data-science-document-ai 1.45.2__py3-none-any.whl → 1.46.0__py3-none-any.whl

{data_science_document_ai-1.45.2.dist-info → data_science_document_ai-1.46.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-science-document-ai
-Version: 1.45.2
+Version: 1.46.0
 Summary: "Document AI repo for data science"
 Author: Naomi Nguyen
 Author-email: naomi.nguyen@forto.com

{data_science_document_ai-1.45.2.dist-info → data_science_document_ai-1.46.0.dist-info}/RECORD

@@ -1,16 +1,18 @@
-src/constants.py,sha256=09Ar-Wzvm7EBQiAQ1S1-MAenFO0DppKk-nyIDWFTQGE,3656
+src/constants.py,sha256=MRwWoJT3npMfleFvsDAjrQRVByq_kcMnLziSQ6o4TDM,3665
 src/constants_sandbox.py,sha256=Iu6HdjCoNSmOX0AwoL9qUQkhq_ZnIN5U9e-Q2UfNuGc,547
 src/docai.py,sha256=dHuR0ehVjUi1CnoNvdp_yxJtpU_HFXqAZ61ywdz7BEo,5655
-src/docai_processor_config.yaml,sha256=81NUGs-u8UFJm6mc0ZOeeNQlhe9h0f35GhjTcwErvTA,1717
+src/docai_processor_config.yaml,sha256=24OanIBj8X3U9I1vd8ZB6dWcHZXo9O7DJJ-vXICWeb0,1530
 src/excel_processing.py,sha256=_vP2q1xEIeyjO8TvZlSTeEM-M1PMceyDSuYGfyZeceY,3361
 src/io.py,sha256=rYjXVLlriEacw1uNuPIYhg12bXNu48Qs9GYMY2YcVTE,5563
 src/llm.py,sha256=OE4IEIqcM-hYK9U7e0x1rAfcqdpeo4iXPHBp64L5Qz0,8199
 src/log_setup.py,sha256=RhHnpXqcl-ii4EJzRt47CF2R-Q3YPF68tepg_Kg7tkw,2895
-src/pdf_processing.py,sha256=lzvoza9itpEyl-rcBQbIcWuFxUAvF_Qyc-OpuPQWWMk,20354
+src/pdf_processing.py,sha256=3avM4UTTR04qNeL9vJdq7bYC2U-N9iiJL1d0b5TCcls,20383
 src/postprocessing/common.py,sha256=dagAg0hZGuZc03bXdfOolxekewMEVUfz917IGCiAtWI,26118
 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=m-un3OFzxV-6sf8xa5PBvBhe-HJAUNtXJ5LCd49kD84,12434
+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
@@ -54,6 +56,6 @@ src/prompts/prompt_library.py,sha256=VJWHeXN-s501C2GiidIIvQQuZdU6T1R27hE2dKBiI40
 src/setup.py,sha256=M-p5c8M9ejKcSZ9N86VtmtPc4TYLxe1_4_dxf6jpfVc,7262
 src/tms.py,sha256=UXbIo1QE--hIX6NZi5Qyp2R_CP338syrY9pCTPrfgnE,1741
 src/utils.py,sha256=Ow5_Jals88o8mbZ1BoHfZpHZoCfig_UQb5aalH-mpWE,17278
-data_science_document_ai-1.45.2.dist-info/METADATA,sha256=AyOAwrTOEHWaLoPk2_9RJLjUXUlumOvwCPt92QZbMw4,2152
-data_science_document_ai-1.45.2.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-data_science_document_ai-1.45.2.dist-info/RECORD,,
+data_science_document_ai-1.46.0.dist-info/METADATA,sha256=O2VzKiSg4D-Y9cTUwk8N2zxPkReEbtxtyMAf3H3yZe0,2152
+data_science_document_ai-1.46.0.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+data_science_document_ai-1.46.0.dist-info/RECORD,,

src/constants.py

@@ -55,7 +55,6 @@ project_parameters = {
             "bookingConfirmation": 1,
             "finalMbL": 0,
             "draftMbl": 0,
-            "arrivalNotice": 0,
             "shippingInstruction": 0,
             "customsAssessment": 0,
             "deliveryOrder": 0,
@@ -87,6 +86,7 @@ project_parameters = {
     # Key to combine the LLM results with the Doc Ai results
     "key_to_combine": {
         "bookingConfirmation": ["transportLegs"],
+        "arrivalNotice": ["containers"],
         "finalMbL": ["containers"],
         "draftMbl": ["containers"],
         "customsAssessment": ["containers"],

src/docai_processor_config.yaml

@@ -34,13 +34,6 @@ model_config:
           author: "kumar.rajendrababu@forto.com"
           created_date: ""
 
