unstructured-ingest 0.0.24__tar.gz → 0.0.25__tar.gz

{unstructured_ingest-0.0.24 → unstructured_ingest-0.0.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unstructured-ingest
-Version: 0.0.24
+Version: 0.0.25
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -23,11 +23,11 @@ Requires-Python: >=3.9.0,<3.13
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
 Requires-Dist: dataclasses_json
-Requires-Dist: tqdm
-Requires-Dist: pydantic>=2.7
 Requires-Dist: click
 Requires-Dist: pandas
 Requires-Dist: python-dateutil
+Requires-Dist: tqdm
+Requires-Dist: pydantic>=2.7
 Requires-Dist: opentelemetry-sdk
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.25.8; extra == "remote"
@@ -66,16 +66,16 @@ Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
 Requires-Dist: astrapy; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: fsspec; extra == "azure"
 Requires-Dist: adlfs; extra == "azure"
+Requires-Dist: fsspec; extra == "azure"
 Provides-Extra: azure-cognitive-search
 Requires-Dist: azure-search-documents; extra == "azure-cognitive-search"
 Provides-Extra: biomed
-Requires-Dist: bs4; extra == "biomed"
 Requires-Dist: requests; extra == "biomed"
+Requires-Dist: bs4; extra == "biomed"
 Provides-Extra: box
-Requires-Dist: boxfs; extra == "box"
 Requires-Dist: fsspec; extra == "box"
+Requires-Dist: boxfs; extra == "box"
 Provides-Extra: chroma
 Requires-Dist: chromadb; extra == "chroma"
 Provides-Extra: clarifai
@@ -96,8 +96,8 @@ Requires-Dist: dropboxdrivefs; extra == "dropbox"
 Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
-Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: gcsfs; extra == "gcs"
+Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: fsspec; extra == "gcs"
 Provides-Extra: github
 Requires-Dist: pygithub>1.58.0; extra == "github"
@@ -107,8 +107,8 @@ Requires-Dist: python-gitlab; extra == "gitlab"
 Provides-Extra: google-drive
 Requires-Dist: google-api-python-client; extra == "google-drive"
 Provides-Extra: hubspot
-Requires-Dist: urllib3; extra == "hubspot"
 Requires-Dist: hubspot-api-client; extra == "hubspot"
+Requires-Dist: urllib3; extra == "hubspot"
 Provides-Extra: jira
 Requires-Dist: atlassian-python-api; extra == "jira"
 Provides-Extra: kafka
@@ -120,19 +120,19 @@ Requires-Dist: pymilvus; extra == "milvus"
 Provides-Extra: mongodb
 Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: notion
-Requires-Dist: notion-client; extra == "notion"
 Requires-Dist: httpx; extra == "notion"
-Requires-Dist: htmlBuilder; extra == "notion"
 Requires-Dist: backoff; extra == "notion"
+Requires-Dist: notion-client; extra == "notion"
+Requires-Dist: htmlBuilder; extra == "notion"
 Provides-Extra: onedrive
+Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Requires-Dist: bs4; extra == "onedrive"
 Requires-Dist: msal; extra == "onedrive"
-Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Provides-Extra: opensearch
 Requires-Dist: opensearch-py; extra == "opensearch"
 Provides-Extra: outlook
-Requires-Dist: msal; extra == "outlook"
 Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
+Requires-Dist: msal; extra == "outlook"
 Provides-Extra: pinecone
 Requires-Dist: pinecone-client>=3.7.1; extra == "pinecone"
 Provides-Extra: postgres
@@ -145,13 +145,13 @@ Provides-Extra: s3
 Requires-Dist: fsspec; extra == "s3"
 Requires-Dist: s3fs; extra == "s3"
 Provides-Extra: sharepoint
-Requires-Dist: msal; extra == "sharepoint"
 Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
+Requires-Dist: msal; extra == "sharepoint"
 Provides-Extra: salesforce
 Requires-Dist: simple-salesforce; extra == "salesforce"
 Provides-Extra: sftp
-Requires-Dist: fsspec; extra == "sftp"
 Requires-Dist: paramiko; extra == "sftp"
+Requires-Dist: fsspec; extra == "sftp"
 Provides-Extra: slack
 Requires-Dist: slack_sdk; extra == "slack"
 Provides-Extra: wikipedia
@@ -167,8 +167,8 @@ Requires-Dist: requests; extra == "vectara"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
-Requires-Dist: openai; extra == "embed-octoai"
 Requires-Dist: tiktoken; extra == "embed-octoai"
+Requires-Dist: openai; extra == "embed-octoai"
 Provides-Extra: embed-vertexai
 Requires-Dist: vertexai; extra == "embed-vertexai"
 Provides-Extra: embed-voyageai
@@ -176,8 +176,8 @@ Requires-Dist: voyageai; extra == "embed-voyageai"
 Provides-Extra: embed-mixedbreadai
 Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
 Provides-Extra: openai
-Requires-Dist: openai; extra == "openai"
 Requires-Dist: tiktoken; extra == "openai"
+Requires-Dist: openai; extra == "openai"
 Provides-Extra: bedrock
 Requires-Dist: boto3; extra == "bedrock"
 

unstructured_ingest-0.0.25/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.0.25"  # pragma: no cover

{unstructured_ingest-0.0.24 → unstructured_ingest-0.0.25}/unstructured_ingest/utils/dep_check.py

@@ -20,6 +20,18 @@ def requires_dependencies(
     dependencies: str | list[str],
     extras: Optional[str] = None,
 ) -> Callable[[Callable[_P, _T]], Callable[_P, _T]]:
+    """Decorator ensuring required modules are installed.
+
+    Use on functions with local imports to ensure required modules are available and log
+    an installation instruction if they're not.
+
+    Args:
+        dependencies: Name(s) of module(s) required by the decorated function.
+        extras: unstructured-ingest extra which installs required `dependencies`. Defaults to None.
+
+    Raises:
+        ImportError: When at least one of the `dependencies` is not available.
+    """
     if isinstance(dependencies, str):
         dependencies = [dependencies]
 

{unstructured_ingest-0.0.24 → unstructured_ingest-0.0.25}/unstructured_ingest/v2/processes/connectors/__init__.py

@@ -17,7 +17,10 @@ from .chroma import chroma_destination_entry
 from .couchbase import CONNECTOR_TYPE as COUCHBASE_CONNECTOR_TYPE
 from .couchbase import couchbase_destination_entry, couchbase_source_entry
 from .databricks_volumes import CONNECTOR_TYPE as DATABRICKS_VOLUMES_CONNECTOR_TYPE
-from .databricks_volumes import databricks_volumes_destination_entry
+from .databricks_volumes import (
+    databricks_volumes_destination_entry,
+    databricks_volumes_source_entry,
+)
 from .elasticsearch import CONNECTOR_TYPE as ELASTICSEARCH_CONNECTOR_TYPE
 from .elasticsearch import elasticsearch_destination_entry, elasticsearch_source_entry
 from .google_drive import CONNECTOR_TYPE as GOOGLE_DRIVE_CONNECTOR_TYPE
@@ -34,6 +37,8 @@ from .onedrive import CONNECTOR_TYPE as ONEDRIVE_CONNECTOR_TYPE
 from .onedrive import onedrive_source_entry
 from .opensearch import CONNECTOR_TYPE as OPENSEARCH_CONNECTOR_TYPE
 from .opensearch import opensearch_destination_entry, opensearch_source_entry
+from .outlook import CONNECTOR_TYPE as OUTLOOK_CONNECTOR_TYPE
+from .outlook import outlook_source_entry
 from .pinecone import CONNECTOR_TYPE as PINECONE_CONNECTOR_TYPE
 from .pinecone import pinecone_destination_entry
 from .salesforce import CONNECTOR_TYPE as SALESFORCE_CONNECTOR_TYPE
@@ -78,6 +83,10 @@ add_destination_entry(destination_type=WEAVIATE_CONNECTOR_TYPE, entry=weaviate_d
 add_destination_entry(
     destination_type=DATABRICKS_VOLUMES_CONNECTOR_TYPE, entry=databricks_volumes_destination_entry
 )
+add_source_entry(
+    source_type=DATABRICKS_VOLUMES_CONNECTOR_TYPE, entry=databricks_volumes_source_entry
+)
+
 
 add_destination_entry(destination_type=SQL_CONNECTOR_TYPE, entry=sql_destination_entry)
 
@@ -95,3 +104,5 @@ add_destination_entry(
 
 add_destination_entry(destination_type=KDBAI_CONNECTOR_TYPE, entry=kdbai_destination_entry)
 add_source_entry(source_type=AIRTABLE_CONNECTOR_TYPE, entry=airtable_source_entry)
+
+add_source_entry(source_type=OUTLOOK_CONNECTOR_TYPE, entry=outlook_source_entry)

{unstructured_ingest-0.0.24 → unstructured_ingest-0.0.25}/unstructured_ingest/v2/processes/connectors/databricks_volumes.py

@@ -1,21 +1,35 @@
 import os
 from dataclasses import dataclass
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Optional
+from typing import TYPE_CHECKING, Any, Generator, Optional
 
 from pydantic import Field, Secret
 
-from unstructured_ingest.error import DestinationConnectionError
+from unstructured_ingest.error import (
+    DestinationConnectionError,
+    SourceConnectionError,
+    SourceConnectionNetworkError,
+)
 from unstructured_ingest.utils.dep_check import requires_dependencies
 from unstructured_ingest.v2.interfaces import (
     AccessConfig,
     ConnectionConfig,
+    Downloader,
+    DownloaderConfig,
+    DownloadResponse,
     FileData,
+    FileDataSourceMetadata,
+    Indexer,
+    IndexerConfig,
+    SourceIdentifiers,
     Uploader,
     UploaderConfig,
 )
 from unstructured_ingest.v2.logger import logger
-from unstructured_ingest.v2.processes.connector_registry import DestinationRegistryEntry
+from unstructured_ingest.v2.processes.connector_registry import (
+    DestinationRegistryEntry,
+    SourceRegistryEntry,
+)
 
 if TYPE_CHECKING:
     from databricks.sdk import WorkspaceClient
@@ -32,16 +46,6 @@ class DatabricksVolumesAccessConfig(AccessConfig):
         "https://accounts.azuredatabricks.net/ (Azure), "
         "or https://accounts.gcp.databricks.com/ (GCP).",
     )
-    username: Optional[str] = Field(
-        default=None,
-        description="The Databricks username part of basic authentication. "
-        "Only possible when Host is *.cloud.databricks.com (AWS).",
-    )
-    password: Optional[str] = Field(
-        default=None,
-        description="The Databricks password part of basic authentication. "
-        "Only possible when Host is *.cloud.databricks.com (AWS).",
-    )
     client_id: Optional[str] = Field(default=None, description="Client ID of the OAuth app.")
     client_secret: Optional[str] = Field(
         default=None, description="Client Secret of the OAuth app."
@@ -78,7 +82,6 @@ class DatabricksVolumesAccessConfig(AccessConfig):
         "argument. This argument also holds the currently "
         "selected auth.",
     )
-    cluster_id: Optional[str] = None
     google_credentials: Optional[str] = None
     google_service_account: Optional[str] = None
 
@@ -93,17 +96,11 @@ class DatabricksVolumesConnectionConfig(ConnectionConfig):
         "Databricks workspace endpoint or the "
         "Databricks accounts endpoint.",
     )
-
-
-class DatabricksVolumesUploaderConfig(UploaderConfig):
     volume: str = Field(description="Name of volume in the Unity Catalog")
     catalog: str = Field(description="Name of the catalog in the Databricks Unity Catalog service")
     volume_path: Optional[str] = Field(
         default=None, description="Optional path within the volume to write to"
     )
-    overwrite: bool = Field(
-        default=False, description="If true, an existing file will be overwritten."
-    )
     databricks_schema: str = Field(
         default="default",
         alias="schema",
@@ -117,33 +114,121 @@ class DatabricksVolumesUploaderConfig(UploaderConfig):
             path = f"{path}/{self.volume_path}"
         return path
 
-
-@dataclass
-class DatabricksVolumesUploader(Uploader):
-    connector_type: str = CONNECTOR_TYPE
-    upload_config: DatabricksVolumesUploaderConfig
-    connection_config: DatabricksVolumesConnectionConfig
-
     @requires_dependencies(dependencies=["databricks.sdk"], extras="databricks-volumes")
     def get_client(self) -> "WorkspaceClient":
         from databricks.sdk import WorkspaceClient
 
         return WorkspaceClient(
-            host=self.connection_config.host,
-            **self.connection_config.access_config.get_secret_value().model_dump(),
+            host=self.host,
+            **self.access_config.get_secret_value().model_dump(),
         )
 
+
+@dataclass
+class DatabricksVolumesIndexerConfig(IndexerConfig):
+    recursive: bool = False
+
+
+@dataclass
+class DatabricksVolumesIndexer(Indexer):
+    index_config: DatabricksVolumesIndexerConfig
+    connection_config: DatabricksVolumesConnectionConfig
+    connector_type: str = CONNECTOR_TYPE
+
     def precheck(self) -> None:
         try:
-            assert self.get_client().current_user.me().active
+            self.connection_config.get_client()
+        except Exception as e:
+            logger.error(f"failed to validate connection: {e}", exc_info=True)
+            raise SourceConnectionError(f"failed to validate connection: {e}")
+
+    def run(self, **kwargs: Any) -> Generator[FileData, None, None]:
+        for file_info in self.connection_config.get_client().dbfs.list(
+            path=self.connection_config.path, recursive=self.index_config.recursive
+        ):
+            if file_info.is_dir:
+                continue
+            rel_path = file_info.path.replace(self.connection_config.path, "")
+            if rel_path.startswith("/"):
+                rel_path = rel_path[1:]
+            filename = Path(file_info.path).name
+            yield FileData(
+                identifier=file_info.path,
+                connector_type=CONNECTOR_TYPE,
+                source_identifiers=SourceIdentifiers(
+                    filename=filename,
+                    rel_path=rel_path,
+                    fullpath=file_info.path,
+                ),
+                additional_metadata={
+                    "catalog": self.connection_config.catalog,
+                },
+                metadata=FileDataSourceMetadata(
+                    url=file_info.path, date_modified=str(file_info.modification_time)
+                ),
+            )
+
+
+@dataclass
+class DatabricksVolumesDownloaderConfig(DownloaderConfig):
+    pass
+
+
+@dataclass
+class DatabricksVolumesDownloader(Downloader):
+    download_config: DatabricksVolumesDownloaderConfig
+    connection_config: DatabricksVolumesConnectionConfig
+    connector_type: str = CONNECTOR_TYPE
+
+    def precheck(self) -> None:
+        try:
+            self.connection_config.get_client()
+        except Exception as e:
+            logger.error(f"failed to validate connection: {e}", exc_info=True)
+            raise SourceConnectionError(f"failed to validate connection: {e}")
+
+    def get_download_path(self, file_data: FileData) -> Path:
+        return self.download_config.download_dir / Path(file_data.source_identifiers.relative_path)
+
+    def run(self, file_data: FileData, **kwargs: Any) -> DownloadResponse:
+        download_path = self.get_download_path(file_data=file_data)
+        download_path.parent.mkdir(parents=True, exist_ok=True)
+        logger.info(f"Writing {file_data.identifier} to {download_path}")
+        try:
+            with self.connection_config.get_client().dbfs.download(path=file_data.identifier) as c:
+                read_content = c._read_handle.read()
+            with open(download_path, "wb") as f:
+                f.write(read_content)
+        except Exception as e:
+            logger.error(f"failed to download file {file_data.identifier}: {e}", exc_info=True)
+            raise SourceConnectionNetworkError(f"failed to download file {file_data.identifier}")
+
+        return self.generate_download_response(file_data=file_data, download_path=download_path)
+
+
+class DatabricksVolumesUploaderConfig(UploaderConfig):
+    overwrite: bool = Field(
+        default=False, description="If true, an existing file will be overwritten."
+    )
+
+
+@dataclass
+class DatabricksVolumesUploader(Uploader):
+    upload_config: DatabricksVolumesUploaderConfig
+    connection_config: DatabricksVolumesConnectionConfig
+    connector_type: str = CONNECTOR_TYPE
+
+    def precheck(self) -> None:
+        try:
+            assert self.connection_config.get_client().current_user.me().active
         except Exception as e:
             logger.error(f"failed to validate connection: {e}", exc_info=True)
             raise DestinationConnectionError(f"failed to validate connection: {e}")
 
     def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
-        output_path = os.path.join(self.upload_config.path, path.name)
+        output_path = os.path.join(self.connection_config.path, path.name)
         with open(path, "rb") as elements_file:
-            self.get_client().files.upload(
+            self.connection_config.get_client().files.upload(
                 file_path=output_path,
                 contents=elements_file,
                 overwrite=self.upload_config.overwrite,
@@ -155,3 +240,11 @@ databricks_volumes_destination_entry = DestinationRegistryEntry(
     uploader=DatabricksVolumesUploader,
     uploader_config=DatabricksVolumesUploaderConfig,
 )
+
+databricks_volumes_source_entry = SourceRegistryEntry(
+    connection_config=DatabricksVolumesConnectionConfig,
+    indexer=DatabricksVolumesIndexer,
+    indexer_config=DatabricksVolumesIndexerConfig,
+    downloader=DatabricksVolumesDownloader,
+    downloader_config=DatabricksVolumesDownloaderConfig,
+)

unstructured_ingest-0.0.25/unstructured_ingest/v2/processes/connectors/outlook.py

@@ -0,0 +1,239 @@
+import hashlib
+import time
+from dataclasses import dataclass, field
+from datetime import timezone
+from pathlib import Path
+from typing import TYPE_CHECKING, Any, Coroutine, Generator
+
+from pydantic import Field, Secret
+
+from unstructured_ingest.error import SourceConnectionError
+from unstructured_ingest.logger import logger
+from unstructured_ingest.utils.dep_check import requires_dependencies
+from unstructured_ingest.v2.interfaces import (
+    AccessConfig,
+    ConnectionConfig,
+    Downloader,
+    DownloaderConfig,
+    FileData,
+    Indexer,
+    IndexerConfig,
+    download_responses,
+)
+from unstructured_ingest.v2.interfaces.file_data import FileDataSourceMetadata, SourceIdentifiers
+from unstructured_ingest.v2.processes.connector_registry import SourceRegistryEntry
+
+MAX_EMAILS_PER_FOLDER = 1_000_000  # Maximum number of emails per folder
+
+if TYPE_CHECKING:
+    from office365.graph_client import GraphClient
+    from office365.outlook.mail.folders.folder import MailFolder
+    from office365.outlook.mail.messages.message import Message
+
+
+CONNECTOR_TYPE = "outlook"
+
+
+class OutlookAccessConfig(AccessConfig):
+    client_credential: str = Field(description="Azure AD App client secret", alias="client_cred")
+
+
+class OutlookConnectionConfig(ConnectionConfig):
+    access_config: Secret[OutlookAccessConfig]
+    client_id: str = Field(description="Azure AD App client ID")
+    tenant: str = Field(
+        default="common", description="ID or domain name associated with your Azure AD instance"
+    )
+    authority_url: str = Field(
+        default="https://login.microsoftonline.com",
+        description="Authentication token provider for Microsoft apps",
+    )
+
+    @requires_dependencies(["msal"], extras="outlook")
+    def _acquire_token(self):
+        """Acquire token via MSAL"""
+        from msal import ConfidentialClientApplication
+
+        # NOTE: It'd be nice to use `msal.authority.AuthorityBuilder` here paired with AZURE_PUBLIC
+        # constant as default in the future but they do not fit well with `authority_url` right now
+        authority_url = f"{self.authority_url.rstrip('/')}/{self.tenant}"
+        app = ConfidentialClientApplication(
+            authority=authority_url,
+            client_id=self.client_id,
+            client_credential=self.access_config.get_secret_value().client_credential,
+        )
+        token = app.acquire_token_for_client(scopes=["https://graph.microsoft.com/.default"])
+        return token
+
+    @requires_dependencies(["office365"], extras="outlook")
+    @SourceConnectionError.wrap
+    def get_client(self) -> "GraphClient":
+        from office365.graph_client import GraphClient
+
+        return GraphClient(self._acquire_token)
+
+
+class OutlookIndexerConfig(IndexerConfig):
+    outlook_folders: list[str] = Field(
+        description="Folders to download email messages from. Do not specify subfolders. "
+        "Use quotes if there are spaces in folder names."
+    )
+    recursive: bool = Field(
+        default=False,
+        description="Recursively download files in their respective folders otherwise stop at the"
+        " files in provided folder level.",
+    )
+    user_email: str = Field(description="Outlook email to download messages from.")
+
+
+@dataclass
+class OutlookIndexer(Indexer):
+    index_config: OutlookIndexerConfig
+    connection_config: OutlookConnectionConfig
+    connector_type: str = CONNECTOR_TYPE
+
+    def run(self, **kwargs: Any) -> Generator[FileData, None, None]:
+        messages = self._list_messages(recursive=self.index_config.recursive)
+
+        for message in messages:
+            yield self._message_to_file_data(message)
+
+    def run_async(self, **kwargs: Any) -> Coroutine[Any, Any, Any]:
+        raise NotImplementedError
+
+    @SourceConnectionError.wrap
+    def precheck(self) -> None:
+        client = self.connection_config.get_client()
+        client.users[self.index_config.user_email].get().execute_query()
+
+    def is_async(self) -> bool:
+        return False
+
+    def _list_messages(self, recursive: bool) -> list["Message"]:
+        mail_folders = self._get_selected_root_folders()
+        messages = []
+
+        while mail_folders:
+            mail_folder = mail_folders.pop()
+            messages += list(mail_folder.messages.get().top(MAX_EMAILS_PER_FOLDER).execute_query())
+
+            if recursive:
+                mail_folders += list(mail_folder.child_folders.get().execute_query())
+
+        return messages
+
+    def _get_selected_root_folders(self) -> list["MailFolder"]:
+        client_user = self.connection_config.get_client().users[self.index_config.user_email]
+        root_mail_folders = client_user.mail_folders.get().execute_query()
+
+        selected_names_normalized = [
+            folder_name.lower() for folder_name in self.index_config.outlook_folders
+        ]
+        selected_root_mail_folders = [
+            folder
+            for folder in root_mail_folders
+            if folder.display_name.lower() in selected_names_normalized
+        ]
+
+        if not selected_root_mail_folders:
+            logger.error(
+                f"Root folders selected in configuration: {self.index_config.outlook_folders}"
+                f"not found for user email {self.index_config.user_email}. Aborting."
+            )
+            raise ValueError("Root folders selected in configuration not found.")
+
+        return selected_root_mail_folders
+
+    def _message_to_file_data(self, message: "Message") -> FileData:
+        fullpath = self._generate_fullpath(message)
+
+        return FileData(
+            identifier=message.id,
+            connector_type=CONNECTOR_TYPE,
+            source_identifiers=SourceIdentifiers(filename=fullpath.name, fullpath=str(fullpath)),
+            metadata=FileDataSourceMetadata(
+                url=message.resource_url,
+                version=message.change_key,
+                date_modified=str(
+                    message.last_modified_datetime.replace(tzinfo=timezone.utc).timestamp()
+                ),
+                date_created=str(message.created_datetime.replace(tzinfo=timezone.utc).timestamp()),
+                date_processed=str(time.time()),
+                record_locator={
+                    "message_id": message.id,
+                    "user_email": self.index_config.user_email,
+                },
+            ),
+            additional_metadata={
+                "sent_from": str(message.sent_from),
+                "to_recipients": [str(recipient) for recipient in message.to_recipients],
+                "bcc_recipients": [str(recipient) for recipient in message.to_recipients],
+                "subject": message.subject,
+                "conversation_id": message.conversation_id,
+                "is_draft": message.is_draft,
+                "is_read": message.is_read,
+                "has_attachments": message.has_attachments,
+                "importance": message.importance,
+            },
+        )
+
+    def _generate_fullpath(self, message: "Message") -> Path:
+        return Path(hashlib.sha256(message.id.encode("utf-8")).hexdigest()[:16] + ".eml")
+
+
+class OutlookDownloaderConfig(DownloaderConfig):
+    pass
+
+
+@dataclass
+class OutlookDownloader(Downloader):
+    connector_type: str = CONNECTOR_TYPE
+    connection_config: OutlookConnectionConfig
+    download_config: OutlookDownloaderConfig = field(default_factory=OutlookDownloaderConfig)
+
+    def run(self, file_data: FileData, **kwargs: Any) -> download_responses:
+        # NOTE: Indexer should provide source identifiers required to generate the download path
+        download_path = self.get_download_path(file_data)
+        if download_path is None:
+            logger.error(
+                "Generated download path is None, source_identifiers might be missing"
+                "from FileData."
+            )
+            raise ValueError("Generated invalid download path.")
+
+        self._download_message(file_data, download_path)
+        return self.generate_download_response(file_data, download_path)
+
+    def is_async(self) -> bool:
+        return False
+
+    def _download_message(self, file_data: FileData, download_path: Path) -> None:
+        # NOTE: Indexer should supply the record locator in metadata
+        if (
+            file_data.metadata.record_locator is None
+            or "user_email" not in file_data.metadata.record_locator
+            or "message_id" not in file_data.metadata.record_locator
+        ):
+            logger.error(
+                f"Invalid record locator in metadata: {file_data.metadata.record_locator}."
+                "Keys 'user_email' and 'message_id' must be present."
+            )
+            raise ValueError("Invalid record locator.")
+
+        user_email = file_data.metadata.record_locator["user_email"]
+        message_id = file_data.metadata.record_locator["message_id"]
+
+        message = self.connection_config.get_client().users[user_email].messages[message_id]
+        download_path.parent.mkdir(exist_ok=True, parents=True)
+
+        with open(download_path, "wb") as file:
+            message.download(file).execute_query()
+
+
+outlook_source_entry = SourceRegistryEntry(
+    indexer=OutlookIndexer,
+    indexer_config=OutlookIndexerConfig,
+    downloader=OutlookDownloader,
+    downloader_config=OutlookDownloaderConfig,
+    connection_config=OutlookConnectionConfig,
+)

{unstructured_ingest-0.0.24 → unstructured_ingest-0.0.25}/unstructured_ingest/v2/processes/connectors/pinecone.py

@@ -94,6 +94,10 @@ class PineconeUploaderConfig(UploaderConfig):
     pool_threads: Optional[int] = Field(
         default=1, description="Optional limit on number of threads to use for upload"
     )
+    namespace: Optional[str] = Field(
+        default=None,
+        description="The namespace to write to. If not specified, the default namespace is used",
+    )
 
 
 @dataclass
@@ -183,7 +187,11 @@ class PineconeUploader(Uploader):
             pool_threads = max_pool_threads
         index = self.connection_config.get_index(pool_threads=pool_threads)
         with index:
-            async_results = [index.upsert(vectors=chunk, async_req=True) for chunk in chunks]
+            upsert_kwargs = [{"vectors": chunk, "async_req": True} for chunk in chunks]
+            if namespace := self.upload_config.namespace:
+                for kwargs in upsert_kwargs:
+                    kwargs["namespace"] = namespace
+            async_results = [index.upsert(**kwarg) for kwarg in upsert_kwargs]
             # Wait for and retrieve responses (this raises in case of error)
             try:
                 results = [async_result.get() for async_result in async_results]