Merged in bugfix/effective_date (pull request #550)

Bugfix/effective_date to main

* fixed string page numbers issue


Approved-by: Katon Minhas

fieldExtraction/src/investment/vision_funcs.py

@@ -11,7 +11,7 @@ import src.utils.string_utils as string_utils
 
 def get_image_array_based_answer(
     pdf_path: str, 
-    effective_date_page_numbers: List[int], 
+    effective_date_page_numbers: List, 
     filename: str, 
     fields: List[str] = ["AARETE_DERIVED_EFFECTIVE_DT"]
 ) -> dict:
@@ -41,7 +41,7 @@ def get_image_array_based_answer(
     return response_dict
 
 
-def process_pdf_pages_to_base64_images(pdf_path: str, filename: str, page_numbers: List[int]) -> List[str]:
+def process_pdf_pages_to_base64_images(pdf_path: str, filename: str, page_numbers: List) -> List[str]:
     """
     Convert multiple specific pages of a PDF into a list of base64-encoded JPEG images.
 

fieldExtraction/src/utils/string_utils.py

@@ -472,7 +472,7 @@ def extract_effective_date_pages(text_dict: dict, filename: str) -> dict:
         if textract_pattern.search(page_text) or 'effective date:' in page_text.lower():
             effective_date_pages[page_num] = page_text
         # Always include the first page (page 1) as it often contains effective date.
-        elif page_num == 1:
+        elif page_num == 1 or page_num == "1" or page_num == "1.0":
             effective_date_pages[page_num] = page_text
 
     return effective_date_pages