Update app.py

app.py

@@ -1,36 +1,110 @@
 import streamlit as st
-from utils.constants import metadata_path, embeddings_path
-from question_handler import find_top_question, generate_detailed_prompt
-from code_executor import execute_code
-from utils.openai_client import generate_response
 import pandas as pd
 import numpy as np
+from utils.constants import metadata_path, embeddings_path
+from utils.embeddings_utils import load_model
+from question_handler import find_top_question, generate_detailed_prompt, extract_code_and_test_case
+from utils.openai_client import generate_response
+from code_executor import execute_code
 
-# Load metadata and embeddings
+# Load metadata and embeddings once at app startup
 metadata = pd.read_csv(metadata_path)
 embeddings = np.load(embeddings_path)
 
-# Streamlit UI components (e.g., sidebar, chat interface)
+# Load the SentenceTransformer model once at app startup
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = load_model(device)
+
+# Streamlit UI components
 st.title("Real-World Programming Question Mock Interview")
 
 # Sidebar form for generating questions
 with st.sidebar.form(key="input_form"):
-    company = st.text_input("Company", value="Google")
-    difficulty = st.selectbox("Difficulty", ["Easy", "Medium", "Hard"], index=1)
-    topic = st.text_input("Topic", value="Binary Search")
+    st.markdown("## Generate a New Question")
+    company = st.text_input("Company", value="Google")  # Default value: Google
+    difficulty = st.selectbox("Difficulty", ["Easy", "Medium", "Hard"], index=1)  # Default: Medium
+    topic = st.text_input("Topic", value="Binary Search")  # Default: Binary Search
     generate_button = st.form_submit_button(label="Generate")
 
 if generate_button:
+    # Clear session state and start fresh with follow-up mode disabled
+    st.session_state.messages = []
+    st.session_state.follow_up_mode = False
+
+    # Create a query from user inputs and find the most relevant question
     query = f"{company} {difficulty} {topic}"
-    top_question = find_top_question(query, metadata, embeddings)
+    top_question = find_top_question(query, metadata, embeddings, model)
+    
+    # Prepare a detailed prompt for GPT using the top question's details
     detailed_prompt = generate_detailed_prompt(top_question)
-    response = generate_response(detailed_prompt)
+    
+    # Generate response using OpenAI API with detailed prompt and debugging logs
+    response = generate_response([{"role": "user", "content": detailed_prompt}])
+    
+    # Store generated question in session state for persistence in sidebar and follow-up conversation state
     st.session_state.generated_question = response
 
-# Code execution section in the sidebar
+    # Extract code template and sample test case
+    code_template, sample_test_case, expected_output = extract_code_and_test_case(response)
+    st.session_state.code_template = code_template
+    st.session_state.sample_test_case = sample_test_case
+    st.session_state.expected_output = expected_output
+
+    # Enable follow-up mode after generating the initial question
+    st.session_state.follow_up_mode = True
+
+# Display chat messages from history on app rerun (for subsequent conversation)
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+# Chatbox for subsequent conversations with assistant (follow-up mode)
+if st.session_state.follow_up_mode:
+    if user_input := st.chat_input("Continue your conversation or ask follow-up questions here:"):
+        # Display user message in chat message container and add to session history
+        with st.chat_message("user"):
+            st.markdown(user_input)
+        
+        st.session_state.messages.append({"role": "user", "content": user_input})
+
+        # Prepare messages to send to the assistant
+        assistant_instruction = (
+            "As a real-world interviewer, please reply to the candidate's follow-up questions "
+            "specific to the generated interview question, to the point, and in a natural, human-sounding way."
+        )
+
+        messages_to_send = [
+            {"role": "user", "content": assistant_instruction},
+            {"role": "assistant", "content": st.session_state.generated_question}
+        ] + st.session_state.messages
+
+        assistant_response = generate_response(messages_to_send)
+
+        with st.chat_message("assistant"):
+            st.markdown(assistant_response)
+        
+        st.session_state.messages.append({"role": "assistant", "content": assistant_response})
+
+st.sidebar.markdown("---")
+st.sidebar.markdown("## Generated Question")
+if st.session_state.generated_question:
+    st.sidebar.markdown(st.session_state.generated_question)
+else:
+    st.sidebar.markdown("_No question generated yet._")
+
+st.sidebar.markdown("---")
 st.sidebar.markdown("## Python Code Interpreter")
-code_input = st.sidebar.text_area("Write your Python code here:", height=300)
+
+# Pre-fill code interpreter with code template after question generation
+if st.session_state.code_template:
+    code_input = st.sidebar.text_area("Write your Python code here:", value=st.session_state.code_template, height=300)
+else:
+    code_input = st.sidebar.text_area("Write your Python code here:", height=300)
+
 if st.sidebar.button("Run Code"):
     execute_code(code_input)
 
-# Display generated questions and follow-up chat logic here...
+# Right sidebar toggleable debug logs section
+with st.expander("Debug Logs (Toggle On/Off)", expanded=False):
+    if "debug_logs" in st.session_state:
+        st.write(st.session_state.debug_logs)