data-science-document-ai 1.50.0__tar.gz → 1.51.1__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.
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/PKG-INFO +1 -1
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/pyproject.toml +1 -1
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bundeskasse/other/placeholders.json +4 -4
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bundeskasse/other/prompt.txt +3 -3
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/constants.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/constants_sandbox.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/docai.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/docai_processor_config.yaml +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/excel_processing.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/io.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/llm.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/log_setup.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/pdf_processing.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/postprocessing/common.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/postprocessing/postprocess_booking_confirmation.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/postprocessing/postprocess_commercial_invoice.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/postprocessing/postprocess_partner_invoice.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/arrivalNotice/other/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/arrivalNotice/other/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/evergreen/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/evergreen/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/hapag-lloyd/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/hapag-lloyd/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/maersk/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/maersk/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/msc/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/msc/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/oocl/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/oocl/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/other/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/other/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/yangming/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/bookingConfirmation/yangming/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/commercialInvoice/other/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/commercialInvoice/other/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/customsAssessment/other/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/customsAssessment/other/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/customsInvoice/other/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/customsInvoice/other/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/deliveryOrder/other/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/deliveryOrder/other/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/draftMbl/other/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/draftMbl/other/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/finalMbL/other/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/finalMbL/other/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/packingList/other/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/packingList/other/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/partnerInvoice/other/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/partnerInvoice/other/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/postprocessing/port_code/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/postprocessing/port_code/prompt_port_code.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/preprocessing/carrier/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/preprocessing/carrier/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/shippingInstruction/other/placeholders.json +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/library/shippingInstruction/other/prompt.txt +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/prompt_library.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/setup.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/tms.py +0 -0
- {data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/utils.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[tool.poetry]
|
|
2
2
|
name = "data-science-document-ai"
|
|
3
|
-
version = "1.
|
|
3
|
+
version = "1.51.1"
|
|
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 = [
|
|
@@ -1,15 +1,15 @@
|
|
|
1
1
|
{
|
|
2
2
|
"type": "OBJECT",
|
|
3
3
|
"properties": {
|
|
4
|
-
"
|
|
4
|
+
"grandTotal": {
|
|
5
5
|
"type": "STRING",
|
|
6
6
|
"nullable": true,
|
|
7
|
-
"description": "The
|
|
7
|
+
"description": "The overall total amount of the invoice. It can be found with the key words Gesamtabgabenbetrag, Gesamtbetrag, or Zu erstattender Abgabenbetrag"
|
|
8
8
|
},
|
|
9
|
-
"
|
|
9
|
+
"currencyCode": {
|
|
10
10
|
"type": "STRING",
|
|
11
11
|
"nullable": true,
|
|
12
|
-
"description": "The
|
|
12
|
+
"description": "The currency in which the invoice is issued. Extract the currency associated with the grand total (grandTotal) amount. It is majorly mentioned as EUR, Euro or €."
|
|
13
13
|
},
|
|
14
14
|
"issueDate": {
|
|
15
15
|
"type": "STRING",
|
|
@@ -13,6 +13,7 @@ Your role is to accurately extract specific entities from these Customs invoices
|
|
|
13
13
|
- Populate fields as defined in the response schema.
|
|
14
14
|
- Multiple line item entries may exist, capture all instances under "lineItem".
|
|
15
15
|
- Use the data field description to understand the context of the data.
|
|
16
|
+
- The amount and the currency is always in EUR both for grandTotal and line items.
|
|
16
17
|
|
|
17
18
|
- containerNumber:
|
|
18
19
|
- Container Number consists of 4 capital letters followed by 7 digits (e.g., TEMU7972458, CAIU7222892).
|
|
@@ -39,9 +40,8 @@ Your role is to accurately extract specific entities from these Customs invoices
|
|
|
39
40
|
- issueDate can also be referred to as "Einfuhrabgabenbescheid" in the invoice. issueDate and serviceDate can be same in some cases.
|
|
40
41
|
- vendor details can be "Hauptzollamt" details in the top portion of the invoice.
|
|
41
42
|
|
|
42
|
-
- lineItem:
|
|
43
|
-
-
|
|
44
|
-
- totalAmount in the Credit Note is the Differenzbetrag in the line items.
|
|
43
|
+
- lineItem: Each line item should be extracted only once. Give priority to the first occurrence of the line item details in the document.
|
|
44
|
+
- totalAmount in the Credit Note is the Differenzbetrag in the line items. The totalAmount value is always or mostly mentioned in EUR currency.
|
|
45
45
|
- deferredDutyPayer can be identified under "Aufschubenhmer" for each line item. It is a combination of number code and entity.
|
|
46
46
|
|
|
47
47
|
You can usually find all the information in the top 2 pages of the invoice.
|
|
File without changes
|
{data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/constants_sandbox.py
RENAMED
|
File without changes
|
|
File without changes
|
{data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/docai_processor_config.yaml
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/postprocessing/common.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{data_science_document_ai-1.50.0 → data_science_document_ai-1.51.1}/src/prompts/prompt_library.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|