data-science-document-ai 1.40.4__tar.gz → 1.41.0__tar.gz

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-science-document-ai
-Version: 1.40.4
+Version: 1.41.0
 Summary: "Document AI repo for data science"
 Author: Naomi Nguyen
 Author-email: naomi.nguyen@forto.com

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "data-science-document-ai"
-version = "1.40.4"
+version = "1.41.0"
 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-1.40.4 → data_science_document_ai-1.41.0}/src/excel_processing.py

@@ -2,6 +2,8 @@
 # flake8: noqa: E402
 import logging
 
+from src.postprocessing.common import llm_prediction_to_tuples
+
 logger = logging.getLogger(__name__)
 
 import asyncio
@@ -73,6 +75,8 @@ async def extract_data_from_excel(
     ]
     extracted_data = {k: v for k, v in await asyncio.gather(*sheet_extract_tasks)}
 
+    # Convert LLM prediction dictionary to tuples of (value, page_number).
+    extracted_data = llm_prediction_to_tuples(extracted_data)
     stored_data = json.dumps(extracted_data)
 
     return extracted_data, stored_data, params["gemini_params"]["model_id"]

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/pdf_processing.py

@@ -14,7 +14,7 @@ from google.cloud.documentai_v1 import Document as docaiv1_document
 
 from src.docai import _batch_process_pdf_w_docai, _process_pdf_w_docai
 from src.excel_processing import extract_data_from_excel
-from src.postprocessing.common import format_all_entities, remove_none_values
+from src.postprocessing.common import format_all_entities, remove_none_values, llm_prediction_to_tuples
 from src.postprocessing.postprocess_booking_confirmation import (
     postprocess_booking_confirmation,
 )
@@ -31,6 +31,7 @@ from src.utils import (
     get_processor_name,
     run_background_tasks,
     validate_based_on_schema,
+    transform_schema_strings
 )
 
 
@@ -104,9 +105,16 @@ async def extract_data_from_pdf_w_docai(
     # Extract entities from the result
     for entity in result.entities:
         value = (
-            {child.type_: child.mention_text for child in entity.properties}
+            {child.type_: (child.mention_text,
+                           child.page_anchor.page_refs[0].page
+                           if hasattr(child.page_anchor.page_refs[0], "page")
+                           else 0)
+             for child in entity.properties}
             if entity.properties
-            else entity.mention_text
+            else (entity.mention_text,
+                  entity.page_anchor.page_refs[0].page
+                  if hasattr(entity.page_anchor.page_refs[0], "page")
+                  else 0)
         )
         aggregated_data[entity.type_].append(value)
 
@@ -220,6 +228,9 @@ async def process_file_w_llm(params, file_content, input_doc_type, llm_client):
         result = await llm_client.get_unified_json_genai(
             prompt=prompt, document=document, response_schema=response_schema
         )
+
+        result = llm_prediction_to_tuples(result)
+
         return result
     return {}
 

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/postprocessing/common.py

@@ -380,6 +380,11 @@ async def format_label(entity_k, entity_value, document_type_code, params):
             ]
         )
         return entity_k, [v for _, v in format_tasks]
+    if isinstance(entity_value, tuple):
+        page = entity_value[1]
+        entity_value = entity_value[0]
+    else:
+        page = -1
     entity_key = entity_k.lower()
     formatted_value = None
 
@@ -474,6 +479,7 @@ async def format_label(entity_k, entity_value, document_type_code, params):
     result = {
         "documentValue": entity_value,
         "formattedValue": formatted_value,
+        "page": page,
     }
     return entity_k, result
 
@@ -616,3 +622,24 @@ def remove_stop_words(lineitem: str):
         .upper()
         .strip()
     )
+
+
+def llm_prediction_to_tuples(llm_prediction):
+    """Convert LLM prediction dictionary to tuples of (value, page_number)."""
+    if isinstance(llm_prediction, dict):
+        if "page_number" in llm_prediction.keys() and "value" in llm_prediction.keys():
+            if llm_prediction["value"]:
+                try:
+                    page_number = int(llm_prediction["page_number"])
+                except:  # noqa: E722
+                    page_number = -1
+                return (llm_prediction["value"], page_number)
+            return None
+        for key, value in llm_prediction.items():
+            llm_prediction[key] = llm_prediction_to_tuples(
+                llm_prediction.get(key, value)
+            )
+    elif isinstance(llm_prediction, list):
+        for i, item in enumerate(llm_prediction):
+            llm_prediction[i] = llm_prediction_to_tuples(item)
+    return llm_prediction

data_science_document_ai-1.41.0/src/prompts/library/bookingConfirmation/evergreen/placeholders.json

