data-science-document-ai 1.56.0__tar.gz → 1.57.0__tar.gz

{data_science_document_ai-1.56.0 → data_science_document_ai-1.57.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-science-document-ai
-Version: 1.56.0
+Version: 1.57.0
 Summary: "Document AI repo for data science"
 Author: Naomi Nguyen
 Author-email: naomi.nguyen@forto.com

{data_science_document_ai-1.56.0 → data_science_document_ai-1.57.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "data-science-document-ai"
-version = "1.56.0"
+version = "1.57.0"
 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-1.56.0 → data_science_document_ai-1.57.0}/src/constants.py

@@ -37,6 +37,8 @@ project_parameters = {
     # models metadata (confidence),
     "g_model_data_folder": "models",
     "local_model_data_folder": "data",
+    "if_use_docai": False,
+    "if_use_llm": True,  # Keep it always True
     "released_doc_types": {
         "bookingConfirmation",
         "packingList",
@@ -51,16 +53,6 @@ project_parameters = {
         "customsInvoice",
         "bundeskasse",
     },
-    "model_selector": {
-        "stable": {
-            "bookingConfirmation": 1,
-        },
-        "beta": {
-            "bookingConfirmation": 0,
-        },
-    },
-    # this is the model selector for the model to be used from the model_config.yaml
-    # file based on the environment, 0 mean the first model in the list
     # LLM model parameters
     "gemini_params": {
         "temperature": 0,
@@ -78,25 +70,15 @@ project_parameters = {
         "seed": 42,
         "model_id": "gemini-2.5-flash",
     },
-    # Key to combine the LLM results with the Doc Ai results
-    "key_to_combine": {
-        "bookingConfirmation": ["transportLegs"],
-        "arrivalNotice": ["containers"],
-        "finalMbL": ["containers"],
-        "draftMbl": ["containers"],
-        "deliveryOrder": ["Equipment", "TransportLeg"],
-        "customsAssessment": ["containers"],
-        "packingList": ["skuData"],
-        "commercialInvoice": ["skus"],
-        "shippingInstruction": ["containers"],
-        "partnerInvoice": ["lineItem"],
-        "customsInvoice": ["lineItem"],
-        "bundeskasse": ["lineItem"],
-    },
 }
 
 # Hardcoded rules for data points formatting that can't be based on label name alone
 formatting_rules = {
-    "bookingConfirmation": {"pickUpTerminal": "depot", "gateInTerminal": "terminal"},
+    "bookingConfirmation": {
+        "pickUpDepotCode": "depot",
+        "dropOffDepotCode": "depot",
+        "gateInTerminalCode": "terminal",
+        "pickUpTerminalCode": "terminal",
+    },
     "deliveryOrder": {"pickUpTerminal": "terminal", "EmptyContainerDepot": "depot"},
 }

data_science_document_ai-1.57.0/src/docai_processor_config.yaml

@@ -0,0 +1,9 @@
+models_project_id: "738250249861"
+model_config:
+  stable:
+    bookingConfirmation:
+      - id: "dc3e714cd168aeaa"
+        details:
+          display_name: "doc_cap_bookingConfirmation"
+          author: "reet.kanjilal@forto.com"
+          created_date: ""

{data_science_document_ai-1.56.0 → data_science_document_ai-1.57.0}/src/pdf_processing.py

@@ -201,9 +201,6 @@ async def process_file_w_llm(params, file_content, input_doc_type, llm_client):
     number_of_pages = get_pdf_page_count(file_content)
     logger.info(f"processing {input_doc_type} with {number_of_pages} pages...")
 
