data-science-document-ai 1.51.0__tar.gz → 1.60.1__tar.gz

{data_science_document_ai-1.51.0 → data_science_document_ai-1.60.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-science-document-ai
-Version: 1.51.0
+Version: 1.60.1
 Summary: "Document AI repo for data science"
 Author: Naomi Nguyen
 Author-email: naomi.nguyen@forto.com

{data_science_document_ai-1.51.0 → data_science_document_ai-1.60.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "data-science-document-ai"
-version = "1.51.0"
+version = "1.60.1"
 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-1.51.0 → data_science_document_ai-1.60.1}/src/constants.py

@@ -20,10 +20,11 @@ project_parameters = {
     # Fuzzy lookup
     "g_model_fuzzy_lookup_folder": "fuzzy_lookup",
     "item_code_lookup": "line_item_kvp_table.json",
+    "intermodal_partners": "intermodal_partners.json",
     "invoice_classification_lookup": "invoice_classification.json",
     "reverse_charge_sentence_lookup": "reverse_charge_sentences.json",
     # Fuzzy logic params
-    "fuzzy_threshold_item_code": 90,
+    "fuzzy_threshold_item_code": 92,
     "fuzzy_threshold_reverse_charge": 80,
     "fuzzy_threshold_invoice_classification": 70,
     # Chunking params
@@ -36,6 +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",
@@ -50,16 +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,
@@ -77,25 +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-1.60.1/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-1.51.0 → data_science_document_ai-1.60.1}/src/pdf_processing.py

@@ -32,7 +32,6 @@ from src.postprocessing.postprocess_partner_invoice import (
 from src.prompts.prompt_library import prompt_library
 from src.utils import (
     extract_top_pages,
-    generate_schema_structure,
     get_pdf_page_count,
     get_processor_name,
     run_background_tasks,
@@ -202,9 +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", {})
@@ -241,6 +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"]
 
@@ -258,7 +257,11 @@ async def process_file_w_llm(params, file_content, input_doc_type, llm_client):
     ):
         tasks.append(
             process_chunk_with_retry(
-                chunk, prompt, response_schema, llm_client, input_doc_type
+                chunk,
+                prompt,
+                response_schema,
+                llm_client,
+                input_doc_type,
             )
         )
 
@@ -350,8 +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
 
 
@@ -370,13 +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
@@ -384,28 +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
 
 
@@ -499,13 +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,
@@ -517,7 +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-1.51.0 → data_science_document_ai-1.60.1}/src/postprocessing/postprocess_partner_invoice.py

@@ -1,4 +1,6 @@
 """This module contains the postprocessing functions for the partner invoice."""
+from collections import defaultdict
+
 from rapidfuzz import fuzz, process
 
 from src.io import logger
@@ -143,6 +145,20 @@ def update_recipient_and_vendor(aggregated_data, is_recipient_forto):
     ] = "Dasbachstraße 15, 54292 Trier, Germany"
 
 
+def select_unique_bank_account(bank_account):
+    # Select the unique bank account if multiple are present
+    if isinstance(bank_account, list) and bank_account:
+        best = defaultdict(lambda: None)
+
+        for item in bank_account:
+            dv = item["documentValue"]
+            if best[dv] is None or item["page"] < best[dv]["page"]:
+                best[dv] = item
+
+        unique = list(best.values())
+        return unique
+
+
 async def process_partner_invoice(params, aggregated_data, document_type_code):
     """Process the partner invoice data."""
     # Post process bundeskasse invoices
@@ -150,6 +166,11 @@ async def process_partner_invoice(params, aggregated_data, document_type_code):
         post_process_bundeskasse(aggregated_data)
         return
 
+    if "bankAccount" in aggregated_data:
+        aggregated_data["bankAccount"] = select_unique_bank_account(
+            aggregated_data["bankAccount"]
+        )
+
     line_items = aggregated_data.get("lineItem", [])
     # Add debug logging
     logger.info(f"Processing partnerInvoice with {len(line_items)} line items")
@@ -167,15 +188,20 @@ async def process_partner_invoice(params, aggregated_data, document_type_code):
         reverse_charge_info["formattedValue"] = reverse_charge_value
         reverse_charge = aggregated_data.pop("reverseChargeSentence", None)
 