@@ -0,0 +1,32 @@
+{
+  "type": "OBJECT",
+  "properties": {
+    "cfsCutOff": {"type": "STRING", "nullable": true, "description": "the date by which an LCL (Less than Container Load) shipment needs to be checked in to a CFS (Container Freight Station) to meet its scheduled sailing"},
+    "bookingNumber": {"type": "STRING", "nullable": true},
+    "cyCutOff": {"type": "STRING", "nullable": true},
+    "gateInReference": {"type": "STRING", "nullable": true},
+    "gateInTerminal": {"type": "STRING", "nullable": true},
+    "mblNumber": {"type": "STRING", "nullable": true},
+    "pickUpReference": {"type": "STRING", "nullable": true},
+    "pickUpTerminal": {"type": "STRING", "nullable": true},
+    "siCutOff": {"type": "STRING", "nullable": true},
+    "vgmCutOff": {"type": "STRING", "nullable": true},
+    "transportLegs": {
+      "type": "ARRAY",
+      "items": {
+        "type": "OBJECT",
+        "properties": {
+            "eta": {"type": "STRING", "nullable": true},
+            "etd": {"type": "STRING", "nullable": true},
+            "imoNumber": {"type": "STRING", "nullable": true},
+            "portOfDischarge": {"type": "STRING", "nullable": true},
+            "portOfLoading": {"type": "STRING", "nullable": true},
+            "vesselName": {"type": "STRING", "nullable": true},
+            "voyage": {"type": "STRING", "nullable": true}
+          },
+        "required": []
+      }
+    }
+  },
+  "required": []
+}

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/prompts/library/bookingConfirmation/evergreen/prompt.txt

