data-science-document-ai 1.57.0__py3-none-any.whl → 1.58.0__py3-none-any.whl

{data_science_document_ai-1.57.0.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: 1.57.0
+Version: 1.58.0
 Summary: "Document AI repo for data science"
 Author: Naomi Nguyen
 Author-email: naomi.nguyen@forto.com

{data_science_document_ai-1.57.0.dist-info → data_science_document_ai-1.58.0.dist-info}/RECORD

@@ -7,7 +7,7 @@ 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=Fx-Glb9niEUU3WUCrBZ02ZYV-E2vWoUM0ifN7-0A1Q4,19961
-src/postprocessing/common.py,sha256=dagAg0hZGuZc03bXdfOolxekewMEVUfz917IGCiAtWI,26118
+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
@@ -15,8 +15,8 @@ src/prompts/library/arrivalNotice/other/placeholders.json,sha256=1vzly1amgyKt3jr
 src/prompts/library/arrivalNotice/other/prompt.txt,sha256=QNuU-BvMA8VbdupVNapad4O3WmCotH5cKNxImRMbKDk,2906
 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=5efq6b--KGWeqGbvASZFTqXJgUEAvsC-0ljo-q0Lhew,5855
-src/prompts/library/bookingConfirmation/hapag-lloyd/prompt.txt,sha256=I9x52U9Kt3vwiQK96KnaAhD48rEjL47jS0JDm3QT27k,5025
+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
@@ -54,7 +54,7 @@ src/prompts/library/shippingInstruction/other/prompt.txt,sha256=CbrqlKMtB-sVY-8E
 src/prompts/prompt_library.py,sha256=VJWHeXN-s501C2GiidIIvQQuZdU6T1R27hE2dKBiI40,2555
 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-1.57.0.dist-info/METADATA,sha256=CnYlyCERc0j4WniG4qrEYOKLhcTtEXWZw6nQ5XJEQeE,2152
-data_science_document_ai-1.57.0.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-data_science_document_ai-1.57.0.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/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/hapag-lloyd/placeholders.json

@@ -134,7 +134,7 @@
     "carrierAddress": {
       "type": "STRING",
       "nullable": true,
-      "description": "The address of the carrier who provides service and issued the document."
+      "description": "The address of the carrier who provides service and issued the document. It can be from Germany, Poland, Italy, Vietnam, China, etc."
     },
     "carrierName": {
       "type": "STRING",

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

@@ -29,8 +29,10 @@ For Import Shipment: The loaded container / cargo arrives at a port of discharge
 
 - carrierName and carrierAddress:
     - Extract the name and address of the carrier who is the main parent company in the document.
+    - It can be found in the top section of the document, often near the logo or header.
     - Example:
-        - "Hapag-Lloyd AG" or "Hapag-Lloyd Aktiengesellschaft" for vendorName.
+        - "Hapag-Lloyd" for vendorName
+        - Hamburg, Germany, Poland, Italy, Vietnam, China etc... for vendorAddress
 
 - 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.

src/utils.py

@@ -361,7 +361,10 @@ def extract_top_pages(pdf_bytes, num_pages=4):
 
 
 async def get_tms_mappings(
-    input_list: List[str], embedding_type: str, llm_ports: Optional[List[str]] = None
+    input_list: List[str],
+    embedding_type: str,
+    llm_ports: Optional[List[str]] = None,
+    input_key: str = None,
 ) -> Dict[str, Any]:
     """Get TMS mappings for the given values.
 
@@ -370,6 +373,7 @@ async def get_tms_mappings(
         embedding_type (str): Type of embedding to use
          (e.g., "container_types", "ports", "depots", "lineitems", "terminals").
         llm_ports (list[str], optional): List of LLM ports to use. Defaults to None.
+        input_key (str, optional): Key to use for input list in payload. Defaults to None.
 
     Returns:
         dict or string: A dictionary or a string with the mapping results.
@@ -389,7 +393,7 @@ async def get_tms_mappings(
         input_list = [input_list]
 
     # Always send a dict with named keys
-    payload = {embedding_type: input_list}
+    payload = {input_key or embedding_type: input_list}
 
     if llm_ports:
         payload["llm_ports"] = llm_ports if isinstance(llm_ports, list) else [llm_ports]