+    # Partner Name
+    partner_name = aggregated_data.get("vendorName", {}).get("documentValue", None)
+
     # Process everything in one go
-    processed_items = await process_line_items_batch(params, line_items, reverse_charge)
+    processed_items = await process_line_items_batch(
+        params, line_items, reverse_charge, partner_name
+    )
 
     # Update your main data structure
     aggregated_data["lineItem"] = processed_items
 
 
 async def process_line_items_batch(
-    params: dict, line_items: list[dict], reverse_charge=None
+    params: dict, line_items: list[dict], reverse_charge=None, partner_name=None
 ):
     """
     Processes all line items efficiently using a "Split-Apply-Combine" strategy.
@@ -213,23 +239,12 @@ async def process_line_items_batch(
 
     # Batch API Call for Embedding lookups
     if pending_line_items:
-        values_to_fetch = list(set(pending_line_items.values()))
-        logger.info(f"Mapping {len(values_to_fetch)} line items from Embedding API...")
-
-        # Await the batch response {"desc1": "code1", "desc2": "code2"}
-        api_results = await get_tms_mappings(
-            input_list=values_to_fetch, embedding_type="line_items"
-        )
+        code_map = await fetch_line_item_codes(pending_line_items, partner_name, params)
 
-        # Merge API results back into original list
         for index, desc in pending_line_items.items():
-            # Get result from API response, or None if API failed for that item
-            forto_code = api_results.get(desc)
-
-            # Update the original item
             line_items[index]["itemCode"] = {
                 "documentValue": desc,
-                "formattedValue": forto_code,  # Might be None if API failed
+                "formattedValue": code_map.get(desc),
                 "page": line_items[index]["lineItemDescription"].get("page"),
             }
 
@@ -285,11 +300,14 @@ def if_reverse_charge_sentence(sentence: str, params):
         return False
 
     # Check if the sentence is similar to any of the reverse charge sentences
-    _, is_reverse_charge = get_fuzzy_match_score(
-        sentence, reverse_charge_sentences, threshold
+    match, _ = get_fuzzy_match_score(
+        sentence, list(reverse_charge_sentences.keys()), threshold
     )
 
-    return is_reverse_charge
+    if match:
+        return reverse_charge_sentences[match]
+
+    return False
 
 
 def find_matching_lineitem(new_lineitem: str, kvp_dict: dict, threshold=90):
@@ -320,12 +338,13 @@ def find_matching_lineitem(new_lineitem: str, kvp_dict: dict, threshold=90):
     return None
 
 
-async def associate_forto_item_code(line_item_data, params):
+async def associate_forto_item_code(line_item_data, params, partner_name=None):
     """
     Associates Forto item codes to a list of line item descriptions.
     Args:
         line_item_data (dict): A dictionary where keys are original descriptions and values are cleaned descriptions.
         params (dict): Parameters containing lookup data and thresholds.
+        partner_name (str, optional): The name of the partner for context in matching. Defaults to None.
 
     Returns:
         list: A list of dictionaries with 'description' and 'itemCode' keys.
@@ -347,14 +366,51 @@ async def associate_forto_item_code(line_item_data, params):
 
     # Batch API Call for Embedding lookups
     if pending_line_items:
-        api_results = await get_tms_mappings(
-            input_list=list(pending_line_items.values()),
-            embedding_type="line_items",
-        )
+        code_map = await fetch_line_item_codes(pending_line_items, partner_name, params)
 
-        # Merge API results back into original list
         for desc, f_desc in pending_line_items.items():
-            code = api_results.get(f_desc)
-            result.append({"description": desc, "itemCode": code})
+            result.append(
+                {
+                    "description": desc,
+                    "itemCode": code_map.get(f_desc),
+                }
+            )
+
+    return result
 
