sdf

llm/inference.py

@@ -20,14 +20,17 @@ def extract_product_info(text):
 
     # Extract price separately using regex (to avoid confusion with brand name)
     price_match = re.search(r'\$\s?\d{1,3}(?:,\d{3})*(?:\.\d{2})?', text)
+    print(f'price_match:{price_match}')
     if price_match:
         result["price"] = price_match.group().replace("$", "").replace(",", "").strip()
         # Remove the price part from the text to prevent it from being included in the brand/model extraction
         text = text.replace(price_match.group(), "").strip()
-
+    print(f'text:{text}')
     # Tokenize the remaining text and tag parts of speech
     tokens = nltk.word_tokenize(text)
+    print(f'tokens are:{tokens}')
     pos_tags = nltk.pos_tag(tokens)
+    print(tokens, pos_tags)
 
     # Extract brand and model (Proper Nouns + Alphanumeric patterns)
     brand_parts = []