@@ -1,3 +1,4 @@
+your task is to extract the text value of the following entities and page numbers starting from 0 where the value was found in the document:
 ```json
 {
 "mblNumber": "Extract the value after the label 'BOOKING NO.'.",

data_science_document_ai-1.41.0/src/prompts/library/bookingConfirmation/hapag-lloyd/placeholders.json

@@ -0,0 +1,32 @@
+{
+  "type": "OBJECT",
+  "properties": {
+    "cfsCutOff": {"type": "STRING", "nullable": true, "description": "the date by which an LCL (Less than Container Load) shipment needs to be checked in to a CFS (Container Freight Station) to meet its scheduled sailing"},
+    "bookingNumber": {"type": "STRING", "nullable": true},
+    "cyCutOff": {"type": "STRING", "nullable": true},
+    "gateInReference": {"type": "STRING", "nullable": true},
+    "gateInTerminal": {"type": "STRING", "nullable": true},
+    "mblNumber": {"type": "STRING", "nullable": true},
+    "pickUpReference": {"type": "STRING", "nullable": true},
+    "pickUpTerminal": {"type": "STRING", "nullable": true},
+    "siCutOff": {"type": "STRING", "nullable": true},
+    "vgmCutOff": {"type": "STRING", "nullable": true},
+    "transportLegs": {
+      "type": "ARRAY",
+      "items": {
+        "type": "OBJECT",
+        "properties": {
+            "eta": {"type": "STRING", "nullable": true},
+            "etd": {"type": "STRING", "nullable": true},
+            "imoNumber": {"type": "STRING", "nullable": true},
+            "portOfDischarge": {"type": "STRING", "nullable": true},
+            "portOfLoading": {"type": "STRING", "nullable": true},
+            "vesselName": {"type": "STRING", "nullable": true},
+            "voyage": {"type": "STRING", "nullable": true}
+          },
+        "required": []
+      }
+    }
+  },
+  "required": []
+}

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/prompts/library/bookingConfirmation/hapag-lloyd/prompt.txt

@@ -18,7 +18,7 @@ transportLegs:
     vesselName: The name of the vessel for a specific leg.
     voyage: The journey or route taken by the vessel for a specific leg.
 
-your task is to extract the text value of the following entities:
+your task is to extract the text value of the following entities and page numbers starting from 0 where the value was found in the document:
 SCHEMA_PLACEHOLDER
 
 Keywords for datapoints:

data_science_document_ai-1.41.0/src/prompts/library/bookingConfirmation/maersk/placeholders.json

@@ -0,0 +1,32 @@
+{
+  "type": "OBJECT",
+  "properties": {
+    "bookingNumber": {"type": "STRING", "nullable": true},
+    "cfsCutOff": {"type": "STRING", "nullable": true, "description": "the date by which an LCL (Less than Container Load) shipment needs to be checked in to a CFS (Container Freight Station) to meet its scheduled sailing"},
+    "cyCutOff": {"type": "STRING", "nullable": true},
+    "gateInReference": {"type": "STRING", "nullable": true},
+    "gateInTerminal": {"type": "STRING", "nullable": true},
+    "mblNumber": {"type": "STRING", "nullable": true},
+    "pickUpReference": {"type": "STRING", "nullable": true},
+    "pickUpTerminal": {"type": "STRING", "nullable": true},
+    "siCutOff": {"type": "STRING", "nullable": true},
+    "vgmCutOff": {"type": "STRING", "nullable": true},
+    "transportLegs": {
+      "type": "ARRAY",
+      "items": {
+        "type": "OBJECT",
+        "properties": {
+            "eta": {"type": "STRING", "nullable": true},
+            "etd": {"type": "STRING", "nullable": true},
+            "imoNumber": {"type": "STRING", "nullable": true},
+            "portOfDischarge": {"type": "STRING", "nullable": true},
+            "portOfLoading": {"type": "STRING", "nullable": true},
+            "vesselName": {"type": "STRING", "nullable": true},
+            "voyage": {"type": "STRING", "nullable": true}
+          },
+        "required": []
+      }
+    }
+  },
+  "required": []
+}

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/prompts/library/bookingConfirmation/maersk/prompt.txt

@@ -18,7 +18,7 @@ transportLegs:
     vesselName: The name of the vessel for a specific leg.
     voyage: The journey or route taken by the vessel for a specific leg.
 
-your task is to extract the text value of the following entities:
+your task is to extract the text value of the following entities and page numbers starting from 0 where the value was found in the document:
 SCHEMA_PLACEHOLDER
 
 Keywords for datapoints:

data_science_document_ai-1.41.0/src/prompts/library/bookingConfirmation/msc/placeholders.json

@@ -0,0 +1,32 @@
+{
+  "type": "OBJECT",
+  "properties": {
+    "cfsCutOff": {"type": "STRING", "nullable": true, "description": "the date by which an LCL (Less than Container Load) shipment needs to be checked in to a CFS (Container Freight Station) to meet its scheduled sailing"},
+    "bookingNumber": {"type": "STRING", "nullable": true},
+    "cyCutOff": {"type": "STRING", "nullable": true},
