data-science-document-ai 1.40.1__py3-none-any.whl → 1.40.3__py3-none-any.whl

{data_science_document_ai-1.40.1.dist-info → data_science_document_ai-1.40.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-science-document-ai
-Version: 1.40.1
+Version: 1.40.3
 Summary: "Document AI repo for data science"
 Author: Naomi Nguyen
 Author-email: naomi.nguyen@forto.com

{data_science_document_ai-1.40.1.dist-info → data_science_document_ai-1.40.3.dist-info}/RECORD

@@ -7,10 +7,10 @@ src/io.py,sha256=IXz4wWqiHa9mnHNgtrC6X9M2lItYp9eu6rHCThUIh5c,3585
 src/llm.py,sha256=aEK3rL8XvY7CakvkOJQmcHpEKwZRd8PPrLrzHiO-GFk,7827
 src/log_setup.py,sha256=RhHnpXqcl-ii4EJzRt47CF2R-Q3YPF68tepg_Kg7tkw,2895
 src/pdf_processing.py,sha256=S_eTsgaDIIr3SCrEmaQZyc7TDJlRI0GCuP0P9EGF1Xc,15385
-src/postprocessing/common.py,sha256=OR9O73gUP4tevIZMnorbiUgzviEJlVr46ArTWMXrYVA,19316
+src/postprocessing/common.py,sha256=ll7VMEJ_51OeczcV8Uw-aVrufV3kd3kNLCmss3kt0Do,19291
 src/postprocessing/postprocess_booking_confirmation.py,sha256=nK32eDiBNbauyQz0oCa9eraysku8aqzrcoRFoWVumDU,4827
 src/postprocessing/postprocess_commercial_invoice.py,sha256=3I8ijluTZcOs_sMnFZxfkAPle0UFQ239EMuvZfDZVPg,1028
-src/postprocessing/postprocess_partner_invoice.py,sha256=bWm3Miaq_mtX62xSs14vNQCWPHOj2895Bt6TuOVZWZU,11742
+src/postprocessing/postprocess_partner_invoice.py,sha256=cM4te4qjOI_bXyrF8Zhb6X7eNf5aMKoRaPCFfqFv-98,11538
 src/prompts/library/bookingConfirmation/evergreen/placeholders.json,sha256=Re2wBgZoaJ5yImUUAwZOZxFcKXHxi83TCZwTuqd2v2k,1405
 src/prompts/library/bookingConfirmation/evergreen/prompt.txt,sha256=qlBMFDHy-gwr2PVeuHrfMEg_8Ibdym243DnaCgINa7g,2614
 src/prompts/library/bookingConfirmation/hapag-lloyd/placeholders.json,sha256=Re2wBgZoaJ5yImUUAwZOZxFcKXHxi83TCZwTuqd2v2k,1405
@@ -54,6 +54,6 @@ src/prompts/prompt_library.py,sha256=VJWHeXN-s501C2GiidIIvQQuZdU6T1R27hE2dKBiI40
 src/setup.py,sha256=kPSZosrICfaGZeDaajr40Ha7Ok4XK4fo_uq35Omiwr0,7128
 src/tms.py,sha256=UXbIo1QE--hIX6NZi5Qyp2R_CP338syrY9pCTPrfgnE,1741
 src/utils.py,sha256=-1Yq_5ExZlFQRUPRsQHiBD3TthNSiPVPp46Dvdb9Kf0,13830
-data_science_document_ai-1.40.1.dist-info/METADATA,sha256=RhLAfUQIqkJFJByLNyO0C3er2Q4loNhYi9n7T9uAY5Y,2153
-data_science_document_ai-1.40.1.dist-info/WHEEL,sha256=M5asmiAlL6HEcOq52Yi5mmk9KmTVjY2RDPtO4p9DMrc,88
-data_science_document_ai-1.40.1.dist-info/RECORD,,
+data_science_document_ai-1.40.3.dist-info/METADATA,sha256=ym7EzwlZAar6Qvx0GgwVQM44p30sw74-nrPl7Liyg_8,2153
+data_science_document_ai-1.40.3.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+data_science_document_ai-1.40.3.dist-info/RECORD,,

{data_science_document_ai-1.40.1.dist-info → data_science_document_ai-1.40.3.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.2.0
+Generator: poetry-core 2.2.1
 Root-Is-Purelib: true
 Tag: py3-none-any

src/postprocessing/common.py

@@ -425,10 +425,12 @@ async def format_label(entity_k, entity_value, document_type_code, params):
         # Remove all non-alphanumeric characters like ' ', '-', etc.
         formatted_value = convert_container_number(entity_value)
 
-    elif (
-        document_type_code in ["finalMbL", "draftMbl"] and entity_key == "measurements"
+    elif any(
+        numeric_indicator in entity_key
+        for numeric_indicator in ["measurements", "weight"]
     ):
-        formatted_value = decimal_convertor(extract_number(entity_value))
+        formatted_value = extract_number(entity_value)
+
     elif any(
         packaging_type in entity_key
         for packaging_type in ["packagingtype", "packagetype", "currency"]
@@ -447,7 +449,6 @@ async def format_label(entity_k, entity_value, document_type_code, params):
     elif any(
         numeric_indicator in entity_key
         for numeric_indicator in [
-            "weight",
             "quantity",
             "value",
             "amount",

src/postprocessing/postprocess_partner_invoice.py

@@ -301,10 +301,6 @@ def associate_forto_item_code(input_string, params):
     if forto_item_code is None:
         # 2. Fallback to embedding function if no good fuzzy match
         forto_item_code = get_tms_mappings(input_string, "line_items")
-        # embeddings_dict = embed_manager.embeddings_dict
-        # forto_item_code = embed_manager._find_most_similar_option(
-        #     input_string, *embeddings_dict["item_codes_label"]
-        # )
 
     result = {"documentValue": input_string, "formattedValue": forto_item_code}
     return result