-    # get the schema placeholder
-    response_schema = prompt_library.library[input_doc_type]["other"]["placeholders"]
-
     carrier = "other"
     carrier_schema = (
         prompt_library.library.get("preprocessing", {})
@@ -240,6 +237,9 @@ async def process_file_w_llm(params, file_content, input_doc_type, llm_client):
     # get the related prompt from predefined prompt library
     prompt = prompt_library.library[input_doc_type][carrier]["prompt"]
 
+    # get the schema placeholder
+    response_schema = prompt_library.library[input_doc_type][carrier]["placeholders"]
+
     # Add page-number extraction for moderately large docs
     use_chunking = number_of_pages >= params["chunk_after"]
 
@@ -353,8 +353,7 @@ async def extract_data_from_pdf_w_llm(params, input_doc_type, file_content, llm_
     # Add currency from the amount field
     if input_doc_type in ["commercialInvoice"]:
         result = postprocessing_commercial_invoice(result, params, input_doc_type)
-    elif input_doc_type == "bookingConfirmation":
-        result = postprocess_booking_confirmation(result)
+
     return result, llm_client.model_id
 
 
@@ -373,13 +372,14 @@ def combine_llm_results_w_doc_ai(
     Returns:
         combined result
     """
-    result = doc_ai.copy()
-    llm = remove_none_values(llm)
-    if not llm:
+    result = remove_none_values(llm)
+
+    docAi = doc_ai.copy()
+    if not docAi:
         return result
 
     # Merge top-level keys
-    result.update({k: v for k, v in llm.items() if k not in result})
+    result.update({k: v for k, v in docAi.items() if k not in result})
 
     if (
         input_doc_type
@@ -387,28 +387,28 @@ def combine_llm_results_w_doc_ai(
         and keys_to_combine
     ):
         result.update(
-            {key: llm.get(key) for key in keys_to_combine if key in llm.keys()}
+            {key: docAi.get(key) for key in keys_to_combine if key in docAi.keys()}
         )
         return result
 
     # Handle specific key-based merging logic for multiple keys
     if keys_to_combine:
         for key in keys_to_combine:
-            if key in llm.keys():
+            if key in docAi.keys():
                 # Merge the list of dictionaries
-                # If the length of the LLM list is less than the Doc AI result, replace with the LLM list
-                if len(llm[key]) < len(result[key]):
-                    result[key] = llm[key]
+                # If the length of the docAi list is less than the LLM result, replace with the docAi list
+                if len(docAi[key]) < len(result[key]):
+                    result[key] = docAi[key]
                 else:
-                    # If the length of the LLM list is greater than or equal to the Doc AI result,
+                    # If the length of the docAi list is greater than or equal to the LLM result,
                     # add & merge the dictionaries
-                    if isinstance(llm[key], list):
-                        for i in range(len(llm[key])):
+                    if isinstance(docAi[key], list):
+                        for i in range(len(docAi[key])):
                             if i == len(result[key]):
-                                result[key].append(llm[key][i])
+                                result[key].append(docAi[key][i])
                             else:
-                                for sub_key in llm[key][i].keys():
-                                    result[key][i][sub_key] = llm[key][i][sub_key]
+                                for sub_key in docAi[key][i].keys():
+                                    result[key][i][sub_key] = docAi[key][i][sub_key]
     return result
 
 
@@ -502,13 +502,15 @@ async def data_extraction_manual_flow(
     page_count = None
     # Validate the file type
     if mime_type == "application/pdf":
+        if_use_docai = params["if_use_docai"]
+
         # Enable Doc Ai only for certain document types.
-        if_use_docai = (
-            True if meta.documentTypeCode in params["model_config"]["stable"] else False
-        )
-        if_use_llm = (
-            True if meta.documentTypeCode in params["key_to_combine"].keys() else False
-        )
+        if params["if_use_docai"]:
+            if_use_docai = (
+                True
+                if meta.documentTypeCode in params["model_config"]["stable"]
+                else False
+            )
 
         (
             extracted_data,
@@ -520,7 +522,7 @@ async def data_extraction_manual_flow(
             meta.documentTypeCode,
             processor_client,
             if_use_docai=if_use_docai,
-            if_use_llm=if_use_llm,
+            if_use_llm=params["if_use_llm"],
             llm_client=llm_client,
             isBetaTest=False,
         )

data_science_document_ai-1.57.0/src/prompts/library/bookingConfirmation/evergreen/placeholders.json

