({"role": "assistant", "content": response})
    
    with col2:
        st.subheader("Testing Tools")
        if st.button("Clear Chat History"):
            st.session_state.messages = []
            st.experimental_rerun()
        
        st.subheader("Sample Questions")
        if st.button("Tell me about your ML projects"):
            st.session_state.messages.append({
                "role": "user",
                "content": "Tell me about your ML projects"
            })
            st.experimental_rerun()
        
        if st.button("What are your Python skills?"):
            st.session_state.messages.append({
                "role": "user",
                "content": "What are your Python skills?"
            })
            st.experimental_rerun()

if __name__ == "__main__":
    main()