+
+async def fetch_line_item_codes(
+    pending_line_items: dict,
+    partner_name: str | None,
+    params: dict,
+):
+    """Returns: {original_description: mapped_code_or_None}"""
+    t_mode = (
+        find_matching_lineitem(
+            partner_name.upper(),
+            params["lookup_data"]["intermodal_partners"],
+            threshold=87,
+        )
+        if partner_name
+        else None
+    )
+
+    unique_descs = list(set(pending_line_items.values()))
+    logger.info(f"Mapping {len(unique_descs)} line items from Embedding API...")
+
+    # Build API input map
+    api_input_map = {
+        desc: f"{t_mode} - {desc}" if t_mode else desc for desc in unique_descs
+    }
+
+    api_results = await get_tms_mappings(
+        input_list=list(api_input_map.values()),
+        embedding_type="line_items",
+    )
+
+    # Normalize response back to original descriptions
+    result = {
+        original_desc: api_results.get(api_desc)
+        for original_desc, api_desc in api_input_map.items()
+    }
     return result

data_science_document_ai-1.60.1/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. Shipment Id 'S' followed by 6, 7, or 8 digits e.g. S9486358 is not a contract number."
+    },
+    "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., FULL RETURN TO or Export terminal name."
+    },
+    "proformaDate": {
+      "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 CARGO CUT OFF DATE/TIME"
+    },
+    "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 'Booking Number'."
+    },
+    "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 DOC CUT OFF DATE/TIME"
+    },
+    "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 AT 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/VOYAGE e.g., MOL EMERALD"
+          },
+          "voyage": {
+            "type": "STRING",
+            "nullable": true,
+            "description": "The journey or route taken by the vessel for a specific leg. It can be found at VESSEL/VOYAGE e.g., 087E"
+          }
+        }
+      },
+      "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. Extract full name. e,g, Evergreen Line."
+    }
+  },
+  "required": ["bookingNumber", "transportLegs", "containers", "cyCutOff", "vgmCutOff", "siCutOff"]
+}

data_science_document_ai-1.60.1/src/prompts/library/bookingConfirmation/evergreen/prompt.txt

@@ -0,0 +1,62 @@
+<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.
+
+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. Then the POL of the First TransportLeg may start from the gateInTerminal or a different POL too.
+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.
+
+- 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.It is identified as Empty Pick Up AT Depot or Export Empty Pick Up Depot(s).
+    - dropOffDepotCode: The code of the depot where the empty container is dropped off. It is identified as Import Empty Drop Off Depot(s). Full Return To is not the drop off depot.
+
+
+- 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. ETD DATE above the PORT OF DISCHARGING information.
+    - 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. Can be found at VESSEL/VOYAGE (e.g., EVER LAUREL).
+    - voyage: The journey or route taken by the vessel for a specific leg. It can be found at VESSEL/VOYAGE e.g., 087E.
+
+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.
+    - "T/S PORT OF LOADING" indicates the presence of a multi-leg journey.
+    - Transhipment Handling: Treat any mentioned "T/S PORT OF LOADING" as the bridge between two legs (Discharge for Leg A and Loading for Leg B).
+    - The Connectivity Rule: For any sequence of legs, the Port of Discharge of the previous leg must match the Port of Loading of the following leg.
+        - First T/S PORT OF LOADING is the Port of Discharge for the first transportLegs and Port of Loading for the second transportLegs.
+        - Second T/S PORT OF LOADING is the Port of Discharge for the second transportLegs and Port of Loading for the third transportLegs.
+    - 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.
+
+Structure of Multiple Leg Sequence & Mapping
+ Leg 1 (Initial):
+ - `portOfLoading`: PORT OF LOADING.
+ - `portOfDischarge`: T/S PORT OF LOADING.
+ - `vesselName`: VESSEL/VOYAGE (ignore parentheses).
+ - `etd`: ETD DATE above the PORT OF DISCHARGING information.
+ - `eta`: ETA DATE below first T/S PORT OF LOADING
+
+ Leg 2 (Intermediate):  Trigger: Only if T/S PORT OF LOADING exists.
+ - `portOfLoading`: First T/S PORT OF LOADING. POD of Leg 1.
+ - `portOfDischarge`: Second T/S PORT OF LOADING (if exists), otherwise PORT OF DISCHARGE before the FINAL DESTINATION.
+ - `vesselName`: EST. CONNECTING VESSEL / VOY.
+ - `etd`: ETD DATE after first T/S PORT OF LOADING
+ - `eta`: ETA DATE after second T/S PORT OF LOADING (if exists), otherwise ETA next to the FINAL DESTINATION section.
+
+<INSTRUCTIONS>