Update app.py

app.py

@@ -1,16 +1,35 @@
 import streamlit as st
 from openai import OpenAI
 import os
+import pandas as pd
+import numpy as np
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise_distances_reduction import cosine_similarity_reduction
+import torch
 
 # Set up OpenAI client
 client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
 
-st.title("LeetCode to Real-World Interview Question Generator")
+# Check if GPU is available
+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 = '/kaggle/working/leetcode_metadata.csv'  # Update this path if needed
+embeddings_path = '/kaggle/working/leetcode_embeddings2.npy'  # Update this path if needed
+
+metadata = pd.read_csv(metadata_path)
+embeddings = np.load(embeddings_path)
+
+# Load the SentenceTransformer model
+model = SentenceTransformer("all-MiniLM-L6-v2").to(device)
 
 # Load the system prompt from the file
 with open("prompt.txt", "r") as file:
     system_prompt = file.read()
 
+st.title("LeetCode to Real-World Interview Question Generator")
+
 # Initialize chat history
 if "messages" not in st.session_state:
     st.session_state.messages = [{"role": "assistant", "content": system_prompt}]
@@ -20,8 +39,30 @@ for message in st.session_state.messages[1:]:  # Skip the system message
     with st.chat_message(message["role"]):
         st.markdown(message["content"])
 
-# Function to generate response using OpenAI API
+# 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()
+    
+    # Compute cosine similarity between query embedding and dataset embeddings using scikit-learn's pairwise_distances_reduction
+    similarities = cosine_similarity_reduction(
+        X=query_embedding.reshape(1, -1), Y=embeddings, reduce_func="argmax"
+    )
+    
+    # Get the index of the most similar result (top 1)
+    top_index = similarities.indices[0]  # Index of highest similarity
+    
+    # Retrieve metadata for the top result
+    top_result = metadata.iloc[top_index].copy()
+    top_result['similarity_score'] = similarities.distances[0]
+    
+    return top_result
+
+# Function to generate response using OpenAI API with debugging logs
 def generate_response(prompt):
+    st.write("### Debugging Log: Data Sent to GPT")
+    st.write(prompt)  # Log the prompt being sent to GPT for debugging
+    
     response = client.chat.completions.create(
         model="gpt-4o",
         messages=st.session_state.messages + [{"role": "system", "content": prompt}]
@@ -29,23 +70,39 @@ def generate_response(prompt):
     return response.choices[0].message.content
 
 # React to user input
-if prompt := st.chat_input("Enter a LeetCode question to transform:"):
+if prompt := st.chat_input("Enter a LeetCode-related query (e.g., 'google backtracking'):"):
     # Display user message in chat message container
     st.chat_message("user").markdown(prompt)
     # Add user message to chat history
     st.session_state.messages.append({"role": "user", "content": prompt})
 
-    # Generate response
-    response = generate_response(prompt)
+    # Find the top question based on user input
+    top_question = find_top_question(prompt)
+    
+    # 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"
+        f"**Question ID**: {top_question['questionId']}\n"
+        f"**Question Name**: {top_question['questionName']}\n"
+        f"**Difficulty Level**: {top_question['difficulty level']}\n"
+        f"**Tags**: {top_question['Tags']}\n"
+        f"**Content**: {top_question['Content']}\n"
+        f"\nPlease create a real-world interview question based on this information."
+    )
+    
+    # Generate response using GPT-4 with detailed prompt and debugging logs
+    response = generate_response(detailed_prompt)
 
     # 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})
 
 st.sidebar.markdown("""
 ## About
 This is a LeetCode to Real-World Interview Question Generator powered by OpenAI's GPT-4.
-Enter a LeetCode question to transform it into a real-world interview scenario!
+Enter a LeetCode-related query, and it will transform a relevant question into a real-world interview scenario!
 """)