Update app.py

app.py

@@ -67,8 +67,7 @@ def extract_entities(text):
 
     # Flexible regex patterns to handle variations
     invoice_num_pattern = r"(?:Invoice\s*(?:Number|No\.?|#)\s*[:\-\s]*)([\w-]+)"
-    # Simplified vendor pattern to capture only the name, stopping at specific patterns
-    vendor_pattern = r"(?:Vendor\s*(?:Name|Company)?|Supplier|Company\s*Name|From)\s*[:\-\s]*([A-Za-z\s&]+)(?=\s*(?:Invoice|Date|$|\d))"
+    vendor_pattern = r"(?:Vendor\s*(?:Name|Company)?|Supplier|Company\s*Name|From)\s*[:\-\s]*([A-Za-z\s&\.]+)(?=\s*(?:Invoice|No\.?|Date|$|\d))"
     invoice_date_pattern = r"(?:Invoice\s*Date\s*[:\-\s]*|Date\s*[:\-\s]*)(\d{4}-\d{2}-\d{2}|\d{2}/\d{2}/\d{4}|\d{2}-\d{2}-\d{4}|[A-Za-z]+\s*\d{1,2},\s*\d{4})"
     total_amount_pattern = r"(?:Total\s*(?:Amount|Due)?\s*[:\-\s]*\$?)([\d,]+\.?\d*)"
 
@@ -93,7 +92,6 @@ def extract_entities(text):
             elif entity['entity'].startswith('I-ORG') and org_name_parts:
                 org_name_parts.append(entity['word'])
         if org_name_parts:
-            # Clean up NER output (remove ## from subword tokens)
             vendor_name = " ".join(part.replace("##", "") for part in org_name_parts)
             print(f"NER Matched Vendor Name: {vendor_name}")  # Debug