Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -4,7 +4,7 @@ import os
|
|
| 4 |
import pandas as pd
|
| 5 |
import numpy as np
|
| 6 |
from sentence_transformers import SentenceTransformer
|
| 7 |
-
from sklearn.metrics.
|
| 8 |
import torch
|
| 9 |
|
| 10 |
# Set up OpenAI client
|
|
@@ -15,8 +15,8 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
|
|
| 15 |
print(f"Using device: {device}")
|
| 16 |
|
| 17 |
# Load metadata and embeddings (ensure these files are in your working directory or update paths)
|
| 18 |
-
metadata_path = '
|
| 19 |
-
embeddings_path = '
|
| 20 |
|
| 21 |
metadata = pd.read_csv(metadata_path)
|
| 22 |
embeddings = np.load(embeddings_path)
|
|
@@ -45,9 +45,7 @@ def find_top_question(query):
|
|
| 45 |
query_embedding = model.encode(query, convert_to_tensor=True, device=device).cpu().numpy()
|
| 46 |
|
| 47 |
# Compute cosine similarity between query embedding and dataset embeddings using scikit-learn's pairwise_distances_reduction
|
| 48 |
-
similarities =
|
| 49 |
-
X=query_embedding.reshape(1, -1), Y=embeddings, reduce_func="argmax"
|
| 50 |
-
)
|
| 51 |
|
| 52 |
# Get the index of the most similar result (top 1)
|
| 53 |
top_index = similarities.indices[0] # Index of highest similarity
|
|
@@ -64,8 +62,8 @@ def generate_response(prompt):
|
|
| 64 |
st.write(prompt) # Log the prompt being sent to GPT for debugging
|
| 65 |
|
| 66 |
response = client.chat.completions.create(
|
| 67 |
-
model="
|
| 68 |
-
messages=st.session_state.messages + [{"role": "
|
| 69 |
)
|
| 70 |
return response.choices[0].message.content
|
| 71 |
|
|
@@ -103,6 +101,6 @@ if prompt := st.chat_input("Enter a LeetCode-related query (e.g., 'google backtr
|
|
| 103 |
|
| 104 |
st.sidebar.markdown("""
|
| 105 |
## About
|
| 106 |
-
This is a LeetCode to Real-World Interview Question Generator powered by OpenAI's
|
| 107 |
Enter a LeetCode-related query, and it will transform a relevant question into a real-world interview scenario!
|
| 108 |
""")
|
|
|
|
| 4 |
import pandas as pd
|
| 5 |
import numpy as np
|
| 6 |
from sentence_transformers import SentenceTransformer
|
| 7 |
+
from sklearn.metrics.pairwise import cosine_similarity
|
| 8 |
import torch
|
| 9 |
|
| 10 |
# Set up OpenAI client
|
|
|
|
| 15 |
print(f"Using device: {device}")
|
| 16 |
|
| 17 |
# Load metadata and embeddings (ensure these files are in your working directory or update paths)
|
| 18 |
+
metadata_path = 'question_metadata.csv' # Update this path if needed
|
| 19 |
+
embeddings_path = 'question_dataset_embeddings.npy' # Update this path if needed
|
| 20 |
|
| 21 |
metadata = pd.read_csv(metadata_path)
|
| 22 |
embeddings = np.load(embeddings_path)
|
|
|
|
| 45 |
query_embedding = model.encode(query, convert_to_tensor=True, device=device).cpu().numpy()
|
| 46 |
|
| 47 |
# Compute cosine similarity between query embedding and dataset embeddings using scikit-learn's pairwise_distances_reduction
|
| 48 |
+
similarities = cosine_similarity(query_embedding, embeddings).flatten()
|
|
|
|
|
|
|
| 49 |
|
| 50 |
# Get the index of the most similar result (top 1)
|
| 51 |
top_index = similarities.indices[0] # Index of highest similarity
|
|
|
|
| 62 |
st.write(prompt) # Log the prompt being sent to GPT for debugging
|
| 63 |
|
| 64 |
response = client.chat.completions.create(
|
| 65 |
+
model="o1-mini",
|
| 66 |
+
messages=st.session_state.messages + [{"role": "assistant", "content": prompt}]
|
| 67 |
)
|
| 68 |
return response.choices[0].message.content
|
| 69 |
|
|
|
|
| 101 |
|
| 102 |
st.sidebar.markdown("""
|
| 103 |
## About
|
| 104 |
+
This is a LeetCode to Real-World Interview Question Generator powered by OpenAI's API.
|
| 105 |
Enter a LeetCode-related query, and it will transform a relevant question into a real-world interview scenario!
|
| 106 |
""")
|