@@ -0,0 +1,146 @@
+{
+  "type": "OBJECT",
+  "properties": {
+    "bookingNumber": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "A unique identifier assigned to the shipment booking, used for tracking and reference. They are often referred to as 'Booking No.', 'Booking Reference', 'Our Reference', or 'Order Ref'."
+    },
+    "contractNumber": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "It's a contract number between the carrier and Forto Logistics SE & Co KG."
+    },
+    "pickUpTerminalCode": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The specific terminal for cargo pickup during the import shipment."
+    },
+    "gateInTerminalCode": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The specific terminal where cargo is gated in especially Export terminal delivery address. E.g., Export terminal delivery address, Export terminal location, or Export terminal name."
+    },
+    "performaDate": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The date considered to apply the rates and charges specified in the booking confirmation"
+    },
+    "cyCutOff": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The datetime by which the cargo to be delivered to the Container Yard. It can be found with keys FCL delivery cut-off, FCL DG delivery cut-off, CY CUT OFF, CY Closing."
+    },
+    "gateInReference": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "A reference code for cargo entering the terminal to drop the loaded cargo for Export. Sometimes it can be 'Our Reference'."
+    },
+    "mblNumber": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "Bill of Lading number (B/L NO.), a document issued by the carrier."
+    },
+    "pickUpReference": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "A reference code for cargo pickup during the import shipment. Sometimes it can be 'Our Reference'."
+    },
+    "siCutOff": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The deadline datetime for submitting the Shipping Instructions (SI) to the carrier. It can be found with keys Shipping Instruction Closing."
+    },
+    "vgmCutOff": {
+      "type": "STRING",
+      "nullable": true,
+        "description": "The deadline datetime for submitting the Verified Gross Mass (VGM) to the carrier. It can be found with keys VGM DEADLINE, VGM DUE, VGM CUT OFF."
+    },
+    "containers": {
+      "type": "ARRAY",
+      "items": {
+        "type": "OBJECT",
+        "properties": {
+          "containerType": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The size / type of the container, such as 20ft, 40ft, 40HC, 20DC etc under Type/Size column."
+          },
+          "pickUpDepotCode": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The depot code where the empty container will be picked up. It is identified as Empty Pick Up Depot or Export Empty Pick Up Depot(s)."
+          },
+          "dropOffDepotCode": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The depot code where the empty container will be dropped off."
+          }
+        }
+      },
+      "required": ["containerType", "pickupDepotCode", "dropoffDepotCode"]
+    },
+    "transportLegs": {
+      "type": "ARRAY",
+      "items": {
+        "type": "OBJECT",
+        "properties": {
+          "eta": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "Estimated Time of Arrival (ETA) is the expected date when the shipment will arrive at its destination."
+          },
+          "etd": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "Estimated Time of Departure (ETD) is the expected date when the shipment will leave the origin port."
+          },
+          "imoNumber": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The International Maritime Organization number for a specific leg. It can be found as IMO No, IMO number."
+          },
+          "portOfDischarge": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The port where the goods are discharged from the vessel. This is the destination port for the shipment. It can be found at POD, Port of Discharge, To, Discharge Port"
+          },
+          "portOfLoading": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The port where the goods are loaded onto the vessel. This is the origin port for the shipment. It can be found at POL, Port of Loading, From, Load Port"
+          },
+          "vesselName": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The name of the vessel carrying the shipment. It can be found at vessel, INTENDED VESSEL/VOYAGE"
+          },
+          "voyage": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The journey or route taken by the vessel for a specific leg. It can be found at Voy. no, INTENDED VESSEL/VOYAGE"
+          }
+        }
+      },
+      "required": [
+          "eta",
+          "etd",
+          "portOfDischarge",
+          "portOfLoading",
+          "vesselName",
+          "voyage"
+        ]
+    },
+    "carrierAddress": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The address of the carrier who provides service and issued the document."
+    },
+    "carrierName": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The name of the carrier who issued the document e,g, Hapag-Lloyd."
+    }
+  },
+  "required": ["bookingNumber", "transportLegs", "containers", "cyCutOff", "vgmCutOff", "siCutOff"]
+}

{data_science_document_ai-1.56.0 → data_science_document_ai-1.57.0}/src/prompts/library/bookingConfirmation/evergreen/prompt.txt

@@ -1,6 +1,14 @@
-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
-{
+<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 Booking Confirmation documents as per the given response schema structure. <TASK>
+
+<CONTEXT>
+The Freight Forwarding company receives Booking Confirmation from EverGreen Carrier (Shipping Lines) partner.
+These Booking Confirmations contain various details related to booking, container pick up and drop off depot details, vessel details, as well as other transport Legs data.
+They may be written in different languages such as English, German, Vietnamese, Chinese, and other European languages, and can appear in a variety of formats and layouts.
+Your role is to accurately extract specific entities from these Booking Confirmations to support efficient processing and accurate record-keeping.
+<CONTEXT>
+
 "mblNumber": "Extract the value after the label 'BOOKING NO.'.",
 "gateInReference": "Extract the value after the label 'BOOKING NO.'.",
 "pickUpReference": "Extract the value after the label 'BOOKING NO.'.",
@@ -14,23 +22,19 @@ your task is to extract the text value of the following entities and page number
 "portOfDischarge": "Extract the text after the label 'PORT OF DISCHARGING:' and before 'FINAL DESTINATION'.",
 "pickUpTerminal": "Extract the text after the label 'EMPTY PICK UP AT:' removing any extra spaces or line breaks.",
 "gateInTerminal": "Extract the text after the label 'FULL RETURN TO:' removing any extra spaces or line breaks.",
-"transportLegs": [
-{
-"portOfLoading": "For the first leg, use the extracted 'portOfLoading'.",
-"portOfDischarge": "Extract the text after the label 'T/S PORT OF LOADING:'.",
-"vesselName": "For the first leg, use the extracted 'vesselName'.",
-"voyage": "Voyage is a code of numbers and letters sometimes separated by '-'. For the first leg, use the extracted 'voyage'.",
-"eta": "Extract the date after the label 'ETA DATE' that appears within the section starting with 'FINAL DESTINATION:' and ending with 'T/S PORT OF LOADING:'.",
-"etd": "Extract the date after the label 'ETD DATE' that appears within the section starting with 'PORT OF LOADING:' and ending with 'FINAL DESTINATION:'.",
-},
-{
+
+"transportLegs":
+    "portOfLoading": "For the first leg, use the extracted 'portOfLoading'.",
+    "portOfDischarge": "Extract the text after the label 'T/S PORT OF LOADING:'.",
+    "vesselName": "For the first leg, use the extracted 'vesselName'.",
+    "voyage": "Voyage is a code of numbers and letters sometimes separated by '-'. For the first leg, use the extracted 'voyage'.",
+    "eta": "Extract the date after the label 'ETA DATE' that appears within the section starting with 'FINAL DESTINATION:' and ending with 'T/S PORT OF LOADING:'.",
+    "etd": "Extract the date after the label 'ETD DATE' that appears within the section starting with 'PORT OF LOADING:' and ending with 'FINAL DESTINATION:'.",
+
+
 "portOfLoading": "For the second leg, use the 'portOfDischarge' from the previous leg.",
 "portOfDischarge": "For the second leg, use the extracted 'portOfDischarge' from the main extraction.",
 "vesselName": "Extract the text after the label 'EST. CONNECT VSL/VOY:' and before the hyphen and numbers.",
 "voyage": "Voyage is a code of numbers and letters sometimes separated by '-'. Extract the code after the label 'EST. CONNECT VSL/VOY:' and after the vessel name.",
 "eta": "Extract the date after the label 'ETA DATE' that is after the line that contains 'T/S PORT OF LOADING'",
 "etd": "Extract the date after the label 'ETD DATE' that is related to the 'EST. CONNECT VSL/VOY:'. "
-}
-]
-}
-```

data_science_document_ai-1.57.0/src/prompts/library/bookingConfirmation/hapag-lloyd/placeholders.json

