Upload app.py

app.py

@@ -75,14 +75,14 @@ def build_faiss_index(dataset: pd.DataFrame) -> Tuple[faiss.IndexFlatIP, np.ndar
 
 
 def compute_correlations_faiss(index, book_titles: List[str],
-                               target_book, ) -> pd.DataFrame:
+                               target_book, num_recommendations) -> pd.DataFrame:
     print(target_book, type(target_book))
     emb = create_embedding([target_book[0]])
     # target_vector = book_titles.index(emb)
 
 
     # Perform the search
-    k = len(book_titles)  # Search for all books
+    k = num_recommendations
     similarities, I = index.search(emb.astype('float16'), k)
     print(similarities, I)
 
@@ -143,9 +143,9 @@ def recommend_books(target_book: str, num_recommendations: int = 10) -> str:
     closest_match = process.extractOne(target_book, book_titles)
 
 
-    correlations = compute_correlations_faiss(faiss_index, list(dataset["Book-Title"]), closest_match)
+    correlations = compute_correlations_faiss(faiss_index, list(dataset["Book-Title"]), closest_match, num_recommendations)
 
-    recommendations = correlations[correlations['book'] != target_book].head(num_recommendations)
+    recommendations = dataset[dataset["Book-Title"] != target_book].head(num_recommendations)
 
     result = f"Top {num_recommendations} recommendations for '{target_book}':\n\n"
     for i, (_, row) in enumerate(recommendations.iterrows(), 1):