data-science-document-ai 1.48.0__tar.gz → 1.49.0__tar.gz

{data_science_document_ai-1.48.0 → data_science_document_ai-1.49.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-science-document-ai
-Version: 1.48.0
+Version: 1.49.0
 Summary: "Document AI repo for data science"
 Author: Naomi Nguyen
 Author-email: naomi.nguyen@forto.com

{data_science_document_ai-1.48.0 → data_science_document_ai-1.49.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "data-science-document-ai"
-version = "1.48.0"
+version = "1.49.0"
 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-1.48.0 → data_science_document_ai-1.49.0}/src/postprocessing/postprocess_partner_invoice.py

@@ -103,9 +103,18 @@ def post_process_bundeskasse(aggregated_data):
             )
 
         # Check if the deferredDutyPayer is forto
-        deferredDutyPayer = line_item.get("deferredDutyPayer", {})
-        lower = deferredDutyPayer.get("documentValue", "").lower()
-        if any(key in lower for key in ["de789147263644738", "forto"]):
+        KEYWORDS = {"de789147263644738", "forto", "009812"}
+
+        def is_forto_recipient(line_item: dict) -> bool:
+            values_to_check = [
+                line_item.get("deferredDutyPayer", {}).get("documentValue", ""),
+                line_item.get("vatId", {}).get("documentValue", ""),
+            ]
+
+            combined = " ".join(values_to_check).lower()
+            return any(keyword in combined for keyword in KEYWORDS)
+
+        if is_forto_recipient(line_item):
             is_recipient_forto = True
 
     update_recipient_and_vendor(aggregated_data, is_recipient_forto)

{data_science_document_ai-1.48.0 → data_science_document_ai-1.49.0}/src/setup.py

@@ -1,11 +1,8 @@
 """Contains project setup parameters and initialization functions."""
 import json
-
-# import streamlit as st
 import os
 import random
 import time
-from pathlib import Path
 
 import toml
 import vertexai
@@ -18,7 +15,7 @@ from src.constants import project_parameters
 from src.constants_sandbox import project_parameters_sandbox
 
 # Parent repos are imported without .
-from src.io import download_dir_from_bucket, get_bq_client, get_storage_client, logger
+from src.io import get_bq_client, get_storage_client, logger
 from src.llm import LlmClient
 
 
@@ -133,15 +130,7 @@ def setup_params(args=None):
         assert params.keys() & yaml_content.keys() == set()
         params.update(yaml_content)
 
-    # Get models meta data from cloud
-    client = get_storage_client(params)
-    bucket = client.bucket(params["doc_ai_bucket_name"])
-    downloaded_meta = download_dir_from_bucket(
-        bucket, params["g_model_data_folder"], Path(params["local_model_data_folder"])
-    )
-    if not downloaded_meta:
-        logger.info(f"Could not load models metadata from cloud.")
-
+    # Set up LLM clients
     params["LlmClient"] = LlmClient(
         openai_key=os.getenv("OPENAI_KEY"), parameters=params["gemini_params"]
     )
@@ -149,7 +138,8 @@ def setup_params(args=None):
         openai_key=os.getenv("OPENAI_KEY"), parameters=params["gemini_flash_params"]
     )
 
-    params["lookup_data"] = setup_lookup_data(params, bucket)
+    # Load lookup data from GCS bucket
+    setup_lookup_data(params)
 
     return params
 
@@ -182,10 +172,13 @@ def setup_vertexai(params):
     )
 
 
-def setup_lookup_data(params, bucket):
+def setup_lookup_data(params):
     """
     Loads JSON mapping data from given GCP Bucket.
     """
+    client = get_storage_client(params)
+    bucket = client.bucket(params["doc_ai_bucket_name"])
+
     data = dict()
 
     input_path_item_code = (
@@ -208,4 +201,4 @@ def setup_lookup_data(params, bucket):
         input_path_reverse_charge
     )
 
-    return data
+    params["lookup_data"] = data