Upload app.py

app.py

@@ -108,7 +108,7 @@ def compute_correlations_faiss(index: faiss.IndexFlatIP, book_titles: List[str],
 
 
 def load_and_prepare_data():
-    global dataset, faiss_index, normalized_data, book_titles
+    global dataset, faiss_index, normalized_data, book_titles, ratings_by_isbn
 
     # Download data files from Hugging Face
     ratings = "BX-Book-Ratings.csv"
@@ -132,7 +132,7 @@ def load_and_prepare_data():
 
 
 def recommend_books(target_book: str, num_recommendations: int = 10) -> str:
-    global dataset, faiss_index, normalized_data, book_titles
+    global dataset, faiss_index, normalized_data, book_titles, ratings_by_isbn
 
     if dataset is None or faiss_index is None or normalized_data is None or book_titles is None:
         load_and_prepare_data()
@@ -148,8 +148,9 @@ def recommend_books(target_book: str, num_recommendations: int = 10) -> str:
 
     result = f"Top {num_recommendations} recommendations for '{target_book}':\n\n"
     result += "\n\n".join([
-        f"{idx}. Title: {dataset.loc[dataset['Book-Title'] == row['book'], 'Book-Title'].values[0]} "
-        f"ISBN: {dataset.loc[dataset['Book-Title'] == row['book'], 'ISBN'].values[0]}"
+        f"{idx}. Title: {dataset.loc[dataset['Book-Title'] == row['book'], 'Book-Title'].values[0]}, "
+        f"ISBN: {dataset.loc[dataset['Book-Title'] == row['book'], 'ISBN'].values[0]}, "
+        f"Rating: {ratings_by_isbn.loc[ratings_by_isbn['ISBN'] == dataset.loc[dataset['Book-Title'] == row['book'], 'ISBN'].values[0], 'rating'].values[0]}"
         for idx, (_, row) in enumerate(recommendations.iterrows(), 1)
     ])