iatoolkit 0.7.5__py3-none-any.whl → 0.7.6__py3-none-any.whl

{iatoolkit-0.7.5.dist-info → iatoolkit-0.7.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: iatoolkit
-Version: 0.7.5
+Version: 0.7.6
 Summary: IAToolkit
 Author: Fernando Libedinsky
 License-Expression: MIT

iatoolkit-0.7.6.dist-info/RECORD

@@ -0,0 +1,80 @@
+common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+common/auth.py,sha256=kKBvZoIm8RPpPFZ6KEm1oowHJfJwSO0mf10Yac8SG9k,8456
+common/exceptions.py,sha256=EXx40n5htp7UiOM6P1xfJ9U6NMcADqm62dlFaKz7ICU,1154
+common/routes.py,sha256=_1ywiXorwEeJ8IAamQwSxU9z8jlAAL_U64tMb01-zFg,4188
+common/session_manager.py,sha256=7D_RuJs60w-1zDr3fOGEz9JW7IZlSXuUHgUT87CzaUo,472
+common/util.py,sha256=5zw1wL_FdPBibGJbQAl1kozgTjUpsOZlPqT3tbWsHp4,15515
+iatoolkit/__init__.py,sha256=GkFxAQHKPifz4Kd8M73Rc8TWRVIxjxkl1N0nsPvb_sU,1743
+iatoolkit/base_company.py,sha256=WmD4o0qFC1n5DW5eRsRsuNfaGot9nxGFcJe3LmibSuE,4259
+iatoolkit/cli_commands.py,sha256=BGuThg19eoSssrBJIqzBNaWpMmyy7u4yRUz0JA7d-vc,2270
+iatoolkit/company_registry.py,sha256=tduqt3oV8iDX_IB1eA7KIgvIxE4edTcy-3qZIXh3Lzw,2549
+iatoolkit/iatoolkit.py,sha256=bbwLkLS_xZGNS0Dki3zX73RhAYMS32IshXDIdr_RVXg,15776
+iatoolkit/system_prompts/format_styles.prompt,sha256=MSMe1qvR3cF_0IbFshn8R0z6Wx6VCHQq1p37rpu5wwk,3576
+iatoolkit/system_prompts/query_main.prompt,sha256=w_9ybgWgiQH4V_RbAXqsvz0M7oOuiyhxcwf-D0CgfA4,3017
+iatoolkit/system_prompts/sql_rules.prompt,sha256=y4nURVnb9AyFwt-lrbMNBHHtZlhk6kC9grYoOhRnrJo,59174
+infra/__init__.py,sha256=5JqK9sZ6jBuK83zDQokUhxQ0wuJJJ9DXB8pYCLkX7X4,102
+infra/call_service.py,sha256=170qCNJb_9caUiEi8PprQaqSUS3Rj7XmU917J2-m62I,4919
+infra/gemini_adapter.py,sha256=MLesq8Oyx_Jd6-cSA_41zC1UtDM6CMino054NEybOJM,15031
+infra/google_chat_app.py,sha256=XHyFQyX92ztpJQLvNx4mKPjbR2x7_15t_dcpVqW25ZQ,1927
+infra/llm_client.py,sha256=cN1uaZxOP7H8LkmFpSpQMesBH3Pg1LKJuent4r1yovg,18548
+infra/llm_proxy.py,sha256=qBird4-k3Z8ABECvnWXbljXCQWx2q6RTmylJZQLDk4U,5684
+infra/llm_response.py,sha256=YUUQPBHzmP3Ce6-t0kKMRIpowvh7de1odSoefEByIvI,904
+infra/mail_app.py,sha256=eWSOz5uWf-KmZoUJbYFPad-0uWP2LekINAamDYbxYpg,6093
+infra/openai_adapter.py,sha256=roPrp-DJWcHHhOXdUttsgwfhJpMhHNy1RpkdzVKQMFo,3510
+infra/redis_session_manager.py,sha256=Dkwii8fns0_Vd9hm9GmotmrKtSCxVps868U5sqj7FAE,2278
+infra/connectors/__init__.py,sha256=5JqK9sZ6jBuK83zDQokUhxQ0wuJJJ9DXB8pYCLkX7X4,102
+infra/connectors/file_connector.py,sha256=HOjRTFd-WfDOcFyvHncAhnGNZuFgChIwC-P6osPo9ZM,352
+infra/connectors/file_connector_factory.py,sha256=xa4hphbeNVt0l4nn_mNbBT31lgn-OMlIQ8TtXpgN42M,2068
+infra/connectors/google_cloud_storage_connector.py,sha256=5KDZlT7ndgkqFOC3SebrmSQpP2zSb3KnSBVXWWt7Alg,2040
+infra/connectors/google_drive_connector.py,sha256=MyRECNWvLf5j-YvNwokcwihRS1WhZnBDUjx8tSup2L0,2527
+infra/connectors/local_file_connector.py,sha256=FO9_HFGKRE_GQqOjyWuIHyNFXYUgro39CxxqEcXUq1c,1719
+infra/connectors/s3_connector.py,sha256=M91gWnOgyCYIsoB0xka2oSaOTL4gDgjfjHwZi20jgnw,1113
+repositories/__init__.py,sha256=5JqK9sZ6jBuK83zDQokUhxQ0wuJJJ9DXB8pYCLkX7X4,102
+repositories/database_manager.py,sha256=UWOZhbUjNQV0yoL9xevuAnxV2OuBkMaxu5nqaqMuMQE,3098
+repositories/document_repo.py,sha256=dq41jj5hBOd6mRKdaSRMhyiHk12ukX43njVyLuuGl44,1094
+repositories/llm_query_repo.py,sha256=NF8Ybye_sMVvzeQGa_5MGJup0AFvl_P1Z0oCsr2Wz0Y,3592
+repositories/models.py,sha256=RJH0dtq2VIDJFaFDufV05NUnNW4WtNpdTjhONtfLyCw,13179
+repositories/profile_repo.py,sha256=JWbClu9SM18koUceLQdeuT5DA37h6ij5aeK-nwoRgIk,4042
+repositories/tasks_repo.py,sha256=cCg4uz8ou4tkx7yzmktEV4lfQjQBU-RylcqUof2dytY,1725
+repositories/vs_repo.py,sha256=PP6iPf0rt64rMyvqg-ffJk__sLbT2wgxx3dta3o8Vuo,5270
+services/__init__.py,sha256=5JqK9sZ6jBuK83zDQokUhxQ0wuJJJ9DXB8pYCLkX7X4,102
+services/benchmark_service.py,sha256=_ruKh9YzrTLtR0ZKrRNxqJQW0HdbwWuFz1gfLzJ9owA,5850
+services/dispatcher_service.py,sha256=y2J-TfrkoCcsOESr3E6E3q5bleJfRibT4ONxs9AxUSg,13959
+services/document_service.py,sha256=8MsJz0pihM9E9Z92PrPqDgQnpMAmpFrbogXr5HscMWM,5926
+services/excel_service.py,sha256=ATPaeAvkLwQAkPZ3AKIUpO73RVyRg0D8c6i37_mcql0,3559
+services/file_processor_service.py,sha256=98yWYF7nIq1nm7nh6IzMmTKaOMTIeqCFWYwXVtV-ZJI,4102
+services/history_service.py,sha256=j0QCqcIIyw7DBy3GrZrEZNk0I4m-uuRoG5g0Z2RCcOE,1586
+services/jwt_service.py,sha256=YoZ9h7_o9xBko-arNQv4MbcwnxoSWVNj4VbZmMo_QGY,3908
+services/load_documents_service.py,sha256=UGfomYz7seWFXawbDuk2t6CyoEr1vggR8vmrCUAeLBg,7190
+services/mail_service.py,sha256=_67pctxZO46DHnWBip51ayuYtWd4bEoS1kg29ACO7_I,2162
+services/profile_service.py,sha256=vTK9TvH_2AFdqgL3sGjhck9LyLGIbvdC2USoaRx82G8,17561
+services/prompt_manager_service.py,sha256=7SMC6N_T4BP4m5-ZNYAL3Y2YWHwl1bytXSgnEqu5bWI,8301
+services/query_service.py,sha256=gvUnq0Vpn4gv5ycQk8-fklh7NDFIXpO1Vt1lT2ugO6Q,15283
+services/search_service.py,sha256=bB3FWFxJi1iYsOdBxyu9tzIO406nQxcyeQzEowpmpjY,1803
+services/sql_service.py,sha256=s84K1ADlvMtum949wgMh8jsmqlOUeL-m_SWfAM4Wsv4,2141
+services/tasks_service.py,sha256=1DdbERlAxIkCpGEylnHDKC-KAsXRJugbaRSzRbPfL58,6790
+services/user_feedback_service.py,sha256=_LeNBYz4hHFapXfYTQVfkkD34gE8j2UeKnyOZ8H0nWo,2442
+services/user_session_context_service.py,sha256=GluNSgqP6W_hFke4oslSnfGnU_b-ph28BHH6jf3EIm0,3797
+views/__init__.py,sha256=5JqK9sZ6jBuK83zDQokUhxQ0wuJJJ9DXB8pYCLkX7X4,102
+views/change_password_view.py,sha256=KY6mf25Vc-rJn8pTLuJlkIHB7j9_NI0UoxIWod32qpM,3930
+views/chat_token_request_view.py,sha256=7Bgf7rOVdgo4u4nU4lZWk87wi_D9_-sYxB9zBuL8TcA,4388
+views/chat_view.py,sha256=XvKJApeJPU9uoH0XpHusehNbge3dDwwr72iMcuBveBY,2048
+views/download_file_view.py,sha256=AIHLURyPi7w0k_Rs_fqz0yOp1Hav8K73AC5Bxx4vzf4,1980
+views/external_chat_login_view.py,sha256=pz8EPmTSrYHpr3WbfYYBbPvSKaDJ9taOro4bMqTAZZE,3732
+views/external_login_view.py,sha256=2NPzdxIqw1zvRHcsKOVvL896mE9B4GCUI6gBW7LsZCU,1335
+views/file_store_view.py,sha256=591Kc2QR7SdxMrcJcL1ciMEwRopCpqYbmODL4XZ2SU8,1913
+views/forgot_password_view.py,sha256=7W2VP3nZlUdgGLv-zc7Pj5wa7OsT3K66t6fkntrSPzI,2705
+views/history_view.py,sha256=nkvV6Dg6SrVWZsWQJaCpy7D9VygwXDQF5FVanhzHdeo,2044
+views/home_view.py,sha256=lQvDYUJ1X-xu0GuJcZJwF9iW74d834_q8fCkLgqo6j4,1238
+views/llmquery_view.py,sha256=_CsbtFQFRuGCe50TWJDtTSUyaM3kMMwkn54kVuxMEQw,2412
+views/login_view.py,sha256=s2FQPo8EuJCWPoC2hs1Wyqh8rY6Dc_5HmiL9b9GLhho,2322
+views/prompt_view.py,sha256=ARuZ64EYjBhMAClUvjeFcr7zcgZUt2rEktbUvqpiE2U,1237
+views/signup_view.py,sha256=Jn2F0gGBDmyUYt4vo0fw2UMHoJblau-Be62zNAMas50,3795
+views/tasks_review_view.py,sha256=nvxdUJowfpgrJk0m8quxYg4iw5BZOhZhpDpPt5-wsDI,3368
+views/tasks_view.py,sha256=TWW48wzcJzqIPat1kSRx41Et92-wLr-wCkgypWYZ7dk,4090
+views/user_feedback_view.py,sha256=inZoNl5YnEq9_2FXOVvzKymXuSPELLmi9zPNG3zQxEQ,2632
+views/verify_user_view.py,sha256=0hRKIudox7KjxZDH973trUhw4fZtc7eiLz6R44QbIG8,2341
+iatoolkit-0.7.6.dist-info/METADATA,sha256=ewI228_gn4LwbqX0Dmd39uey9MCnkMRxpsL6Dcs5ujg,9300
+iatoolkit-0.7.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+iatoolkit-0.7.6.dist-info/top_level.txt,sha256=ZXCST2AUsVPIeMiz49ZFn7WEfIiO4d8BfWY9QzUqP0s,51
+iatoolkit-0.7.6.dist-info/RECORD,,

{iatoolkit-0.7.5.dist-info → iatoolkit-0.7.6.dist-info}/top_level.txt

@@ -1,3 +1,6 @@
 common
 iatoolkit
+infra
+repositories
 services
+views

infra/__init__.py

@@ -0,0 +1,5 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+

infra/call_service.py

@@ -0,0 +1,140 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+
+from common.exceptions import IAToolkitException
+from injector import inject
+# call_service.py
+import requests
+from typing import Optional, Dict, Any, Tuple, Union
+from requests import RequestException
+
+class CallServiceClient:
+    @inject
+    def __init__(self):
+        self.headers = {'Content-Type': 'application/json'}
+
+    def _merge_headers(self, extra: Optional[Dict[str, str]]) -> Dict[str, str]:
+        if not extra:
+            return dict(self.headers)
+        merged = dict(self.headers)
+        merged.update(extra)
+        return merged
+
+    def _normalize_timeout(self, timeout: Union[int, float, Tuple[int, int], Tuple[float, float]]) -> Tuple[float, float]:
+        # Si pasan un solo número → (connect, read) = (10, timeout)
+        if isinstance(timeout, (int, float)):
+            return (10, float(timeout))
+        return (float(timeout[0]), float(timeout[1]))
+
+    def _deserialize_response(self, response) -> Tuple[Any, int]:
+        try:
+            return response.json(), response.status_code
+        except ValueError:
+            # No es JSON → devolver texto
+            return response.text, response.status_code
+
+    def get(
+        self,
+        endpoint: str,
+        params: Optional[Dict[str, Any]] = None,
+        headers: Optional[Dict[str, str]] = None,
+        timeout: Union[int, float, Tuple[int, int]] = 10
+    ):
+        try:
+            response = requests.get(
+                endpoint,
+                params=params,
+                headers=self._merge_headers(headers),
+                timeout=self._normalize_timeout(timeout)
+            )
+        except RequestException as e:
+            raise IAToolkitException(IAToolkitException.ErrorType.REQUEST_ERROR, str(e))
+        return self._deserialize_response(response)
+
+    def post(
+        self,
+        endpoint: str,
+        json_dict: Optional[Dict[str, Any]] = None,
+        params: Optional[Dict[str, Any]] = None,
+        headers: Optional[Dict[str, str]] = None,
+        timeout: Union[int, float, Tuple[int, int]] = 10
+    ):
+        try:
+            response = requests.post(
+                endpoint,
+                params=params,
+                json=json_dict,
+                headers=self._merge_headers(headers),
+                timeout=self._normalize_timeout(timeout)
+            )
+        except RequestException as e:
+            raise IAToolkitException(IAToolkitException.ErrorType.REQUEST_ERROR, str(e))
+        return self._deserialize_response(response)
+
+    def put(
+        self,
+        endpoint: str,
+        json_dict: Optional[Dict[str, Any]] = None,
+        params: Optional[Dict[str, Any]] = None,
+        headers: Optional[Dict[str, str]] = None,
+        timeout: Union[int, float, Tuple[int, int]] = 10
+    ):
+        try:
+            response = requests.put(
+                endpoint,
+                params=params,
+                json=json_dict,
+                headers=self._merge_headers(headers),
+                timeout=self._normalize_timeout(timeout)
+            )
+        except RequestException as e:
+            raise IAToolkitException(IAToolkitException.ErrorType.REQUEST_ERROR, str(e))
+        return self._deserialize_response(response)
+
+    def delete(
+        self,
+        endpoint: str,
+        json_dict: Optional[Dict[str, Any]] = None,
+        params: Optional[Dict[str, Any]] = None,
+        headers: Optional[Dict[str, str]] = None,
+        timeout: Union[int, float, Tuple[int, int]] = 10
+    ):
+        try:
+            response = requests.delete(
+                endpoint,
+                params=params,
+                json=json_dict,
+                headers=self._merge_headers(headers),
+                timeout=self._normalize_timeout(timeout)
+            )
+        except RequestException as e:
+            raise IAToolkitException(IAToolkitException.ErrorType.REQUEST_ERROR, str(e))
+        return self._deserialize_response(response)
+
+    def post_files(
+        self,
+        endpoint: str,
+        data: Dict[str, Any],
+        params: Optional[Dict[str, Any]] = None,
+        headers: Optional[Dict[str, str]] = None,
+        timeout: Union[int, float, Tuple[int, int]] = 10
+    ):
+        # Para multipart/form-data no imponemos Content-Type por defecto
+        merged_headers = dict(self.headers)
+        merged_headers.pop('Content-Type', None)
+        if headers:
+            merged_headers.update(headers)
+
+        try:
+            response = requests.post(
+                endpoint,
+                params=params,
+                files=data,
+                headers=merged_headers,
+                timeout=self._normalize_timeout(timeout)
+            )
+        except RequestException as e:
+            raise IAToolkitException(IAToolkitException.ErrorType.REQUEST_ERROR, str(e))
+        return self._deserialize_response(response)

infra/connectors/__init__.py

@@ -0,0 +1,5 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+

infra/connectors/file_connector.py

@@ -0,0 +1,17 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+
+from abc import ABC, abstractmethod
+from typing import List
+
+
+class FileConnector(ABC):
+    @abstractmethod
+    def list_files(self) -> List[str]:
+        pass
+
+    @abstractmethod
+    def get_file_content(self, file_path: str) -> bytes:
+        pass

infra/connectors/file_connector_factory.py

@@ -0,0 +1,57 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+
+from infra.connectors.file_connector import FileConnector
+from infra.connectors.local_file_connector import LocalFileConnector
+from infra.connectors.s3_connector import S3Connector
+from infra.connectors.google_drive_connector import GoogleDriveConnector
+from infra.connectors.google_cloud_storage_connector import GoogleCloudStorageConnector
+from typing import Dict
+import os
+
+
+class FileConnectorFactory:
+    @staticmethod
+    def create(config: Dict) -> FileConnector:
+        """
+        Configuración esperada:
+        {
+            "type": "local" | "s3" | "gdrive" | "gcs",
+            "path": "/ruta/local",  # solo para local
+            "bucket": "mi-bucket", "prefix": "datos/", "auth": {...},  # solo para S3
+            "folder_id": "xxxxxxx",  # solo para Google Drive
+            "bucket": "mi-bucket", "service_account": "/ruta/service_account.json"  # solo para GCS
+        }
+        """
+        connector_type = config.get('type')
+
+        if connector_type == 'local':
+            return LocalFileConnector(config['path'])
+
+        elif connector_type == 's3':
+            auth = {
+                'aws_access_key_id': os.getenv('AWS_ACCESS_KEY_ID'),
+                'aws_secret_access_key': os.getenv('AWS_SECRET_ACCESS_KEY'),
+                'region_name': os.getenv('AWS_REGION', 'us-east-1')
+            }
+
+            return S3Connector(
+                bucket=config['bucket'],
+                prefix=config.get('prefix', ''),
+                auth=auth
+            )
+
+        elif connector_type == 'gdrive':
+            return GoogleDriveConnector(config['folder_id'],
+                    'service_account.json')
+
+        elif connector_type == 'gcs':
+            return GoogleCloudStorageConnector(
+                bucket_name=config['bucket'],
+                service_account_path=config.get('service_account', 'service_account.json')
+            )
+
+        else:
+            raise ValueError(f"Unknown connector type: {connector_type}")

infra/connectors/google_cloud_storage_connector.py

@@ -0,0 +1,53 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+
+from infra.connectors.file_connector import FileConnector
+from google.cloud import storage
+from typing import List
+
+
+class GoogleCloudStorageConnector(FileConnector):
+    def __init__(self, bucket_name: str, service_account_path: str = "service_account.json"):
+        """
+        Inicializa el conector de Google Cloud Storage utilizando la API oficial de Google.
+        :param bucket_name: Nombre del bucket en Google Cloud Storage.
+        :param service_account_path: Ruta al archivo JSON de la cuenta de servicio.
+        """
+        self.bucket_name = bucket_name
+        self.service_account_path = service_account_path
+        self.storage_client = self._authenticate()
+        self.bucket = self.storage_client.bucket(bucket_name)
+
+    def _authenticate(self):
+        """
+        Autentica en Google Cloud Storage utilizando una cuenta de servicio.
+        """
+        # Crear cliente de GCS con las credenciales
+        client = storage.Client.from_service_account_json(self.service_account_path)
+        return client
+
+    def list_files(self) -> List[dict]:
+        """
+        Lista todos los archivos en el bucket de GCS como diccionarios con claves 'path', 'name' y 'metadata'.
+        """
+        blobs = self.bucket.list_blobs()
+
+        return [
+            {
+                "path": blob.name,  # Nombre o "ruta" del blob en el bucket
+                "name": blob.name.split("/")[-1],  # Nombre del archivo (última parte del path)
+                "metadata": {"size": blob.size}  # Incluye tamaño como metadata (u otros metadatos relevantes)
+            }
+            for blob in blobs
+        ]
+
+    def get_file_content(self, file_path: str) -> bytes:
+        """
+        Descarga el contenido de un archivo en GCS dado su path (nombre del blob).
+        """
+        blob = self.bucket.blob(file_path)
+        file_buffer = blob.download_as_bytes()  # Descarga el contenido como bytes
+
+        return file_buffer

infra/connectors/google_drive_connector.py

@@ -0,0 +1,68 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+
+from infra.connectors.file_connector import FileConnector
+from googleapiclient.discovery import build
+from googleapiclient.http import MediaIoBaseDownload
+from google.oauth2.service_account import Credentials
+import io
+from typing import List
+
+
+class GoogleDriveConnector(FileConnector):
+    def __init__(self, folder_id: str, service_account_path: str = "service_account.json"):
+        """
+        Inicializa el conector de Google Drive utilizando la API oficial de Google.
+        :param folder_id: ID de la carpeta en Google Drive.
+        :param service_account_path: Ruta al archivo JSON de la cuenta de servicio.
+        """
+        self.folder_id = folder_id
+        self.service_account_path = service_account_path
+        self.drive_service = self._authenticate()
+
+    def _authenticate(self):
+        """
+        Autentica en Google Drive utilizando una cuenta de servicio.
+        """
+        # Cargar credenciales desde el archivo de servicio
+        credentials = Credentials.from_service_account_file(
+            self.service_account_path,
+            scopes=["https://www.googleapis.com/auth/drive"]
+        )
+
+        # Crear el cliente de Google Drive API
+        service = build('drive', 'v3', credentials=credentials)
+        return service
+
+    def list_files(self) -> List[dict]:
+        """
+        Estándar: Lista todos los archivos como diccionarios con claves 'path', 'name' y 'metadata'.
+        """
+        query = f"'{self.folder_id}' in parents and trashed=false"
+        results = self.drive_service.files().list(q=query, fields="files(id, name)").execute()
+        files = results.get('files', [])
+
+        return [
+            {
+                "path": file['id'],  # ID único del archivo en Google Drive
+                "name": file['name'],  # Nombre del archivo en Google Drive
+                "metadata": {}  # No hay metadatos adicionales en este caso
+            }
+            for file in files
+        ]
+
+    def get_file_content(self, file_path: str) -> bytes:
+        """
+        Obtiene el contenido de un archivo en Google Drive utilizando su ID (file_path).
+        """
+        request = self.drive_service.files().get_media(fileId=file_path)
+        file_buffer = io.BytesIO()
+        downloader = MediaIoBaseDownload(file_buffer, request)
+
+        done = False
+        while not done:
+            status, done = downloader.next_chunk()
+
+        return file_buffer.getvalue()

infra/connectors/local_file_connector.py

@@ -0,0 +1,46 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+
+import os
+from infra.connectors.file_connector import FileConnector
+from typing import List
+from common.exceptions import IAToolkitException
+
+
+class LocalFileConnector(FileConnector):
+    def __init__(self, directory: str):
+        local_root = os.getenv("ROOT_DIR_LOCAL_FILES", '')
+        self.directory = os.path.join(local_root, directory)
+
+    def list_files(self) -> List[dict]:
+        """
+        Estándar: Lista todos los archivos como diccionarios con claves 'path', 'name' y 'metadata'.
+        """
+        try:
+            files = [
+                os.path.join(self.directory, f)
+                for f in os.listdir(self.directory)
+                if os.path.isfile(os.path.join(self.directory, f))
+            ]
+
+            return [
+                {
+                    "path": file,  # Ruta completa al archivo local
+                    "name": os.path.basename(file),  # Nombre del archivo
+                    "metadata": {"size": os.path.getsize(file), "last_modified": os.path.getmtime(file)}
+                }
+                for file in files
+            ]
+        except Exception as e:
+            raise IAToolkitException(IAToolkitException.ErrorType.FILE_IO_ERROR,
+                               f"Error procesando el directorio {self.directory}: {e}")
+
+    def get_file_content(self, file_path: str) -> bytes:
+        try:
+            with open(file_path, 'rb') as f:
+                return f.read()
+        except Exception as e:
+            raise IAToolkitException(IAToolkitException.ErrorType.FILE_IO_ERROR,
+                               f"Error leyendo el archivo {file_path}: {e}")

infra/connectors/s3_connector.py

@@ -0,0 +1,33 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+
+import boto3
+from infra.connectors.file_connector import FileConnector
+from typing import List
+
+
+class S3Connector(FileConnector):
+    def __init__(self, bucket: str, prefix: str, auth: dict):
+        self.bucket = bucket
+        self.prefix = prefix
+        self.s3 = boto3.client('s3', **auth)
+
+    def list_files(self) -> List[dict]:
+        # list all the files as dictionaries, with keys:  'path', 'name' y 'metadata'.
+        response = self.s3.list_objects_v2(Bucket=self.bucket, Prefix=self.prefix)
+        files = response.get('Contents', [])
+
+        return [
+            {
+                "path": obj['Key'],  # s3 key
+                "name": obj['Key'].split('/')[-1],  # filename
+                "metadata": {"size": obj.get('Size'), "last_modified": obj.get('LastModified')}
+            }
+            for obj in files
+        ]
+
+    def get_file_content(self, file_path: str) -> bytes:
+        response = self.s3.get_object(Bucket=self.bucket, Key=file_path)
+        return response['Body'].read()