+    "gateInReference": {"type": "STRING", "nullable": true},
+    "gateInTerminal": {"type": "STRING", "nullable": true},
+    "mblNumber": {"type": "STRING", "nullable": true},
+    "pickUpReference": {"type": "STRING", "nullable": true},
+    "pickUpTerminal": {"type": "STRING", "nullable": true},
+    "siCutOff": {"type": "STRING", "nullable": true},
+    "vgmCutOff": {"type": "STRING", "nullable": true},
+    "transportLegs": {
+      "type": "ARRAY",
+      "items": {
+        "type": "OBJECT",
+        "properties": {
+            "eta": {"type": "STRING", "nullable": true},
+            "etd": {"type": "STRING", "nullable": true},
+            "imoNumber": {"type": "STRING", "nullable": true},
+            "portOfDischarge": {"type": "STRING", "nullable": true},
+            "portOfLoading": {"type": "STRING", "nullable": true},
+            "vesselName": {"type": "STRING", "nullable": true},
+            "voyage": {"type": "STRING", "nullable": true}
+          },
+        "required": []
+      }
+    }
+  },
+  "required": []
+}

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/prompts/library/bookingConfirmation/msc/prompt.txt

@@ -18,7 +18,7 @@ transportLegs:
     vesselName: The name of the vessel for a specific leg.
     voyage: The journey or route taken by the vessel for a specific leg.
 
-your task is to extract the text value of the following entities:
+your task is to extract the text value of the following entities and page numbers starting from 0 where the value was found in the document:
 SCHEMA_PLACEHOLDER
 
 Further explanation and Keywords for the transportLegs part as follows. The below 2 conditions is crucial. Take attention here:

data_science_document_ai-1.41.0/src/prompts/library/bookingConfirmation/oocl/placeholders.json

@@ -0,0 +1,32 @@
+{
+  "type": "OBJECT",
+  "properties": {
+    "cfsCutOff": {"type": "STRING", "nullable": true, "description": "the date by which an LCL (Less than Container Load) shipment needs to be checked in to a CFS (Container Freight Station) to meet its scheduled sailing"},
+    "bookingNumber": {"type": "STRING", "nullable": true},
+    "cyCutOff": {"type": "STRING", "nullable": true},
+    "gateInReference": {"type": "STRING", "nullable": true},
+    "gateInTerminal": {"type": "STRING", "nullable": true},
+    "mblNumber": {"type": "STRING", "nullable": true},
+    "pickUpReference": {"type": "STRING", "nullable": true},
+    "pickUpTerminal": {"type": "STRING", "nullable": true},
+    "siCutOff": {"type": "STRING", "nullable": true},
+    "vgmCutOff": {"type": "STRING", "nullable": true},
+    "transportLegs": {
+      "type": "ARRAY",
+      "items": {
+        "type": "OBJECT",
+        "properties": {
+            "eta": {"type": "STRING", "nullable": true},
+            "etd": {"type": "STRING", "nullable": true},
+            "portOfDischarge": {"type": "STRING", "nullable": true},
+            "portOfLoading": {"type": "STRING", "nullable": true},
+            "vesselName": {"type": "STRING", "nullable": true},
+            "voyage": {"type": "STRING", "nullable": true},
+            "imoNumber": {"type": "STRING", "nullable": true}
+        },
+        "required": []
+      }
+    }
+  },
+  "required": []
+}

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/prompts/library/bookingConfirmation/oocl/prompt.txt

@@ -1,4 +1,6 @@
-bookingNumber: Extract the booking number. This information can be found near the labels "BOOKING ACKNOWLEDGEMENT" or "BOOKING NUMBER". 
+your task is to extract the text value of the following entities and page numbers starting from 0 where the value was found in the document:
+
+bookingNumber: Extract the booking number. This information can be found near the labels "BOOKING ACKNOWLEDGEMENT" or "BOOKING NUMBER".
 gateInReference: This field should have the same value as the bookingNumber.
 cyCutOff: Look for the "INTENDED FCL CY CUT-OFF" label and extract the date and time value.
 vgmCutOff: Look for the "INTENDED VGM CUT-OFF" label and extract the date and time value.

data_science_document_ai-1.41.0/src/prompts/library/bookingConfirmation/other/placeholders.json

@@ -0,0 +1,32 @@
+{
+  "type": "OBJECT",
+  "properties": {
+    "cfsCutOff": {"type": "STRING", "nullable": true, "description": "the date by which an LCL (Less than Container Load) shipment needs to be checked in to a CFS (Container Freight Station) to meet its scheduled sailing"},
+    "bookingNumber": {"type": "STRING", "nullable": true},
+    "cyCutOff": {"type": "STRING", "nullable": true},
+    "gateInReference": {"type": "STRING", "nullable": true},
+    "gateInTerminal": {"type": "STRING", "nullable": true},
+    "mblNumber": {"type": "STRING", "nullable": true},
+    "pickUpReference": {"type": "STRING", "nullable": true},
+    "pickUpTerminal": {"type": "STRING", "nullable": true},
+    "siCutOff": {"type": "STRING", "nullable": true},
