data-science-document-ai 1.42.2__tar.gz → 1.42.3__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (56) hide show
  1. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/PKG-INFO +1 -1
  2. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/pyproject.toml +1 -1
  3. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/postprocessing/common.py +1 -0
  4. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/partnerInvoice/other/prompt.txt +1 -1
  5. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/constants.py +0 -0
  6. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/constants_sandbox.py +0 -0
  7. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/docai.py +0 -0
  8. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/docai_processor_config.yaml +0 -0
  9. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/excel_processing.py +0 -0
  10. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/io.py +0 -0
  11. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/llm.py +0 -0
  12. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/log_setup.py +0 -0
  13. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/pdf_processing.py +0 -0
  14. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/postprocessing/postprocess_booking_confirmation.py +0 -0
  15. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/postprocessing/postprocess_commercial_invoice.py +0 -0
  16. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/postprocessing/postprocess_partner_invoice.py +0 -0
  17. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/evergreen/placeholders.json +0 -0
  18. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/evergreen/prompt.txt +0 -0
  19. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/hapag-lloyd/placeholders.json +0 -0
  20. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/hapag-lloyd/prompt.txt +0 -0
  21. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/maersk/placeholders.json +0 -0
  22. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/maersk/prompt.txt +0 -0
  23. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/msc/placeholders.json +0 -0
  24. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/msc/prompt.txt +0 -0
  25. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/oocl/placeholders.json +0 -0
  26. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/oocl/prompt.txt +0 -0
  27. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/other/placeholders.json +0 -0
  28. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/other/prompt.txt +0 -0
  29. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/yangming/placeholders.json +0 -0
  30. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bookingConfirmation/yangming/prompt.txt +0 -0
  31. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bundeskasse/other/placeholders.json +0 -0
  32. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/bundeskasse/other/prompt.txt +0 -0
  33. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/commercialInvoice/other/prompt.txt +0 -0
  34. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/customsAssessment/other/prompt.txt +0 -0
  35. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/customsInvoice/other/placeholders.json +0 -0
  36. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/customsInvoice/other/prompt.txt +0 -0
  37. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/deliveryOrder/other/placeholders.json +0 -0
  38. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/deliveryOrder/other/prompt.txt +0 -0
  39. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/draftMbl/hapag-lloyd/prompt.txt +0 -0
  40. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/draftMbl/maersk/prompt.txt +0 -0
  41. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/draftMbl/other/placeholders.json +0 -0
  42. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/draftMbl/other/prompt.txt +0 -0
  43. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/finalMbL/hapag-lloyd/prompt.txt +0 -0
  44. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/finalMbL/maersk/prompt.txt +0 -0
  45. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/finalMbL/other/prompt.txt +0 -0
  46. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/packingList/other/prompt.txt +0 -0
  47. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/partnerInvoice/other/placeholders.json +0 -0
  48. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/postprocessing/port_code/placeholders.json +0 -0
  49. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/postprocessing/port_code/prompt_port_code.txt +0 -0
  50. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/preprocessing/carrier/placeholders.json +0 -0
  51. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/preprocessing/carrier/prompt.txt +0 -0
  52. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/library/shippingInstruction/other/prompt.txt +0 -0
  53. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/prompts/prompt_library.py +0 -0
  54. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/setup.py +0 -0
  55. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/tms.py +0 -0
  56. {data_science_document_ai-1.42.2 → data_science_document_ai-1.42.3}/src/utils.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: data-science-document-ai
3
- Version: 1.42.2
3
+ Version: 1.42.3
4
4
  Summary: "Document AI repo for data science"
5
5
  Author: Naomi Nguyen
6
6
  Author-email: naomi.nguyen@forto.com
@@ -1,6 +1,6 @@
1
1
  [tool.poetry]
2
2
  name = "data-science-document-ai"
3
- version = "1.42.2"
3
+ version = "1.42.3"
4
4
  description = "\"Document AI repo for data science\""
5
5
  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>"]
6
6
  packages = [
@@ -456,6 +456,7 @@ async def format_label(entity_k, entity_value, document_type_code, params):
456
456
  elif "quantity" in entity_key:
457
457
  if document_type_code in ["partnerInvoice", "customsInvoice", "bundeskasse"]:
458
458
  # For partner invoice, quantity can be mentioned as whole number
459
+ # Apply decimal convertor for 46,45 --> 46.45 but not for 1.000 --> 1000
459
460
  formatted_value = decimal_convertor(
460
461
  extract_number(entity_value), quantity=True
461
462
  )
@@ -52,7 +52,7 @@ Your role is to accurately extract specific entities from these invoices to supp
52
52
  - 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.
53
53
  - totalAmount: The total amount for the item. It can be in different currencies, so ensure to capture the currency as well for the totalAmountCurrency.
54
54
  - totalAmountEuro: Few line items contains a total amount in Euro. You can find it by looking for the term "Total EUR" or "Amount in Euro" in the line item but it's always in the EURO / € currency. Sometimes, it can be same as totalAmount if the line item is already in Euro.
55
- - quantity: The quantity of the item or service provided in the line item.
55
+ - quantity: The quantity of the item or service provided in the line item. Pay attention to 2x40HC. It means, quantity is 2 and containerSize is 40HC but not 240.
56
56
  - containerNumber: Container Number always starts with 4 letters and is followed by 7 digits (e.g., ABCD1234567).
57
57
 
58
58
  - hblNumber and mblNumber: