data-science-document-ai 1.56.1__py3-none-any.whl → 1.58.0__py3-none-any.whl

{data_science_document_ai-1.56.1.dist-info → data_science_document_ai-1.58.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-science-document-ai
-Version: 1.56.1
+Version: 1.58.0
 Summary: "Document AI repo for data science"
 Author: Naomi Nguyen
 Author-email: naomi.nguyen@forto.com

{data_science_document_ai-1.56.1.dist-info → data_science_document_ai-1.58.0.dist-info}/RECORD

@@ -1,32 +1,32 @@
-src/constants.py,sha256=H43Az9AtoBKfcq9yY4TQQJY8DfdILV5kXy8EMtRaWYA,3583
+src/constants.py,sha256=Mr5HcoMSFQlXY24shJ1EpNKtCBJP_Ai0LZj-0i3BVGk,2845
 src/constants_sandbox.py,sha256=Iu6HdjCoNSmOX0AwoL9qUQkhq_ZnIN5U9e-Q2UfNuGc,547
 src/docai.py,sha256=dHuR0ehVjUi1CnoNvdp_yxJtpU_HFXqAZ61ywdz7BEo,5655
-src/docai_processor_config.yaml,sha256=4yKKZPvFCA-3S56jDYSqMGKXGFND-768OiU2seRiAzE,604
+src/docai_processor_config.yaml,sha256=ZewXqbyiftzmVAaS08BoNp5trY6WXx3HMWDfPwmKfaI,256
 src/excel_processing.py,sha256=TRgAzSHvL1WKbUgjHtpXL701bPhiWGH7kk3S6e1UPaA,3074
 src/io.py,sha256=rYjXVLlriEacw1uNuPIYhg12bXNu48Qs9GYMY2YcVTE,5563
 src/llm.py,sha256=a7UYA4ITUNjzct_2fHgM-bma_XWc28VC0FV71g9tnUI,7137
 src/log_setup.py,sha256=RhHnpXqcl-ii4EJzRt47CF2R-Q3YPF68tepg_Kg7tkw,2895
-src/pdf_processing.py,sha256=81fS2xL36n9QgB7DpXe7SCS-Lyz11cFDgccYMK3ZVkk,20026
-src/postprocessing/common.py,sha256=dagAg0hZGuZc03bXdfOolxekewMEVUfz917IGCiAtWI,26118
+src/pdf_processing.py,sha256=Fx-Glb9niEUU3WUCrBZ02ZYV-E2vWoUM0ifN7-0A1Q4,19961
+src/postprocessing/common.py,sha256=tyy97UBfcnSs8Oh5vVDp4D1qDRit32ri9IGqRlNZcaY,27254
 src/postprocessing/postprocess_booking_confirmation.py,sha256=nK32eDiBNbauyQz0oCa9eraysku8aqzrcoRFoWVumDU,4827
 src/postprocessing/postprocess_commercial_invoice.py,sha256=3I8ijluTZcOs_sMnFZxfkAPle0UFQ239EMuvZfDZVPg,1028
 src/postprocessing/postprocess_partner_invoice.py,sha256=WuaTQK5D09dV_QNrh29ZoKX9IvQn2Ub-WnAMyRjCsvI,14240
 src/prompts/library/arrivalNotice/other/placeholders.json,sha256=1vzly1amgyKt3jr2JJQbb24kNZsnI289iduvoUo5dJU,3061
 src/prompts/library/arrivalNotice/other/prompt.txt,sha256=QNuU-BvMA8VbdupVNapad4O3WmCotH5cKNxImRMbKDk,2906
-src/prompts/library/bookingConfirmation/evergreen/placeholders.json,sha256=IpM9nmSPdyroliZfXB1-NDCjiHZX_Ff5BH7-scNhGqE,1406
-src/prompts/library/bookingConfirmation/evergreen/prompt.txt,sha256=5ivskCG831M2scW3oqQaoltXIyHV-n6DYUygWycXxjw,2755
-src/prompts/library/bookingConfirmation/hapag-lloyd/placeholders.json,sha256=hMPNt9s3LuxR85AxYy7bPcCDleug6gSwVjefm3ismWY,1405
-src/prompts/library/bookingConfirmation/hapag-lloyd/prompt.txt,sha256=XgfhrFTXLJ467L4Cer77K0KTPtWTg_-QJXCsltvLlpI,3430
-src/prompts/library/bookingConfirmation/maersk/placeholders.json,sha256=6p_IQMA1PUgGZqjf_by4ja9jK27ba4loYhEpIa7Oxx4,1406
-src/prompts/library/bookingConfirmation/maersk/prompt.txt,sha256=t-yh1dOrcRa0fm0VPFC1xCRBf0R0Zjp9j_Hb31aZS1w,3223
-src/prompts/library/bookingConfirmation/msc/placeholders.json,sha256=IpM9nmSPdyroliZfXB1-NDCjiHZX_Ff5BH7-scNhGqE,1406
-src/prompts/library/bookingConfirmation/msc/prompt.txt,sha256=_Jfioislp7SNs2BEXoklvnTPVXe6Z0M6myD1IWnBFYQ,4705
-src/prompts/library/bookingConfirmation/oocl/placeholders.json,sha256=JTtWvLSsoxN7huXY8ZNqqPkODM-DOs5wu3YvNHOna3k,1404
-src/prompts/library/bookingConfirmation/oocl/prompt.txt,sha256=xNTrJdUtDalcP3AKkfRiOnHjAdRCbcTvehcBQKurRj0,2201
-src/prompts/library/bookingConfirmation/other/placeholders.json,sha256=IpM9nmSPdyroliZfXB1-NDCjiHZX_Ff5BH7-scNhGqE,1406
-src/prompts/library/bookingConfirmation/other/prompt.txt,sha256=kUK7NgVNDYFMnqOcIblCwWSw2SC0YQEtHsYrspiVUMo,3379
-src/prompts/library/bookingConfirmation/yangming/placeholders.json,sha256=IpM9nmSPdyroliZfXB1-NDCjiHZX_Ff5BH7-scNhGqE,1406
-src/prompts/library/bookingConfirmation/yangming/prompt.txt,sha256=fYKfusDajDFw0v54-nv2iAqUSp2yCeOzc6G7AFe-h2w,3226
+src/prompts/library/bookingConfirmation/evergreen/placeholders.json,sha256=5efq6b--KGWeqGbvASZFTqXJgUEAvsC-0ljo-q0Lhew,5855
+src/prompts/library/bookingConfirmation/evergreen/prompt.txt,sha256=OxNfXZaWppwsFMprthzJpOOr8ApQL4KYEmlu9fSUvxk,3485
+src/prompts/library/bookingConfirmation/hapag-lloyd/placeholders.json,sha256=en83Em25e5PF2OAgFJC8w-MONVnketPZ3J_3zCjIVfE,5915
+src/prompts/library/bookingConfirmation/hapag-lloyd/prompt.txt,sha256=bLHQgGR9e8X4UvFpiyd1OasD00XGvUMG6HSLQy4IgQ4,5157
+src/prompts/library/bookingConfirmation/maersk/placeholders.json,sha256=5efq6b--KGWeqGbvASZFTqXJgUEAvsC-0ljo-q0Lhew,5855
+src/prompts/library/bookingConfirmation/maersk/prompt.txt,sha256=S-C5cq8AkEoGKilCO0XiXLZXgZPwz9udQOTm557GG64,3984
+src/prompts/library/bookingConfirmation/msc/placeholders.json,sha256=5efq6b--KGWeqGbvASZFTqXJgUEAvsC-0ljo-q0Lhew,5855
+src/prompts/library/bookingConfirmation/msc/prompt.txt,sha256=bojE6BytnEoQfdXrQebaXYTToDF1Fbyn4YdIGMke2Jo,5463
+src/prompts/library/bookingConfirmation/oocl/placeholders.json,sha256=LqjzD-8LkX9hAq3eOBMwit6tLrSLmVMUXTIyhBEaYxk,6037
+src/prompts/library/bookingConfirmation/oocl/prompt.txt,sha256=pCsj2BNnP-_kwgUEDt8IehO-tyMv6qeD5nyIzXJL3c0,2925
+src/prompts/library/bookingConfirmation/other/placeholders.json,sha256=LqjzD-8LkX9hAq3eOBMwit6tLrSLmVMUXTIyhBEaYxk,6037
+src/prompts/library/bookingConfirmation/other/prompt.txt,sha256=-629upv9-ciO6eG3A0_2TTjy7iLlInMsmQfSwAukjLg,4919
+src/prompts/library/bookingConfirmation/yangming/placeholders.json,sha256=LqjzD-8LkX9hAq3eOBMwit6tLrSLmVMUXTIyhBEaYxk,6037
+src/prompts/library/bookingConfirmation/yangming/prompt.txt,sha256=gySDhfRdQHy3IIomOR3qwY49wlO63Xw73GUSPrEkkr4,3990
 src/prompts/library/bundeskasse/other/placeholders.json,sha256=7xKzi_ypkIICO9nrEl45W9G7-h33uWVRVWnpg2b5lUg,4288
 src/prompts/library/bundeskasse/other/prompt.txt,sha256=miNYoqRZEd6Z1LNisTahX1-tenzr5kEpRA6gvPH7NCw,3316
 src/prompts/library/commercialInvoice/other/placeholders.json,sha256=zUK2mg9MnHiEQRYF6VgTiUiq68WGy5f7_4qL63CWyR0,4700
@@ -52,9 +52,9 @@ src/prompts/library/preprocessing/carrier/prompt.txt,sha256=NLvRZQCZ6aWC1yTr7Q93
 src/prompts/library/shippingInstruction/other/placeholders.json,sha256=eK4AeMfORkGMWVYcqH7NjB56Zb4swHTvcQD5UQbTryg,6374
 src/prompts/library/shippingInstruction/other/prompt.txt,sha256=CbrqlKMtB-sVY-8E460KP1KNmz169YVPMrH3-uEldPg,2135
 src/prompts/prompt_library.py,sha256=VJWHeXN-s501C2GiidIIvQQuZdU6T1R27hE2dKBiI40,2555
-src/setup.py,sha256=yb0Pz1RI-uId5lEjgQrj1Pqo9FvwG9vs0HXRVbyST2M,7186
+src/setup.py,sha256=8-vZWjC8Iwa3xxdk3iR4412VCjtNtgzVqkXcFon7UBE,7309
 src/tms.py,sha256=UXbIo1QE--hIX6NZi5Qyp2R_CP338syrY9pCTPrfgnE,1741
-src/utils.py,sha256=Ow5_Jals88o8mbZ1BoHfZpHZoCfig_UQb5aalH-mpWE,17278
-data_science_document_ai-1.56.1.dist-info/METADATA,sha256=4rIhyVd5XG02M7f9l2UYjH6r-pjzpNiobuZ-v-trvtE,2152
-data_science_document_ai-1.56.1.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-data_science_document_ai-1.56.1.dist-info/RECORD,,
+src/utils.py,sha256=8BpuJJLiJZntZAI86cQMNa-FGjl9jbOjlCWIG27mjJo,17418
+data_science_document_ai-1.58.0.dist-info/METADATA,sha256=8MWt4KlixrpV8lQhKmFo5i1UZn02o16vMaR3uEe94Js,2152
+data_science_document_ai-1.58.0.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+data_science_document_ai-1.58.0.dist-info/RECORD,,

