iatoolkit 0.4.1__py3-none-any.whl → 0.4.2__py3-none-any.whl

{iatoolkit-0.4.1.dist-info → iatoolkit-0.4.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: iatoolkit
-Version: 0.4.1
+Version: 0.4.2
 Summary: IAToolkit
 Author: Fernando Libedinsky
 License-Expression: MIT

{iatoolkit-0.4.1.dist-info → iatoolkit-0.4.2.dist-info}/RECORD

@@ -10,13 +10,13 @@ iatoolkit/system_prompts/sql_rules.prompt,sha256=y4nURVnb9AyFwt-lrbMNBHHtZlhk6kC
 services/__init__.py,sha256=fSvSfIcPW1dHwTBY1hQ5dBEhaoorzk_GzR4G46gD8tY,173
 services/api_service.py,sha256=InIKTc64BWcp4U4tYKHz28x4ErPxIfvR9x3ZlxJZlXs,2911
 services/benchmark_service.py,sha256=0Vgsx_FaUZL7igoBYbe1AZkIWOiEUx1FSCV_0Ut0mtk,5921
-services/dispatcher_service.py,sha256=AOLsv9haFOxW5hV-6LOP8tryDdlfvjEGhNNGjgphH2c,15489
-services/document_service.py,sha256=sm5QtbrKs2dF9hpLuSLMB-IMWYNBD7yWHv3rd80aD0o,5960
+services/dispatcher_service.py,sha256=j3Vm3vgDIgwMn9tF1BBHN3sY-V30XIkbHNcXVR0u-kY,15491
+services/document_service.py,sha256=np8wjaFpS8kVgAeVr8JWzGHcdRl1S4vsOX-dxyaLP8E,5961
 services/excel_service.py,sha256=wE9Udbyb96kGRSnZZ6KM2mbE484rKjTEhta9GKKpy-8,3630
 services/file_processor_service.py,sha256=0CM4CQu6KKfcLVGkxs4hYxgdz8kKRWfkV5rDH9UoccM,4173
 services/history_service.py,sha256=6fGSSWxy60nxtkwp_fodwDHoVKhpIUbHnzAzUSiNi-Y,1657
 services/jwt_service.py,sha256=dC45Sn6FyzdzRiQJnzgkjN3Hy21V1imRxB0hTyWRvlA,3979
-services/load_documents_service.py,sha256=AtB5VnSjOEILG3wcQm6YiXkRrVvL87JWeRPgon81hf4,11064
+services/load_documents_service.py,sha256=eDqi4Nr2K0BvHS4om07LL_wbFcyfJ4qIQiMULviZWsE,7098
 services/mail_service.py,sha256=ystFit1LuYUC4ekYYebyiy1rqYQmxeL6K8h58MxEkOY,2233
 services/profile_service.py,sha256=vZV0cregZQiPKYcNLaD7xjez2y6-3Mq97cDndC8NL8w,17922
 services/prompt_manager_service.py,sha256=bWG4SIgt0u45PVUfm0xRLbLfKC7bk6uozVHRdkdgCmc,7761
@@ -26,7 +26,7 @@ services/sql_service.py,sha256=H7CIPpXTcxLXLojD2fBFr_mIAD0PW1vEJhKHLfJi4Hk,1418
 services/tasks_service.py,sha256=hHJDlcsSOPtEleD6_Vv3pocfxWNmthIhmZSdnoWFpEM,6861
 services/user_feedback_service.py,sha256=YtCndRBekDEWYEbac431Ksn2gMO5iBrI3WqKK0xtShE,2513
 services/user_session_context_service.py,sha256=5qn7fqpuiU8KgMpU4M5-iRUsETumz1raBw-EeZLuE1A,3868
-iatoolkit-0.4.1.dist-info/METADATA,sha256=rzRfT16CeRWOOnJorFb5kNJ3W0U98yKb1FZiB_L6p8M,9300
-iatoolkit-0.4.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-iatoolkit-0.4.1.dist-info/top_level.txt,sha256=dqlBbmgo9okD9d_WMR9uYzdup7Rxgj26yFF85jRGeu4,19
-iatoolkit-0.4.1.dist-info/RECORD,,
+iatoolkit-0.4.2.dist-info/METADATA,sha256=F2KitiTXfL4FN4nIp7ebGr36828ZVRO5QFT5Bvxmfg8,9300
+iatoolkit-0.4.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+iatoolkit-0.4.2.dist-info/top_level.txt,sha256=dqlBbmgo9okD9d_WMR9uYzdup7Rxgj26yFF85jRGeu4,19
+iatoolkit-0.4.2.dist-info/RECORD,,

services/dispatcher_service.py

@@ -109,7 +109,7 @@ class Dispatcher:
                     prompt_name=prompt['name'],
                     description=prompt['description'],
                     order=1,
-                    is_system_prompt=True
+                    is_system_prompt=True,
                 )
                 i += 1
 
@@ -117,7 +117,7 @@ class Dispatcher:
         for company in self.company_instances.values():
             company.register_company()
 
-    def dispatch(self, company_name: str, action: str, **kwargs) -> str:
+    def dispatch(self, company_name: str, action: str, **kwargs) -> dict:
         company_key = company_name.lower()
 
         if company_key not in self.company_instances:

services/document_service.py

@@ -16,7 +16,7 @@ class DocumentService:
     @inject
     def __init__(self):
         # max number of pages to load
-        self.max_doc_pages = int(os.getenv("MAX_DOC_PAGES", "10"))
+        self.max_doc_pages = int(os.getenv("MAX_DOC_PAGES", "200"))
 
     def file_to_txt(self, filename, file_content):
         try:

services/load_documents_service.py

@@ -52,103 +52,16 @@ class LoadDocumentsService:
             separators=["\n\n", "\n", "."]
         )
 
-    # load the files for all of the companies.
-    def load(self, doc_type: str = None):
+    def load_company_files(self,
+                         company: Company,
+                         connector_config: Dict,
+                         predefined_metadata: Dict = None,
+                         filters: Dict = None):
         """
-                Loads documents for all companies based on their configuration.
-                It can load all document types or a specific one if provided.
-
-                Args:
-                    doc_type (str, optional): A specific document type to load.
-                                              If None, all configured types are loaded.
-
-                Returns:
-                    Dict: A dictionary with a summary message.
-                """
-        # doc_type: an optional document_type for loading
-        files_loaded = 0
-        companies = self.profile_repo.get_companies()
-
-        for company in companies:
-            load_config = company.parameters.get('load', {})
-            if not load_config:
-                continue
-
-            print(f"Cargando datos de ** {company.short_name} **")
-
-            # Si hay configuraciones de tipos de documento específicos
-            doc_types_config = load_config.get('document_types', {})
-
-            if doc_types_config and len(doc_types_config) > 0:
-                # Si se especificó un tipo de documento, cargar solo ese tipo
-                if doc_type and doc_type in doc_types_config:
-                    files_loaded += self._load_document_type(company, doc_type, doc_types_config[doc_type])
-                # Si no se especificó, cargar todos los tipos configurados
-                elif not doc_type:
-                    for type_name, type_config in doc_types_config.items():
-                        files_loaded += self._load_document_type(company, type_name, type_config)
-            else:
-                # Comportamiento anterior: usar la configuración general
-                connector = load_config.get('connector', {})
-                if not connector:
-                    raise IAToolkitException(IAToolkitException.ErrorType.MISSING_PARAMETER,
-                                       f"Falta configurar conector en empresa {company.short_name}")
-
-                files_loaded += self.load_data_source(company=company,
-                                                      connector_config=connector)
-
-        return {'message': f'{files_loaded} files processed'}
-
-    def load_company_files(self, company: Company,
-                           connector: dict,
-                           predefined_metadata: Dict = None,
-                           filters: Dict = None):
-        """
-        Loads all files for a specific company using a given connector.
+        Loads all the company files from a connector
 
         Args:
             company (Company): The company to load files for.
-            connector (dict): The connector configuration.
-
-        Returns:
-            Dict: A dictionary with a summary message.
-        """
-        if not connector:
-            raise IAToolkitException(IAToolkitException.ErrorType.MISSING_PARAMETER,
-                        f"Falta configurar conector")
-
-        files_loaded = self.load_data_source(
-                            company=company,
-                            connector_config=connector,
-                            predefined_metadata=predefined_metadata,
-                            filters=filters)
-
-        return {'message': f'{files_loaded} files processed'}
-
-    def _load_document_type(self, company: Company, doc_type_name: str, type_config: Dict) -> int:
-        # load specific document_types for a company
-        connector = type_config.get('connector')
-        if not connector:
-            logging.warning(f"Falta configurar conector para tipo {doc_type_name} en empresa {company.short_name}")
-            raise IAToolkitException(IAToolkitException.ErrorType.MISSING_PARAMETER,
-                               f"Falta configurar conector para tipo {doc_type_name} en empresa {company.short_name}")
-
-        # get the metadata for this connector
-        predefined_metadata = type_config.get('metadata', {})
-
-        # config specific filters
-        filters = type_config.get('filters', {"filename_contains": ".pdf"})
-
-        return self.load_data_source(company=company,
-                                     connector_config=connector,
-                                     predefined_metadata=predefined_metadata,
-                                     filters=filters)
-
-    def load_data_source(self, company: Company, connector_config: Dict, predefined_metadata: Dict = None, filters: Dict = None):
-        """
-        Loads files from a data source using a connector and a FileProcessor.
-
-        Args:
             connector_config (Dict): The configuration for the file connector.
             predefined_metadata (Dict, optional): Metadata to be added to all documents from this source.
             filters (Dict, optional): Filters to apply to the files.
@@ -156,6 +69,10 @@ class LoadDocumentsService:
         Returns:
             int: The number of processed files.
         """
+        if not connector_config:
+            raise IAToolkitException(IAToolkitException.ErrorType.MISSING_PARAMETER,
+                        f"Falta configurar conector")
+
         try:
             if not filters:
                 filters = {"filename_contains": ".pdf"}