-    arrivalNotice:
-      - id: "748b2e2b9161dcf3"
-        details:
-          display_name: "doc_cap_arrivalNotice"
-          author: "osman.demirel@forto.com"
-          created_date: ""
-
     customsAssessment:
       - id: "c464a18d82fad9be"
         details:

src/pdf_processing.py

@@ -213,6 +213,7 @@ async def process_file_w_llm(params, file_content, input_doc_type, llm_client):
             "commercialInvoice",
             "packingList",
             "bookingConfirmation",
+            "arrivalNotice",
         ]
         else generate_schema_structure(params, input_doc_type)
     )

src/prompts/library/arrivalNotice/other/placeholders.json

@@ -0,0 +1,70 @@
+{
+  "type": "OBJECT",
+  "properties": {
+      "bookingNumber": {
+        "type": "STRING",
+        "nullable": true,
+        "description": "The booking number associated with the Arrival Notice document. They are often referred to as 'Booking Number', 'Booking No.', 'Booking Ref.', 'Booking Reference', 'Booking ID', 'carrier's reference' or 'Order Ref'."
+      },
+      "destinationTerminal": {
+        "type": "STRING",
+        "nullable": true,
+        "description": "The terminal at the destination port where the container will be delivered."
+      },
+      "eta": {
+        "type": "STRING",
+        "nullable": true,
+        "description": "Estimated Time of Arrival (ETA) is the expected date when the shipment will arrive at its destination."
+      },
+      "mblNumber": {
+        "type": "STRING",
+        "nullable": true,
+        "description": "Bill of Lading number (B/L NO.), a document issued by the carrier."
+      },
+      "portOfDischarge": {
+        "type": "STRING",
+        "nullable": true,
+        "description": "The port where the goods are discharged from the vessel. This is the destination port for the shipment."
+      },
+      "vesselName": {
+        "type": "STRING",
+        "nullable": true,
+        "description": "The name of the vessel carrying the shipment."
+      },
+      "containers": {
+          "type": "ARRAY",
+          "items": {
+              "type": "OBJECT",
+              "properties": {
+                  "containerNumber": {
+                    "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."
+                  },
+                  "containerType": {
+                    "type": "STRING",
+                    "nullable": true,
+                    "description": "The size of the container associated with the containerNumber, such as 20ft, 40ft, 40HC, 20DC etc."
+                  },
+                  "grossWeight": {
+                    "type": "STRING",
+                    "nullable": true,
+                    "description": "The gross weight of the container. Usually mentioned as G.W or GW or Gross Weight, etc.."
+                  },
+                  "measurements": {
+                    "type": "STRING",
+                    "nullable": true,
+                    "description": "The volume of the container. Usually, it is measured in 'Cubic Meter (cbm)' or dimensions. But volume in 'cbm' is preferred."
+                  },
+                  "sealNumber": {
+                    "type": "STRING",
+                    "nullable": true,
+                    "description": "The seal number associated with the container Number. But it is not same as the container number."
+                  }
+              },
+              "required": ["containerNumber", "containerType", "grossWeight"]
+          }
+      }
+},
+  "required": ["bookingNumber", "destinationTerminal", "eta", "portOfDischarge", "vesselName", "containers"]
+}

src/prompts/library/arrivalNotice/other/prompt.txt

@@ -0,0 +1,40 @@
+<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 Arrival Notice documents as per the given response schema structure. <TASK>
+
+<CONTEXT>
+The Freight Forwarding company receives Arrival Notice from shipping lines.
+These documents contain various details related to arrival of a shipment to the port of destination such as container numbers, estimated time of arrival, vessel details and containers information.
+They may be written in different languages such as English, German, Italian and can appear in a variety of formats and layouts.
+Your role is to accurately extract specific entities from these Arrival Notices to support efficient processing and accurate record-keeping.
+<CONTEXT>
+
+<INSTRUCTIONS>
+- Populate fields as defined in the response schema.
+- Multiple Containers entries may exist, capture all instances under "containers".
+- Use the data field description to understand the context of the data.
+
+- bookingNumbers:
+    - Booking numbers are unique identifiers for shipments. They are often referred to as "Booking Number", "Booking No.", "Booking Ref.", "Booking Reference", "Booking ID", "SACO-Pos.", "Order Ref", "Unsere Referenz", or "Unsere Position"
+    - If there is a unique_id that starts with "S" followed by 6 or 8 digits, it is a shipmentID, not a bookingNumber.
+
+- destinationTerminal:
+    - Destination Terminal can also be referred to as "Destination Termina;", "Pickup Location", "Delivery Location", "Delivery Terminal", "Empfangsort", "Entladeort", or "Abladestelle".
+
+- mblNumbers:
+    - Commonly known as "Bill of Lading Number", "BILL OF LADING NO.", "BL Number", "BL No.", "B/L No.", "BL-Nr.", "B/L", "HBL No.", or "M-AWB Nummer".
+    - Bill of Lading Number is known as mblNumber. Not a shipmentID even if it starts with "S".
+    - mblNumber from Hapag-Lloyd always starts with HLC.... (e.g., "HLCUTS12303AWNT3) and named as SEA WAYBILL or "SWB-NR.
+
+- eta:
+    - Estimated Time of Arrival (ETA) is the expected date and time when the shipment will arrive at the destination port.
+    - It can be referred to as "ETA", "Estimated Arrival", "Voraussichtliche Ankunft", "Ankunftszeit", "Arrivo", "Due to arrive at Terminal"
+
+- vesselName:
+    - Vessel Name is the name of the ship carrying the cargo. It can be referred to as "Vessel", "Ship Name", "Schiff", "Schiffsname", "Nave", or "Vessel/Flight No.".
+
+- containers: Details of each container on the arrival notice. Make sure to extract each container information separately.
+    - containerNumber: Container Number consists of 4 capital letters followed by 7 digits (e.g., TEMU7972458, CAIU 7222892).
+    - sealNumber: Seal numbers are unique identifiers for shipping seals. They are usually mentioned as seal numbers in the document but they are definitely not container numbers.
+
+<INSTRUCTIONS>