Update app.py

app.py

@@ -6,7 +6,6 @@ import numpy as np
 from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
 import torch
-import requests
 
 # Set up OpenAI client
 client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
@@ -16,8 +15,8 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 print(f"Using device: {device}")
 
 # Load metadata and embeddings (ensure these files are in your working directory or update paths)
-metadata_path = 'question_metadata.csv'
-embeddings_path = 'question_dataset_embeddings.npy'
+metadata_path = 'question_metadata.csv'  # Update this path if needed
+embeddings_path = 'question_dataset_embeddings.npy'  # Update this path if needed
 
 metadata = pd.read_csv(metadata_path)
 embeddings = np.load(embeddings_path)
@@ -38,94 +37,65 @@ st.title("Real-World Programming Question Mock Interview")
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
+if "follow_up_mode" not in st.session_state:
+    st.session_state.follow_up_mode = False  # Tracks whether we're in follow-up mode
+
 if "generated_question" not in st.session_state:
-    st.session_state.generated_question = None
+    st.session_state.generated_question = None  # Stores the generated question for persistence
 
-if "code_output" not in st.session_state:
-    st.session_state.code_output = ""
+if "debug_logs" not in st.session_state:
+    st.session_state.debug_logs = []  # Stores debug logs for toggling
 
-if "evaluation_output" not in st.session_state:
-    st.session_state.evaluation_output = ""
+# Function to find the top 1 most similar question based on user input
+def find_top_question(query):
+    # Generate embedding for the query
+    query_embedding = model.encode(query, convert_to_tensor=True, device=device).cpu().numpy()
+    
+    # Reshape query_embedding to ensure it is a 2D array
+    query_embedding = query_embedding.reshape(1, -1)  # Reshape to (1, n_features)
 
-# Sidebar layout for Generated Question and Code Box
-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._")
+    # Compute cosine similarity between query embedding and dataset embeddings
+    similarities = cosine_similarity(query_embedding, embeddings).flatten()  # Flatten to get a 1D array of similarities
 
-st.sidebar.markdown("---")
-st.sidebar.markdown("## Code Box")
+    # Get the index of the most similar result (top 1)
+    top_index = similarities.argsort()[-1]  # Index of highest similarity
 
-code_input = st.sidebar.text_area(
-    label="Write your Python code here:",
-    height=200,
-    placeholder="Enter your code...",
-)
+    # Retrieve metadata for the top result
+    top_result = metadata.iloc[top_index].copy()
+    top_result['similarity_score'] = similarities[top_index]
 
-col1, col2 = st.sidebar.columns(2)
+    return top_result
 
-# Button to run code and display output
-if col1.button("Run Code"):
-    try:
-        exec_globals = {}
-        exec(code_input, exec_globals)
-        st.session_state.code_output = exec_globals.get("output", "Code executed successfully.")
-    except Exception as e:
-        st.session_state.code_output = f"Error: {str(e)}"
-
-# Button to evaluate code using OpenAI API
-if col2.button("Evaluate Code"):
-    if not st.session_state.generated_question:
-        st.sidebar.error("Generate a question first!")
-    else:
-        try:
-            evaluation_prompt = (
-                f"Question: {st.session_state.generated_question}\n\n"
-                f"Code:\n{code_input}\n\n"
-                f"Evaluate this code's correctness, efficiency, and style."
-            )
-            response = client.chat.completions.create(
-                model="gpt-4",
-                messages=[{"role": "user", "content": evaluation_prompt}],
-            )
-            evaluation_response = response.choices[0].message.content
-            st.session_state.evaluation_output = evaluation_response
-
-            # Add evaluation output to follow-up conversation
-            st.session_state.messages.append({"role": "assistant", "content": evaluation_response})
-        except Exception as e:
-            st.sidebar.error(f"Error during evaluation: {str(e)}")
-
-# Display outputs below the main app content
-st.subheader("Code Output")
-st.text(st.session_state.code_output)
-
-st.subheader("Evaluation Output")
-st.text(st.session_state.evaluation_output)
-
-# Main app logic for generating questions and follow-up conversation remains unchanged.
+# Function to generate response using OpenAI API with debugging logs
+def generate_response(messages):
+    debug_log_entry = {"messages": messages}
+    st.session_state.debug_logs.append(debug_log_entry)  # Store debug log
+    
+    response = client.chat.completions.create(
+        model="o1-mini",
+        messages=messages,
+    )
+    
+    return response.choices[0].message.content
+
+# User input form for generating a new question
 with st.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 (e.g., Backtracking)", value="Backtracking")
+    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 (e.g., Backtracking)", value="Backtracking")  # Default: Backtracking
     