@@ -0,0 +1,146 @@
+{
+  "type": "OBJECT",
+  "properties": {
+    "bookingNumber": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "A unique identifier assigned to the shipment booking, used for tracking and reference. They are often referred to as 'Booking No.', 'Booking Reference', 'Our Reference', or 'Order Ref'."
+    },
+    "contractNumber": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "It's a contract number between the carrier and Forto Logistics SE & Co KG."
+    },
+    "pickUpTerminalCode": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The specific terminal for cargo pickup during the import shipment."
+    },
+    "gateInTerminalCode": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The specific terminal where cargo is gated in especially Export terminal delivery address. E.g., Export terminal delivery address, Export terminal location, or Export terminal name."
+    },
+    "performaDate": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The date considered to apply the rates and charges specified in the booking confirmation"
+    },
+    "cyCutOff": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The datetime by which the cargo to be delivered to the Container Yard. It can be found with keys FCL delivery cut-off, FCL DG delivery cut-off, CY CUT OFF, CY Closing."
+    },
+    "gateInReference": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "A reference code for cargo entering the terminal to drop the loaded cargo for Export. Sometimes it can be 'Our Reference'."
+    },
+    "mblNumber": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "Bill of Lading number (B/L NO.), a document issued by the carrier."
+    },
+    "pickUpReference": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "A reference code for cargo pickup during the import shipment. Sometimes it can be 'Our Reference'."
+    },
+    "siCutOff": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The deadline datetime for submitting the Shipping Instructions (SI) to the carrier. It can be found with keys Shipping Instruction Closing."
+    },
+    "vgmCutOff": {
+      "type": "STRING",
+      "nullable": true,
+        "description": "The deadline datetime for submitting the Verified Gross Mass (VGM) to the carrier. It can be found with keys VGM DEADLINE, VGM DUE, VGM CUT OFF."
+    },
+    "containers": {
+      "type": "ARRAY",
+      "items": {
+        "type": "OBJECT",
+        "properties": {
+          "containerType": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The size / type of the container, such as 20ft, 40ft, 40HC, 20DC etc under Type/Size column."
+          },
+          "pickUpDepotCode": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The depot code where the empty container will be picked up. It is identified as Empty Pick Up Depot or Export Empty Pick Up Depot(s)."
+          },
+          "dropOffDepotCode": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The depot code where the empty container will be dropped off."
+          }
+        }
+      },
+      "required": ["containerType", "pickupDepotCode", "dropoffDepotCode"]
+    },
+    "transportLegs": {
+      "type": "ARRAY",
+      "items": {
+        "type": "OBJECT",
+        "properties": {
+          "eta": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "Estimated Time of Arrival (ETA) is the expected date when the shipment will arrive at its destination."
+          },
+          "etd": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "Estimated Time of Departure (ETD) is the expected date when the shipment will leave the origin port."
+          },
+          "imoNumber": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The International Maritime Organization number for a specific leg. It can be found as IMO No, IMO number."
+          },
+          "portOfDischarge": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The port where the goods are discharged from the vessel. This is the destination port for the shipment. It can be found at POD, Port of Discharge, To, Discharge Port"
+          },
+          "portOfLoading": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The port where the goods are loaded onto the vessel. This is the origin port for the shipment. It can be found at POL, Port of Loading, From, Load Port"
+          },
+          "vesselName": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The name of the vessel carrying the shipment. It can be found at vessel, INTENDED VESSEL/VOYAGE"
+          },
+          "voyage": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The journey or route taken by the vessel for a specific leg. It can be found at Voy. no, INTENDED VESSEL/VOYAGE"
+          }
+        }
+      },
+      "required": [
+          "eta",
+          "etd",
+          "portOfDischarge",
+          "portOfLoading",
+          "vesselName",
+          "voyage"
+        ]
+    },
+    "carrierAddress": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The address of the carrier who provides service and issued the document."
+    },
+    "carrierName": {
+      "type": "STRING",
+      "nullable": true,
+      "description": "The name of the carrier who issued the document e,g, Hapag-Lloyd."
+    }
+  },
+  "required": ["bookingNumber", "transportLegs", "containers", "cyCutOff", "vgmCutOff", "siCutOff"]
+}

data_science_document_ai-1.57.0/src/prompts/library/bookingConfirmation/hapag-lloyd/prompt.txt

