data-science-document-ai 1.54.0__tar.gz → 1.55.0__tar.gz

{data_science_document_ai-1.54.0 → data_science_document_ai-1.55.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-science-document-ai
-Version: 1.54.0
+Version: 1.55.0
 Summary: "Document AI repo for data science"
 Author: Naomi Nguyen
 Author-email: naomi.nguyen@forto.com

{data_science_document_ai-1.54.0 → data_science_document_ai-1.55.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "data-science-document-ai"
-version = "1.54.0"
+version = "1.55.0"
 description = "\"Document AI repo for data science\""
 authors = ["Naomi Nguyen <naomi.nguyen@forto.com>", "Kumar Rajendrababu <kumar.rajendrababu@forto.com>", "Igor Tonko <igor.tonko@forto.com>", "Osman Demirel <osman.demirel@forto.com>"]
 packages = [

{data_science_document_ai-1.54.0 → data_science_document_ai-1.55.0}/src/prompts/library/customsInvoice/other/prompt.txt

@@ -48,7 +48,7 @@ Your role is to accurately extract specific entities from these invoices to supp
 - issueDate: The date the document was issued.
 - dueDate: The date by which the payment should be made. Do Not calculate dueDate based on issueDate or any other date. Extract it directly from the invoice.
 
-- lineItem: Details of each COGS and Customs line item on the invoice. Make sure to extract each amount and currency separately.
+- lineItem: Details of each COGS and Customs line item on the invoice from each page. Make sure to extract each amount and currency separately.
     - uniqueId: A unique id which associated with the lineItem as each line item can belong to a different shipment. Extract only if its available in the line item. Either a shipmentId starting with an S and followed by 6 or 8 numeric values or a mblNumber. If shipmentId or mblNumber does not exist, set it to containerNumber.
     - lineItemDescription: The name or description of the item. Usually, it will be a one line sentence.
     - unitPrice: Even if the quantity is not mentioned, you can still extract the unit price. Check the naming of the columns in a different languages, it can be "Unit Price", "Prezzo unitario", "Prix Unitaire", "Unitario", etc. Refer to "Prezzo unitario" field in the italian invoice example.
@@ -92,6 +92,7 @@ Your role is to accurately extract specific entities from these invoices to supp
 
 IMPORTANT NOTE:
 - Ensure all extracted values are directly from the document. Do not make assumptions or modifications.
+- Extract line items from each page if the invoice spans multiple pages.
 - Do not normalize or modify any entity values.
 - Pay attention to the line item details and paymentInformation, as they may vary significantly across different invoices.
 

{data_science_document_ai-1.54.0 → data_science_document_ai-1.55.0}/src/prompts/library/partnerInvoice/other/prompt.txt

@@ -46,7 +46,7 @@ Your role is to accurately extract specific entities from these invoices to supp
 
 - eta and etd: Few invoices contains same date for ARRIVED/DEPARTED or ETA/ETD. Extract it for both eta and etd.
 
-- lineItem: Details of each COGS and Customs line item on the invoice. Make sure to extract each amount and currency separately.
+- lineItem: Details of each COGS and Customs line item on the invoice from each page. Make sure to extract each amount and currency separately.
     - uniqueId: A unique id which associated with the lineItem as each line item can belong to a different shipment. Extract only if its available in the line item. Either a shipmentId starting with an S and followed by 6 or 8 numeric values or a mblNumber. If shipmentId or mblNumber does not exist, set it to containerNumber.
     - lineItemDescription: The name or description of the item. Usually, it will be a one line sentence.
     - unitPrice: Even if the quantity is not mentioned, you can still extract the unit price. Check the naming of the columns in a different languages, it can be "Unit Price", "Prezzo unitario", "Prix Unitaire", "Unitario", etc. Refer to "Prezzo unitario" field in the italian invoice example.