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"},
 }

src/docai_processor_config.yaml

@@ -7,16 +7,3 @@ model_config:
           display_name: "doc_cap_bookingConfirmation"
           author: "reet.kanjilal@forto.com"
           created_date: ""
-      - id: "3c280b11bdb3ed89"
-        details:
-          display_name: "doc_cap_BC_mlg"
-          author: "igor.tonko@forto.com"
-          created_date: ""
-
-  beta:
-    bookingConfirmation:
-      - id: "3c280b11bdb3ed89"
-        details:
-          display_name: "doc_cap_BC_mlg"
-          author: "igor.tonko@forto.com"
-          created_date: ""

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,
         )

src/postprocessing/common.py

@@ -723,10 +723,45 @@ async def format_all_entities(result, document_type_code, params, mime_type):
     if document_type_code in ["partnerInvoice", "bundeskasse"]:
         await process_partner_invoice(params, aggregated_data, document_type_code)
 
+    if document_type_code in ["bookingConfirmation"]:
+        aggregated_data["legalEntity"] = await get_legal_entity(
+            aggregated_data.get("carrierName", {}).get("documentValue", None),
+            aggregated_data.get("carrierAddress", {}).get("documentValue", None),
+        )
+
     logger.info("Data Extraction completed successfully")
     return aggregated_data
 
 
+async def get_legal_entity(name, address):
+    """Get legal entity mapping from TMS mappings.
+
+    Args:
+        name (str): The name of the legal entity. Mandatory.
+        address (str): The address of the legal entity. Optional for better matching.
+
+    Returns:
+        dict or None: The mapping result from TMS embeddings, or None if not found.
+    """
+    # Name is mandatory for legal entity mapping
+    if not name:
+        return {"documentValue": None, "mappedValue": None}
+
+    # Build input safely
+    input_text = name if not address else f"{name} | {address}"
+
+    api_results = await get_tms_mappings(
+        input_list=[input_text],
+        embedding_type="legal_entities",
+        input_key="partnerNameAddress",
+    )
+
+    return {
+        "documentValue": None,
+        "formattedValue": api_results.get(input_text),
+    }
+
+
 def add_text_without_space(text):
     """If the cleaned text is different from the original text, append it.
     Useful for port names like QUINHON - Quinhon"""

src/prompts/library/bookingConfirmation/evergreen/placeholders.json

@@ -1,32 +1,146 @@
 {
   "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},
+    "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},
-            "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": []
-      }
+          "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": []
+  "required": ["bookingNumber", "transportLegs", "containers", "cyCutOff", "vgmCutOff", "siCutOff"]
 }

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:'. "
-}
-]
-}
-```