Cleanup and refactor

src/data_prep/constants.py

@@ -0,0 +1,10 @@
+from src.data_prep.data_prep import (
+    load_bm25_index,
+    load_clean_amazon_product_data,
+    load_faiss_index,
+)
+
+
+BM25_INDEX = load_bm25_index()
+FAISS_INDEX = load_faiss_index()
+PRODUCTS_DF = load_clean_amazon_product_data()

src/{modules → search}/bm25_lexical_search.py

@@ -1,15 +1,11 @@
 import bm25s
 from typing import List, Dict
 from pathlib import Path
-from src.modules.data_prep import load_bm25_index, load_clean_amazon_product_data
+from src.data_prep.constants import BM25_INDEX, PRODUCTS_DF
 
 _FILE_PATH = Path(__file__).parents[2]
 
 
-_BM25_INDEX = load_bm25_index()
-_PRODUCTS_DF = load_clean_amazon_product_data()
-
-
 def search_bm25(query: str, top_k: int = 5) -> List[Dict[str, any]]:
     """
     Search products using BM25 lexical search (keyword matching).
@@ -25,14 +21,14 @@ def search_bm25(query: str, top_k: int = 5) -> List[Dict[str, any]]:
         List of dictionaries containing product information and scores
     """
     query_tokens = bm25s.tokenize(query, stopwords="en")
-    results, scores = _BM25_INDEX.retrieve(query_tokens, k=top_k)
+    results, scores = BM25_INDEX.retrieve(query_tokens, k=top_k)
 
     return [
         {
-            "product_name": _PRODUCTS_DF.iloc[idx]["Product Name"],
-            "description": _PRODUCTS_DF.iloc[idx]["Description"],
-            "main_category": _PRODUCTS_DF.iloc[idx]["MainCategory"],
-            "secondary_category": _PRODUCTS_DF.iloc[idx]["SecondaryCategory"],
+            "product_name": PRODUCTS_DF.iloc[idx]["Product Name"],
+            "description": PRODUCTS_DF.iloc[idx]["Description"],
+            "main_category": PRODUCTS_DF.iloc[idx]["MainCategory"],
+            "secondary_category": PRODUCTS_DF.iloc[idx]["SecondaryCategory"],
             "score": float(score),
         }
         for idx, score in zip(results[0], scores[0])