+    "vgmCutOff": {"type": "STRING", "nullable": true},
+    "transportLegs": {
+      "type": "ARRAY",
+      "items": {
+        "type": "OBJECT",
+        "properties": {
+            "eta": {"type": "STRING", "nullable": true},
+            "etd": {"type": "STRING", "nullable": true},
+            "imoNumber": {"type": "STRING", "nullable": true},
+            "portOfDischarge": {"type": "STRING", "nullable": true},
+            "portOfLoading": {"type": "STRING", "nullable": true},
+            "vesselName": {"type": "STRING", "nullable": true},
+            "voyage": {"type": "STRING", "nullable": true}
+          },
+        "required": []
+      }
+    }
+  },
+  "required": []
+}

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/prompts/library/bookingConfirmation/other/prompt.txt

@@ -18,7 +18,7 @@ transportLegs:
     vesselName: The name of the vessel for a specific leg.
     voyage: The journey or route taken by the vessel for a specific leg.
 
-your task is to extract the text value of the following entities:
+your task is to extract the text value of the following entities and page numbers starting from 0 where the value was found in the document:
 SCHEMA_PLACEHOLDER
 
 Further explanation for the transportLegs part as follows:

data_science_document_ai-1.41.0/src/prompts/library/bookingConfirmation/yangming/placeholders.json

@@ -0,0 +1,32 @@
+{
+  "type": "OBJECT",
+  "properties": {
+    "cfsCutOff": {"type": "STRING", "nullable": true, "description": "the date by which an LCL (Less than Container Load) shipment needs to be checked in to a CFS (Container Freight Station) to meet its scheduled sailing"},
+    "bookingNumber": {"type": "STRING", "nullable": true},
+    "cyCutOff": {"type": "STRING", "nullable": true},
+    "gateInReference": {"type": "STRING", "nullable": true},
+    "gateInTerminal": {"type": "STRING", "nullable": true},
+    "mblNumber": {"type": "STRING", "nullable": true},
+    "pickUpReference": {"type": "STRING", "nullable": true},
+    "pickUpTerminal": {"type": "STRING", "nullable": true},
+    "siCutOff": {"type": "STRING", "nullable": true},
+    "vgmCutOff": {"type": "STRING", "nullable": true},
+    "transportLegs": {
+      "type": "ARRAY",
+      "items": {
+        "type": "OBJECT",
+        "properties": {
+            "eta": {"type": "STRING", "nullable": true},
+            "etd": {"type": "STRING", "nullable": true},
+            "imoNumber": {"type": "STRING", "nullable": true},
+            "portOfDischarge": {"type": "STRING", "nullable": true},
+            "portOfLoading": {"type": "STRING", "nullable": true},
+            "vesselName": {"type": "STRING", "nullable": true},
+            "voyage": {"type": "STRING", "nullable": true}
+          },
+        "required": []
+      }
+    }
+  },
+  "required": []
+}

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/prompts/library/bookingConfirmation/yangming/prompt.txt

@@ -18,7 +18,7 @@ transportLegs:
     vesselName: The name of the vessel for a specific leg.
     voyage: The journey or route taken by the vessel for a specific leg.
 
-your task is to extract the text value of the following entities:
+your task is to extract the text value of the following entities and page numbers starting from 0 where the value was found in the document:
 SCHEMA_PLACEHOLDER
 
 Keywords for datapoints:

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/prompts/library/bundeskasse/other/placeholders.json

@@ -2,47 +2,47 @@
   "type": "OBJECT",
   "properties": {
       "currencyCode": {
-        "type": "string",
+        "type": "STRING",
         "nullable": true,
         "description": "The currency in which the invoice is issued."
       },
       "grandTotal": {
-        "type": "string",
+        "type": "STRING",
         "nullable": true,
         "description": "The overall total amount of the invoice."
       },
       "issueDate": {
-        "type": "string",
+        "type": "STRING",
         "nullable": true,
         "description": "The date the document was issued."
       },
       "recipientAddress": {
-        "type": "string",
+        "type": "STRING",
         "nullable": true,
         "description": "The address of the recipient."
       },
       "recipientName": {
-        "type": "string",
+        "type": "STRING",
         "nullable": true,
         "description": "The name of the recipient."
       },
       "serviceDate": {
-        "type": "string",
+        "type": "STRING",
         "nullable": true,
         "description": "The date of service or transaction."
       },
       "shipmentId": {
-        "type": "string",
+        "type": "STRING",
         "nullable": true,
         "description": "Starting with an \"S\" and followed by 6 or 7 digits. Example: S124321"
       },
       "vendorName": {
-        "type": "string",
+        "type": "STRING",
         "nullable": true,