     generate_button = st.form_submit_button(label="Generate")
 
 if generate_button:
-    query = f"{company} {difficulty} {topic}"
-    
-    def find_top_question(query):
-        query_embedding = model.encode(query, convert_to_tensor=True, device=device).cpu().numpy()
-        query_embedding = query_embedding.reshape(1, -1)
-        similarities = cosine_similarity(query_embedding, embeddings).flatten()
-        top_index = similarities.argsort()[-1]
-        top_result = metadata.iloc[top_index].copy()
-        top_result['similarity_score'] = similarities[top_index]
-        return top_result
+    # 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)
     
+    # Prepare a detailed prompt for GPT using the top question's details
     detailed_prompt = (
         f"Transform this LeetCode question into a real-world interview scenario:\n\n"
         f"**Company**: {top_question['company']}\n"
@@ -136,29 +106,76 @@ if generate_button:
         f"\nPlease create a real-world interview question based on this information."
     )
     
-    response_text = client.chat.completions.create(
-        model="gpt-4",
-        messages=[{"role": "assistant", "content": question_generation_prompt}, {"role": "user", "content": detailed_prompt}],
-    ).choices[0].message.content
-    
-    st.session_state.generated_question = response_text
+    # Generate response using GPT-4 with detailed prompt and debugging logs
+    response = generate_response([{"role": "assistant", "content": question_generation_prompt}, {"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
+
+    # Add the generated question to the conversation history as an assistant message (to make it part of follow-up conversations)
+    st.session_state.messages.append({"role": "assistant", "content": response})
 
+    # 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"])
 
-if user_input := st.chat_input("Continue your conversation or ask follow-up questions here:"):
-    with st.chat_message("user"):
-        st.markdown(user_input)
-    
-    assistant_response_text = client.chat.completions.create(
-        model="gpt-4",
-        messages=[{"role": "assistant", "content": technical_interviewer_prompt}] + [{"role": msg["role"], "content": msg["content"]} for msg in st.session_state.messages],
-    ).choices[0].message.content
-    
-    with st.chat_message("assistant"):
-        st.markdown(assistant_response_text)
-    
-    # Append to session state messages for persistence
-    st.session_state.messages.append({"role": "user", "content": user_input})
-    st.session_state.messages.append({"role": "assistant", "content": assistant_response_text})
+# 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})
+
+        # Generate assistant's response based on follow-up input using technical_interviewer_prompt as system prompt,
+        # including the generated question in context.
+        assistant_response = generate_response(
+            [{"role": "assistant", "content": technical_interviewer_prompt}] + st.session_state.messages
+        )
+
+        with st.chat_message("assistant"):
+            st.markdown(assistant_response)
+        
+        st.session_state.messages.append({"role": "assistant", "content": assistant_response})
+
+# Sidebar content to display persistent generated question (left sidebar)
+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("""
+## About
+This is a Real-World Interview Question Generator powered by OpenAI's API.
+Enter a company name, topic, and level of difficulty, and it will transform a relevant question into a real-world interview scenario!
+Continue chatting with the assistant in the chatbox below.
+""")
+
+# Right sidebar toggleable debug logs and code interpreter section
+with st.expander("Debug Logs (Toggle On/Off)", expanded=False):
+    if len(st.session_state.debug_logs) > 0:
+        for log_entry in reversed(st.session_state.debug_logs):  # Show most recent logs first
+            st.write(log_entry)
+
+st.sidebar.markdown("---")
+st.sidebar.markdown("## Python Code Interpreter")
+code_input = st.sidebar.text_area("Write your Python code here:")
+if st.sidebar.button("Run Code"):
+    try:
+        exec_globals = {}
+        exec(code_input, exec_globals)  # Execute user-provided code safely within its own scope.
+        output_key = [k for k in exec_globals.keys() if k != "__builtins__"]
+        if output_key:
+            output_value = exec_globals[output_key[0]]
+            st.sidebar.success(f"Output: {output_value}")
+        else:
+            st.sidebar.success("Code executed successfully!")
+            
+    except Exception as e:
+        st.sidebar.error(f"Error: {e}")