@@ -0,0 +1,59 @@
+<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 Booking Confirmation documents as per the given response schema structure. <TASK>
+
+<CONTEXT>
+The Freight Forwarding company receives Booking Confirmation from Hapag-Lloyd Carrier (Shipping Lines) partners.
+These Booking Confirmations contain various details related to booking, container pick up and drop off depot details, vessel details, as well as other transport Legs data.
+They may be written in different languages such as English, German, Vietnamese, Chinese, and other European languages, and can appear in a variety of formats and layouts.
+Your role is to accurately extract specific entities from these Booking Confirmations to support efficient processing and accurate record-keeping.
+
+
+To provide context on the journey of a containers for both Export and Import shipments,
+For Export shipment: An empty container is picked up from a depot (pickupDepotCode) using a pickUpReference and goods loaded into it at a warehouse. Then the loaded container / cargo is transported back to a Container Yard or gateInTerminal before the cyCutOff date for further shipping processes.
+For Import Shipment: The loaded container / cargo arrives at a port of discharge then picked up at pickUpTerminal using pickUpReference. After delivery, an empty container is returned to a depot (dropOffDepotCode).
+<CONTEXT>
+
+<INSTRUCTIONS>
+- Populate fields as defined in the response schema.
+- Use the data field description to understand the context of the data.
+
+- gateInTerminal: The specific terminal where cargo is gated in. It can be found as Export terminal delivery address, PORT OF LOADING (after the slash '/').
+- gateInReference: A reference code for cargo entering the terminal. If not mentioned explicitly and gateInTerminal is extracted, then use bookingNumber as gateInReference.
+- pickUpTerminal: The specific terminal for cargo pickup. It can be found as Import pick up address(es),  PORT OF DISCHARGE (after the slash '/').
+- pickUpReference: A reference code for cargo pickup. If not mentioned explicitly and pickUpTerminal is extracted, then use bookingNumber as pickUpReference.
+
+- cyCutOff: The deadline for cargo to be delivered to the Container Yard. It can be referred to as FCL delivery cut-off, CY CUT OFF, CY Closing - Latest Return Container Date, Cargo Cut-off deadline
+- siCutOff: The deadline for submitting shipping instructions. It can be referred to as Shipping Instruction closing, SI Cut Off, Shipping Instruction deadline, INTENDED SI CUT-OFF
+- vgmCutOff: The deadline for submitting the Verified Gross Mass of the cargo. It can be referred to as VGM cut-off, VGM Submission Deadline, Verified Gross Mass deadline
+
+- carrierName and carrierAddress:
+    - Extract the name and address of the carrier who is the main parent company in the document.
+    - Example:
+        - "Hapag-Lloyd AG" or "Hapag-Lloyd Aktiengesellschaft" for vendorName.
+
+- transportLegs: Multiple Transport Legs entries may exist, capture all instances under "transportLegs". Make sure the order of the legs are important.
+    - eta: The estimated time of arrival for a specific leg.
+    - etd: The estimated time of departure for a specific leg.
+    - imoNumber: The International Maritime Organization number for a specific leg.
+    - portOfDischarge: The port where cargo is unloaded for a specific leg.
+    - portOfLoading: The port where cargo is loaded for a specific leg.
+    - vesselName: The name of the vessel for a specific leg.
+    - voyage: The journey or route taken by the vessel for a specific leg.
+
+- Containers: Need to extract Depot details per Container Type. Multiple Containers entries may exist, capture all instances under "Containers".
+    - containerType: The type of container (e.g., 20FT, 40FT, 20ft, 40ft, 40HC, 20DC, etc...).
+    - pickupDepotCode: The code of the depot where the empty container is picked up.
+    - dropOffDepotCode: The code of the depot where the empty container is dropped off.
+
+IMPORTANT explanation for the transportLegs part as follows:
+- There is at least one leg in each document.
+- 'eta' must be equal or later than 'etd'!
+- Multiple legs are possible. When there are multiple legs,
+    - Sequential Sorting: You must manually re-order legs based on etd then eta, regardless of their order in the source text.
+    - The Connectivity Rule: For any sequence of legs, the Destination (Port of Discharge) of the previous leg must match the Origin (Port of Loading) of the following leg.
+    - Transhipment Handling: Treat any mentioned "Transhipment Port" as the bridge between two legs (Discharge for Leg A / Loading for Leg B).
+    - Timeline Integrity: Ensure a "No Time Travel" policy: The eta of a previous leg must be earlier than or equal to the etd of the following leg.
+    - Naming Convention: Look for Port Names followed by abbreviations in parentheses, e.g., "Port Name (ABCDE)".
+
+<INSTRUCTIONS>