         "description": "The name of the vendor."
       },
       "vendorAddress": {
-        "type": "string",
+        "type": "STRING",
         "nullable": true,
         "description": "The address of the vendor."
       },
@@ -52,37 +52,37 @@
               "type": "OBJECT",
               "properties": {
                   "deferredDutyPayer": {
-                    "type": "string",
+                    "type": "STRING",
                     "nullable": true,
                     "description": "It can be identified under \"Aufschubenhmer\" for each line item"
                   },
                   "name": {
-                    "type": "string",
+                    "type": "STRING",
                     "nullable": true,
                     "description": "The name or description of the line item A0000 and B0000"
                   },
                   "taxType": {
-                    "type": "string",
+                    "type": "STRING",
                     "nullable": true,
                     "description": "It's a line item mentioned in the invoice. For example; A0000 and B0000"
                   },
                   "totalAmount": {
-                    "type": "string",
+                    "type": "STRING",
                     "nullable": true,
                     "description": "The total amount for the line item."
                   },
                   "totalAmountCurrency": {
-                    "type": "string",
+                    "type": "STRING",
                     "nullable": true,
                     "description": "The currency of the total amount."
                   },
                   "vatId": {
-                    "type": "string",
+                    "type": "STRING",
                     "nullable": true,
                     "description": "The VAT identification number. This is named a Konto-Nummer for each line item."
                   },
                   "dueDate": {
-                    "type": "string",
+                    "type": "STRING",
                     "nullable": true,
                     "description": "It's a due date. Due date to pay the amount. It's usually mentioned either in a date or a number of days format"
                   }
@@ -91,20 +91,20 @@
           }
       },
       "invoiceNumber": {
-        "type": "string",
+        "type": "STRING",
         "nullable": true,
         "description": "Invoice Number is a unique identifier for the invoice, it starts with \"ATC\", \"AT-C\", or \"AT/C\" only (e.g., ATC40, AT-C-40-, AT/C/40/....). Do NOT extract \"NIZZA-Registrierkennzeichen number."
       },
       "containerNumber": {
         "type": "ARRAY",
         "items": {
-          "type": "string",
+          "type": "STRING",
           "nullable": true,
           "description": "The unique identifier for each container. It always starts with 4 capital letters and followed by 7 digits. Example: TEMU7972458."
       }
   },
       "creditNoteInvoiceNumber": {
-        "type": "string",
+        "type": "STRING",
         "nullable": true,
         "description": "The unique identifier for the associated Invoice. The number usually starts with ATS..."
       }

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/prompts/library/bundeskasse/other/prompt.txt

@@ -1,6 +1,6 @@
 <PERSONA> You are an efficient document entity data extraction specialist working for a Freight Forwarding company. <PERSONA>
 
-<TASK>Your task is to extract data from customs invoice documents as per the given response schema structure.<TASK>
+<TASK>Your task is to extract data and page numbers starting from 0 from customs invoice documents as per the given response schema structure.<TASK>
 
 <CONTEXT>
 The Freight Forwarding company receives Customs invoices from Customs Brokers called Bundeskasse.

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/prompts/library/commercialInvoice/other/prompt.txt

@@ -2,7 +2,8 @@ Task: You are a document entity extraction specialist. Given a document, your ta
 
 Extract all the data points from the given document.
 Each data point is part of a master field called skus. There may be multiple skus entries in a document.
-Your goal is to extract all instances.
+Your task is to extract the text value of the entities and page numbers starting from 0 starting from 0 where the value was found in the document.
+
 
 Instructions:
 - Populate fields as defined in the response schema.

{data_science_document_ai-1.40.4 → data_science_document_ai-1.41.0}/src/prompts/library/customsAssessment/other/prompt.txt

@@ -15,7 +15,7 @@ containers:
     goodsDescription: Goods description.
 
 
-Your task is to extract the text value of the following entities:
+Your task is to extract the text value of the following entities and page numbers starting from 0 where the value was found in the document:
 SCHEMA_PLACEHOLDER
 
 Keywords for datapoints: