unstructured-ingest 0.5.3__tar.gz → 0.5.5__tar.gz

{unstructured_ingest-0.5.3/unstructured_ingest.egg-info → unstructured_ingest-0.5.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.5.3
+Version: 0.5.5
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,13 +22,13 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: python-dateutil
-Requires-Dist: opentelemetry-sdk
-Requires-Dist: tqdm
-Requires-Dist: pandas
 Requires-Dist: click
-Requires-Dist: pydantic>=2.7
+Requires-Dist: pandas
+Requires-Dist: tqdm
 Requires-Dist: dataclasses_json
+Requires-Dist: pydantic>=2.7
+Requires-Dist: opentelemetry-sdk
+Requires-Dist: python-dateutil
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.26.1; extra == "remote"
 Provides-Extra: csv
@@ -66,13 +66,13 @@ Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
 Requires-Dist: astrapy; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: fsspec; extra == "azure"
+Requires-Dist: adlfs; extra == "azure"
 Provides-Extra: azure-ai-search
 Requires-Dist: azure-search-documents; extra == "azure-ai-search"
 Provides-Extra: biomed
-Requires-Dist: requests; extra == "biomed"
 Requires-Dist: bs4; extra == "biomed"
+Requires-Dist: requests; extra == "biomed"
 Provides-Extra: box
 Requires-Dist: fsspec; extra == "box"
 Requires-Dist: boxfs; extra == "box"
@@ -86,8 +86,8 @@ Requires-Dist: requests; extra == "confluence"
 Provides-Extra: couchbase
 Requires-Dist: couchbase; extra == "couchbase"
 Provides-Extra: delta-table
-Requires-Dist: deltalake; extra == "delta-table"
 Requires-Dist: boto3; extra == "delta-table"
+Requires-Dist: deltalake; extra == "delta-table"
 Provides-Extra: discord
 Requires-Dist: discord.py; extra == "discord"
 Provides-Extra: dropbox
@@ -98,19 +98,19 @@ Requires-Dist: duckdb; extra == "duckdb"
 Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
-Requires-Dist: gcsfs; extra == "gcs"
-Requires-Dist: fsspec; extra == "gcs"
 Requires-Dist: bs4; extra == "gcs"
+Requires-Dist: fsspec; extra == "gcs"
+Requires-Dist: gcsfs; extra == "gcs"
 Provides-Extra: github
-Requires-Dist: pygithub>1.58.0; extra == "github"
 Requires-Dist: requests; extra == "github"
+Requires-Dist: pygithub>1.58.0; extra == "github"
 Provides-Extra: gitlab
 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
@@ -125,22 +125,22 @@ Provides-Extra: mongodb
 Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: neo4j
 Requires-Dist: cymple; extra == "neo4j"
-Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Requires-Dist: networkx; extra == "neo4j"
+Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Provides-Extra: notion
+Requires-Dist: backoff; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
-Requires-Dist: backoff; extra == "notion"
 Requires-Dist: httpx; extra == "notion"
 Provides-Extra: onedrive
-Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Requires-Dist: msal; extra == "onedrive"
 Requires-Dist: bs4; extra == "onedrive"
+Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Provides-Extra: opensearch
 Requires-Dist: opensearch-py; extra == "opensearch"
 Provides-Extra: outlook
-Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
 Requires-Dist: msal; extra == "outlook"
+Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
 Provides-Extra: pinecone
 Requires-Dist: pinecone-client>=3.7.1; extra == "pinecone"
 Provides-Extra: postgres
@@ -155,18 +155,18 @@ Provides-Extra: s3
 Requires-Dist: fsspec; extra == "s3"
 Requires-Dist: s3fs; extra == "s3"
 Provides-Extra: sharepoint
-Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
 Requires-Dist: msal; extra == "sharepoint"
+Requires-Dist: Office365-REST-Python-Client; 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[optional]; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python; extra == "snowflake"
 Requires-Dist: psycopg2-binary; extra == "snowflake"
+Requires-Dist: snowflake-connector-python; extra == "snowflake"
 Provides-Extra: wikipedia
 Requires-Dist: wikipedia; extra == "wikipedia"
 Provides-Extra: weaviate
@@ -182,9 +182,9 @@ Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"
 Requires-Dist: httpx; extra == "vectara"
 Provides-Extra: vastdb
-Requires-Dist: vastdb; extra == "vastdb"
-Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: ibis; extra == "vastdb"
+Requires-Dist: pyarrow; extra == "vastdb"
+Requires-Dist: vastdb; extra == "vastdb"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
@@ -200,8 +200,8 @@ Provides-Extra: openai
 Requires-Dist: openai; extra == "openai"
 Requires-Dist: tiktoken; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"
+Requires-Dist: aioboto3; extra == "bedrock"
 Provides-Extra: togetherai
 Requires-Dist: together; extra == "togetherai"
 Dynamic: author

unstructured_ingest-0.5.5/test/integration/connectors/test_sharepoint.py

@@ -0,0 +1,222 @@
+import os
+
+import pytest
+
+from test.integration.connectors.utils.constants import BLOB_STORAGE_TAG, SOURCE_TAG
+from test.integration.connectors.utils.validation.source import (
+    SourceValidationConfigs,
+    source_connector_validation,
+)
+from test.integration.utils import requires_env
+from unstructured_ingest.v2.processes.connectors.sharepoint import (
+    CONNECTOR_TYPE,
+    SharepointAccessConfig,
+    SharepointConnectionConfig,
+    SharepointDownloader,
+    SharepointDownloaderConfig,
+    SharepointIndexer,
+    SharepointIndexerConfig,
+)
+
+
+def sharepoint_config():
+    class SharepointTestConfig:
+        def __init__(self):
+            self.client_id = os.environ["SHAREPOINT_CLIENT_ID"]
+            self.client_cred = os.environ["SHAREPOINT_CRED"]
+            self.user_pname = os.environ["MS_USER_PNAME"]
+            self.tenant = os.environ["MS_TENANT_ID"]
+
+    return SharepointTestConfig()
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG, BLOB_STORAGE_TAG)
+@requires_env("SHAREPOINT_CLIENT_ID", "SHAREPOINT_CRED", "MS_TENANT_ID", "MS_USER_PNAME")
+async def test_sharepoint_source(temp_dir):
+    site = "https://unstructuredio.sharepoint.com/sites/utic-platform-test-source"
+    config = sharepoint_config()
+
+    # Create connection and indexer configurations
+    access_config = SharepointAccessConfig(client_cred=config.client_cred)
+    connection_config = SharepointConnectionConfig(
+        client_id=config.client_id,
+        site=site,
+        tenant=config.tenant,
+        user_pname=config.user_pname,
+        access_config=access_config,
+    )
+    index_config = SharepointIndexerConfig(recursive=True)
+
+    download_config = SharepointDownloaderConfig(download_dir=temp_dir)
+
+    # Instantiate indexer and downloader
+    indexer = SharepointIndexer(
+        connection_config=connection_config,
+        index_config=index_config,
+    )
+    downloader = SharepointDownloader(
+        connection_config=connection_config,
+        download_config=download_config,
+    )
+
+    # Run the source connector validation
+    await source_connector_validation(
+        indexer=indexer,
+        downloader=downloader,
+        configs=SourceValidationConfigs(
+            test_id="sharepoint1",
+            expected_num_files=4,
+            validate_downloaded_files=True,
+            exclude_fields_extend=[
+                "metadata.date_created",
+                "metadata.date_modified",
+                "additional_metadata.LastModified",
+                "additional_metadata.@microsoft.graph.downloadUrl",
+            ],
+        ),
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG, BLOB_STORAGE_TAG)
+@requires_env("SHAREPOINT_CLIENT_ID", "SHAREPOINT_CRED", "MS_TENANT_ID", "MS_USER_PNAME")
+async def test_sharepoint_source_with_path(temp_dir):
+    site = "https://unstructuredio.sharepoint.com/sites/utic-platform-test-source"
+    config = sharepoint_config()
+
+    # Create connection and indexer configurations
+    access_config = SharepointAccessConfig(client_cred=config.client_cred)
+    connection_config = SharepointConnectionConfig(
+        client_id=config.client_id,
+        site=site,
+        tenant=config.tenant,
+        user_pname=config.user_pname,
+        access_config=access_config,
+    )
+    index_config = SharepointIndexerConfig(recursive=True, path="Folder1")
+
+    download_config = SharepointDownloaderConfig(download_dir=temp_dir)
+
+    # Instantiate indexer and downloader
+    indexer = SharepointIndexer(
+        connection_config=connection_config,
+        index_config=index_config,
+    )
+    downloader = SharepointDownloader(
+        connection_config=connection_config,
+        download_config=download_config,
+    )
+
+    # Run the source connector validation
+    await source_connector_validation(
+        indexer=indexer,
+        downloader=downloader,
+        configs=SourceValidationConfigs(
+            test_id="sharepoint2",
+            expected_num_files=2,
+            validate_downloaded_files=True,
+            exclude_fields_extend=[
+                "metadata.date_created",
+                "metadata.date_modified",
+                "additional_metadata.LastModified",
+                "additional_metadata.@microsoft.graph.downloadUrl",
+            ],
+        ),
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG, BLOB_STORAGE_TAG)
+@requires_env("SHAREPOINT_CLIENT_ID", "SHAREPOINT_CRED", "MS_TENANT_ID", "MS_USER_PNAME")
+async def test_sharepoint_root_with_path(temp_dir):
+    site = "https://unstructuredio.sharepoint.com/"
+    config = sharepoint_config()
+
+    # Create connection and indexer configurations
+    access_config = SharepointAccessConfig(client_cred=config.client_cred)
+    connection_config = SharepointConnectionConfig(
+        client_id=config.client_id,
+        site=site,
+        tenant=config.tenant,
+        user_pname=config.user_pname,
+        access_config=access_config,
+    )
+    index_config = SharepointIndexerConfig(recursive=True, path="e2e-test-folder")
+
+    download_config = SharepointDownloaderConfig(download_dir=temp_dir)
+
+    # Instantiate indexer and downloader
+    indexer = SharepointIndexer(
+        connection_config=connection_config,
+        index_config=index_config,
+    )
+    downloader = SharepointDownloader(
+        connection_config=connection_config,
+        download_config=download_config,
+    )
+
+    # Run the source connector validation
+    await source_connector_validation(
+        indexer=indexer,
+        downloader=downloader,
+        configs=SourceValidationConfigs(
+            test_id="sharepoint3",
+            expected_num_files=1,
+            validate_downloaded_files=True,
+            exclude_fields_extend=[
+                "metadata.date_created",
+                "metadata.date_modified",
+                "additional_metadata.LastModified",
+                "additional_metadata.@microsoft.graph.downloadUrl",
+            ],
+        ),
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG, BLOB_STORAGE_TAG)
+@requires_env("SHAREPOINT_CLIENT_ID", "SHAREPOINT_CRED", "MS_TENANT_ID", "MS_USER_PNAME")
+async def test_sharepoint_shared_documents(temp_dir):
+    site = "https://unstructuredio.sharepoint.com/sites/utic-platform-test-source"
+    config = sharepoint_config()
+
+    # Create connection and indexer configurations
+    access_config = SharepointAccessConfig(client_cred=config.client_cred)
+    connection_config = SharepointConnectionConfig(
+        client_id=config.client_id,
+        site=site,
+        tenant=config.tenant,
+        user_pname=config.user_pname,
+        access_config=access_config,
+    )
+    index_config = SharepointIndexerConfig(recursive=True, path="Shared Documents")
+
+    download_config = SharepointDownloaderConfig(download_dir=temp_dir)
+
+    # Instantiate indexer and downloader
+    indexer = SharepointIndexer(
+        connection_config=connection_config,
+        index_config=index_config,
+    )
+    downloader = SharepointDownloader(
+        connection_config=connection_config,
+        download_config=download_config,
+    )
+
+    # Run the source connector validation
+    await source_connector_validation(
+        indexer=indexer,
+        downloader=downloader,
+        configs=SourceValidationConfigs(
+            test_id="sharepoint4",
+            expected_num_files=4,
+            validate_downloaded_files=True,
+            exclude_fields_extend=[
+                "metadata.date_created",
+                "metadata.date_modified",
+                "additional_metadata.LastModified",
+                "additional_metadata.@microsoft.graph.downloadUrl",
+            ],
+        ),
+    )

unstructured_ingest-0.5.5/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.5.5"  # pragma: no cover

{unstructured_ingest-0.5.3 → unstructured_ingest-0.5.5}/unstructured_ingest/v2/processes/connectors/astradb.py

@@ -42,6 +42,7 @@ from unstructured_ingest.v2.processes.connector_registry import (
     DestinationRegistryEntry,
     SourceRegistryEntry,
 )
+from unstructured_ingest.v2.processes.connectors.utils import format_and_truncate_orig_elements
 
 if TYPE_CHECKING:
     from astrapy import AsyncCollection as AstraDBAsyncCollection
@@ -318,6 +319,7 @@ class AstraDBUploadStager(UploadStager):
                 element_dict["metadata"]["text_as_html"] = truncate_string_bytes(
                     text_as_html, MAX_CONTENT_PARAM_BYTE_SIZE
                 )
+            metadata["original_elements"] = format_and_truncate_orig_elements(element_dict)
 
     def conform_dict(self, element_dict: dict, file_data: FileData) -> dict:
         self.truncate_dict_elements(element_dict)

{unstructured_ingest-0.5.3 → unstructured_ingest-0.5.5}/unstructured_ingest/v2/processes/connectors/neo4j.py

@@ -14,7 +14,6 @@ from pydantic import BaseModel, ConfigDict, Field, Secret, field_validator
 
 from unstructured_ingest.error import DestinationConnectionError
 from unstructured_ingest.logger import logger
-from unstructured_ingest.utils.chunking import elements_from_base64_gzipped_json
 from unstructured_ingest.utils.data_prep import batch_generator
 from unstructured_ingest.utils.dep_check import requires_dependencies
 from unstructured_ingest.v2.interfaces import (
@@ -29,6 +28,7 @@ from unstructured_ingest.v2.interfaces import (
 from unstructured_ingest.v2.processes.connector_registry import (
     DestinationRegistryEntry,
 )
+from unstructured_ingest.v2.processes.connectors.utils import format_and_truncate_orig_elements
 
 SimilarityFunction = Literal["cosine"]
 
@@ -132,7 +132,7 @@ class Neo4jUploadStager(UploadStager):
             if self._is_chunk(element):
                 origin_element_nodes = [
                     self._create_element_node(origin_element)
-                    for origin_element in self._get_origin_elements(element)
+                    for origin_element in format_and_truncate_orig_elements(element)
                 ]
                 graph.add_edges_from(
                     [
@@ -166,7 +166,11 @@ class Neo4jUploadStager(UploadStager):
         return _Node(id_=file_data.identifier, properties=properties, labels=[Label.DOCUMENT])
 
     def _create_element_node(self, element: dict) -> _Node:
-        properties = {"id": element["element_id"], "text": element["text"]}
+        properties = {"id": element["element_id"]}
+
+        if text := element.get("text"):
+            # if we have chunks, we won't have text here for the original elements
+            properties["text"] = text
 
         if embeddings := element.get("embeddings"):
             properties["embeddings"] = embeddings
@@ -174,10 +178,6 @@ class Neo4jUploadStager(UploadStager):
         label = Label.CHUNK if self._is_chunk(element) else Label.UNSTRUCTURED_ELEMENT
         return _Node(id_=element["element_id"], properties=properties, labels=[label])
 
-    def _get_origin_elements(self, chunk_element: dict) -> list[dict]:
-        orig_elements = chunk_element.get("metadata", {}).get("orig_elements")
-        return elements_from_base64_gzipped_json(raw_s=orig_elements)
-
 
 class _GraphData(BaseModel):
     nodes: list[_Node]

{unstructured_ingest-0.5.3 → unstructured_ingest-0.5.5}/unstructured_ingest/v2/processes/connectors/sharepoint.py

@@ -31,6 +31,7 @@ if TYPE_CHECKING:
     from office365.onedrive.driveitems.driveItem import DriveItem
 
 CONNECTOR_TYPE = "sharepoint"
+LEGACY_DEFAULT_PATH = "Shared Documents"
 
 
 class SharepointAccessConfig(OnedriveAccessConfig):
@@ -76,10 +77,14 @@ class SharepointIndexer(OnedriveIndexer):
         except ClientRequestException:
             logger.info("Site not found")
 
-        drive_items = await self.list_objects(
-            folder=site_drive_item, recursive=self.index_config.recursive
-        )
-        for drive_item in drive_items:
+        path = self.index_config.path
+        # Deprecated sharepoint sdk needed a default path. Microsoft Graph SDK does not.
+        if path and path != LEGACY_DEFAULT_PATH:
+            site_drive_item = site_drive_item.get_by_path(path).get().execute_query()
+
+        for drive_item in site_drive_item.get_files(
+            recursive=self.index_config.recursive
+        ).execute_query():
             file_data = await self.drive_item_to_file_data(drive_item=drive_item)
             yield file_data
 

unstructured_ingest-0.5.5/unstructured_ingest/v2/processes/connectors/utils.py

@@ -0,0 +1,57 @@
+import json
+from datetime import datetime
+from typing import Any, Union
+
+from dateutil import parser
+from pydantic import ValidationError
+
+from unstructured_ingest.utils.chunking import elements_from_base64_gzipped_json
+
+
+def parse_datetime(date_value: Union[int, str, float, datetime]) -> datetime:
+    if isinstance(date_value, datetime):
+        return date_value
+    elif isinstance(date_value, float):
+        return datetime.fromtimestamp(date_value)
+    elif isinstance(date_value, int):
+        return datetime.fromtimestamp(date_value / 1000)
+
+    try:
+        timestamp = float(date_value)
+        return datetime.fromtimestamp(timestamp)
+    except ValueError:
+        return parser.parse(date_value)
+
+
+def conform_string_to_dict(value: Any) -> dict:
+    if isinstance(value, dict):
+        return value
+    if isinstance(value, str):
+        return json.loads(value)
+    raise ValidationError(f"Input could not be mapped to a valid dict: {value}")
+
+
+def format_and_truncate_orig_elements(element: dict) -> list[dict[str, Any]]:
+    """
+    This function is used to format and truncate the orig_elements field in the metadata.
+    This is used to remove the text field and other larger fields from the orig_elements
+    that are not helpful in filtering/searching when used along with chunked elements.
+    """
+    metadata = element.get("metadata", {})
+    raw_orig_elements = metadata.get("orig_elements", None)
+    orig_elements = []
+    if raw_orig_elements is not None:
+        for element in elements_from_base64_gzipped_json(raw_orig_elements):
+            element.pop("text", None)
+            for prop in (
+                "image_base64",
+                "text_as_html",
+                "table_as_cells",
+                "link_urls",
+                "link_texts",
+                "link_start_indexes",
+                "emphasized_text_contents",
+            ):
+                element["metadata"].pop(prop, None)
+            orig_elements.append(element)
+    return orig_elements

{unstructured_ingest-0.5.3 → unstructured_ingest-0.5.5/unstructured_ingest.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.5.3
+Version: 0.5.5
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,13 +22,13 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: python-dateutil
-Requires-Dist: opentelemetry-sdk
-Requires-Dist: tqdm
-Requires-Dist: pandas
 Requires-Dist: click
-Requires-Dist: pydantic>=2.7
+Requires-Dist: pandas
+Requires-Dist: tqdm
 Requires-Dist: dataclasses_json
+Requires-Dist: pydantic>=2.7
+Requires-Dist: opentelemetry-sdk
+Requires-Dist: python-dateutil
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.26.1; extra == "remote"
 Provides-Extra: csv
@@ -66,13 +66,13 @@ Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
 Requires-Dist: astrapy; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: fsspec; extra == "azure"
+Requires-Dist: adlfs; extra == "azure"
 Provides-Extra: azure-ai-search
 Requires-Dist: azure-search-documents; extra == "azure-ai-search"
 Provides-Extra: biomed
-Requires-Dist: requests; extra == "biomed"
 Requires-Dist: bs4; extra == "biomed"
+Requires-Dist: requests; extra == "biomed"
 Provides-Extra: box
 Requires-Dist: fsspec; extra == "box"
 Requires-Dist: boxfs; extra == "box"
@@ -86,8 +86,8 @@ Requires-Dist: requests; extra == "confluence"
 Provides-Extra: couchbase
 Requires-Dist: couchbase; extra == "couchbase"
 Provides-Extra: delta-table
-Requires-Dist: deltalake; extra == "delta-table"
 Requires-Dist: boto3; extra == "delta-table"
+Requires-Dist: deltalake; extra == "delta-table"
 Provides-Extra: discord
 Requires-Dist: discord.py; extra == "discord"
 Provides-Extra: dropbox
@@ -98,19 +98,19 @@ Requires-Dist: duckdb; extra == "duckdb"
 Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
-Requires-Dist: gcsfs; extra == "gcs"
-Requires-Dist: fsspec; extra == "gcs"
 Requires-Dist: bs4; extra == "gcs"
+Requires-Dist: fsspec; extra == "gcs"
+Requires-Dist: gcsfs; extra == "gcs"
 Provides-Extra: github
-Requires-Dist: pygithub>1.58.0; extra == "github"
 Requires-Dist: requests; extra == "github"
+Requires-Dist: pygithub>1.58.0; extra == "github"
 Provides-Extra: gitlab
 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
@@ -125,22 +125,22 @@ Provides-Extra: mongodb
 Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: neo4j
 Requires-Dist: cymple; extra == "neo4j"
-Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Requires-Dist: networkx; extra == "neo4j"
+Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Provides-Extra: notion
+Requires-Dist: backoff; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
-Requires-Dist: backoff; extra == "notion"
 Requires-Dist: httpx; extra == "notion"
 Provides-Extra: onedrive
-Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Requires-Dist: msal; extra == "onedrive"
 Requires-Dist: bs4; extra == "onedrive"
+Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Provides-Extra: opensearch
 Requires-Dist: opensearch-py; extra == "opensearch"
 Provides-Extra: outlook
-Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
 Requires-Dist: msal; extra == "outlook"
+Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
 Provides-Extra: pinecone
 Requires-Dist: pinecone-client>=3.7.1; extra == "pinecone"
 Provides-Extra: postgres
@@ -155,18 +155,18 @@ Provides-Extra: s3
 Requires-Dist: fsspec; extra == "s3"
 Requires-Dist: s3fs; extra == "s3"
 Provides-Extra: sharepoint
-Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
 Requires-Dist: msal; extra == "sharepoint"
+Requires-Dist: Office365-REST-Python-Client; 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[optional]; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python; extra == "snowflake"
 Requires-Dist: psycopg2-binary; extra == "snowflake"
+Requires-Dist: snowflake-connector-python; extra == "snowflake"
 Provides-Extra: wikipedia
 Requires-Dist: wikipedia; extra == "wikipedia"
 Provides-Extra: weaviate
@@ -182,9 +182,9 @@ Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"
 Requires-Dist: httpx; extra == "vectara"
 Provides-Extra: vastdb
-Requires-Dist: vastdb; extra == "vastdb"
-Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: ibis; extra == "vastdb"
+Requires-Dist: pyarrow; extra == "vastdb"
+Requires-Dist: vastdb; extra == "vastdb"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
@@ -200,8 +200,8 @@ Provides-Extra: openai
 Requires-Dist: openai; extra == "openai"
 Requires-Dist: tiktoken; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"
+Requires-Dist: aioboto3; extra == "bedrock"
 Provides-Extra: togetherai
 Requires-Dist: together; extra == "togetherai"
 Dynamic: author