data-science-document-ai 1.55.0__tar.gz → 1.56.0__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 (59) hide show
  1. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/PKG-INFO +1 -1
  2. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/pyproject.toml +1 -1
  3. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/customsInvoice/other/prompt.txt +1 -1
  4. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/partnerInvoice/other/prompt.txt +1 -0
  5. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/constants.py +0 -0
  6. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/constants_sandbox.py +0 -0
  7. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/docai.py +0 -0
  8. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/docai_processor_config.yaml +0 -0
  9. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/excel_processing.py +0 -0
  10. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/io.py +0 -0
  11. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/llm.py +0 -0
  12. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/log_setup.py +0 -0
  13. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/pdf_processing.py +0 -0
  14. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/postprocessing/common.py +0 -0
  15. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/postprocessing/postprocess_booking_confirmation.py +0 -0
  16. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/postprocessing/postprocess_commercial_invoice.py +0 -0
  17. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/postprocessing/postprocess_partner_invoice.py +0 -0
  18. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/arrivalNotice/other/placeholders.json +0 -0
  19. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/arrivalNotice/other/prompt.txt +0 -0
  20. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/evergreen/placeholders.json +0 -0
  21. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/evergreen/prompt.txt +0 -0
  22. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/hapag-lloyd/placeholders.json +0 -0
  23. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/hapag-lloyd/prompt.txt +0 -0
  24. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/maersk/placeholders.json +0 -0
  25. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/maersk/prompt.txt +0 -0
  26. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/msc/placeholders.json +0 -0
  27. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/msc/prompt.txt +0 -0
  28. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/oocl/placeholders.json +0 -0
  29. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/oocl/prompt.txt +0 -0
  30. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/other/placeholders.json +0 -0
  31. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/other/prompt.txt +0 -0
  32. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/yangming/placeholders.json +0 -0
  33. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bookingConfirmation/yangming/prompt.txt +0 -0
  34. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bundeskasse/other/placeholders.json +0 -0
  35. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/bundeskasse/other/prompt.txt +0 -0
  36. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/commercialInvoice/other/placeholders.json +0 -0
  37. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/commercialInvoice/other/prompt.txt +0 -0
  38. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/customsAssessment/other/placeholders.json +0 -0
  39. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/customsAssessment/other/prompt.txt +0 -0
  40. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/customsInvoice/other/placeholders.json +0 -0
  41. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/deliveryOrder/other/placeholders.json +0 -0
  42. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/deliveryOrder/other/prompt.txt +0 -0
  43. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/draftMbl/other/placeholders.json +0 -0
  44. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/draftMbl/other/prompt.txt +0 -0
  45. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/finalMbL/other/placeholders.json +0 -0
  46. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/finalMbL/other/prompt.txt +0 -0
  47. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/packingList/other/placeholders.json +0 -0
  48. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/packingList/other/prompt.txt +0 -0
  49. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/partnerInvoice/other/placeholders.json +0 -0
  50. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/postprocessing/port_code/placeholders.json +0 -0
  51. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/postprocessing/port_code/prompt_port_code.txt +0 -0
  52. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/preprocessing/carrier/placeholders.json +0 -0
  53. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/preprocessing/carrier/prompt.txt +0 -0
  54. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/shippingInstruction/other/placeholders.json +0 -0
  55. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/library/shippingInstruction/other/prompt.txt +0 -0
  56. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/prompts/prompt_library.py +0 -0
  57. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/setup.py +0 -0
  58. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/tms.py +0 -0
  59. {data_science_document_ai-1.55.0 → data_science_document_ai-1.56.0}/src/utils.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: data-science-document-ai
3
- Version: 1.55.0
3
+ Version: 1.56.0
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 = "1.55.0"
3
+ version = "1.56.0"
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 = [
@@ -92,7 +92,7 @@ Your role is to accurately extract specific entities from these invoices to supp
92
92
 
93
93
  IMPORTANT NOTE:
94
94
  - Ensure all extracted values are directly from the document. Do not make assumptions or modifications.
95
- - Extract line items from each page if the invoice spans multiple pages.
95
+ - Sometimes invoices contain line items in a table format with headings Shipment ID, Line item description, Quantity and Amount. Extract all the line items from such tables in each page.
96
96
  - Do not normalize or modify any entity values.
97
97
  - Pay attention to the line item details and paymentInformation, as they may vary significantly across different invoices.
98
98
 
@@ -82,6 +82,7 @@ Your role is to accurately extract specific entities from these invoices to supp
82
82
 
83
83
  IMPORTANT NOTE:
84
84
  - Ensure all extracted values are directly from the document. Do not make assumptions, modifications or calculations.
85
+ - Sometimes invoices contain line items in a table format with headings Shipment ID, Line item description, Quantity and Amount. Extract all the line items from such tables in each page.
85
86
  - Do not split the quantity into different line items. e.g., if quantity is 2 or 2 CTR or 2 BIL, do not create 2 separate line items with quantity 1 each.
86
87
  - Do not normalize or modify any entity values.
87
88
  - Pay attention to the line item details and paymentInformation, as they may vary significantly across different invoices.