unstructured-ingest 0.7.0__tar.gz → 0.7.2__tar.gz

unstructured_ingest-0.7.2/MANIFEST.in

@@ -0,0 +1,2 @@
+# Connector specific assets
+include unstructured_ingest/processes/connectors/assets/*

{unstructured_ingest-0.7.0/unstructured_ingest.egg-info → unstructured_ingest-0.7.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.7.0
+Version: 0.7.2
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,12 +22,12 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
+Requires-Dist: click
+Requires-Dist: pydantic>=2.7
+Requires-Dist: opentelemetry-sdk
 Requires-Dist: tqdm
 Requires-Dist: python-dateutil
-Requires-Dist: click
 Requires-Dist: dataclasses_json
-Requires-Dist: opentelemetry-sdk
-Requires-Dist: pydantic>=2.7
 Requires-Dist: numpy
 Requires-Dist: pandas
 Provides-Extra: remote
@@ -103,8 +103,8 @@ Requires-Dist: astrapy; extra == "astradb"
 Requires-Dist: numpy; extra == "astradb"
 Requires-Dist: pandas; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: fsspec; extra == "azure"
+Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: numpy; extra == "azure"
 Requires-Dist: pandas; extra == "azure"
 Provides-Extra: azure-ai-search
@@ -139,8 +139,8 @@ Requires-Dist: couchbase; extra == "couchbase"
 Requires-Dist: numpy; extra == "couchbase"
 Requires-Dist: pandas; extra == "couchbase"
 Provides-Extra: delta-table
-Requires-Dist: boto3; extra == "delta-table"
 Requires-Dist: deltalake; extra == "delta-table"
+Requires-Dist: boto3; extra == "delta-table"
 Requires-Dist: numpy; extra == "delta-table"
 Requires-Dist: pandas; extra == "delta-table"
 Provides-Extra: discord
@@ -148,8 +148,8 @@ Requires-Dist: discord.py; extra == "discord"
 Requires-Dist: numpy; extra == "discord"
 Requires-Dist: pandas; extra == "discord"
 Provides-Extra: dropbox
-Requires-Dist: dropboxdrivefs; extra == "dropbox"
 Requires-Dist: fsspec; extra == "dropbox"
+Requires-Dist: dropboxdrivefs; extra == "dropbox"
 Requires-Dist: numpy; extra == "dropbox"
 Requires-Dist: pandas; extra == "dropbox"
 Provides-Extra: duckdb
@@ -161,9 +161,9 @@ Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Requires-Dist: numpy; extra == "elasticsearch"
 Requires-Dist: pandas; extra == "elasticsearch"
 Provides-Extra: gcs
+Requires-Dist: fsspec; extra == "gcs"
 Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: gcsfs; extra == "gcs"
-Requires-Dist: fsspec; extra == "gcs"
 Requires-Dist: numpy; extra == "gcs"
 Requires-Dist: pandas; extra == "gcs"
 Provides-Extra: github
@@ -180,15 +180,15 @@ Requires-Dist: google-api-python-client; extra == "google-drive"
 Requires-Dist: numpy; extra == "google-drive"
 Requires-Dist: pandas; extra == "google-drive"
 Provides-Extra: hubspot
-Requires-Dist: hubspot-api-client; extra == "hubspot"
 Requires-Dist: urllib3; extra == "hubspot"
+Requires-Dist: hubspot-api-client; extra == "hubspot"
 Requires-Dist: numpy; extra == "hubspot"
 Requires-Dist: pandas; extra == "hubspot"
 Provides-Extra: ibm-watsonx-s3
 Requires-Dist: pyiceberg; extra == "ibm-watsonx-s3"
 Requires-Dist: tenacity; extra == "ibm-watsonx-s3"
-Requires-Dist: httpx; extra == "ibm-watsonx-s3"
 Requires-Dist: pyarrow; extra == "ibm-watsonx-s3"
+Requires-Dist: httpx; extra == "ibm-watsonx-s3"
 Requires-Dist: numpy; extra == "ibm-watsonx-s3"
 Requires-Dist: pandas; extra == "ibm-watsonx-s3"
 Provides-Extra: jira
@@ -216,22 +216,22 @@ Requires-Dist: pymongo; extra == "mongodb"
 Requires-Dist: numpy; extra == "mongodb"
 Requires-Dist: pandas; extra == "mongodb"
 Provides-Extra: neo4j
-Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: cymple; extra == "neo4j"
+Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Requires-Dist: numpy; extra == "neo4j"
 Requires-Dist: pandas; extra == "neo4j"
 Provides-Extra: notion
-Requires-Dist: backoff; extra == "notion"
-Requires-Dist: htmlBuilder; 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: numpy; extra == "notion"
 Requires-Dist: pandas; extra == "notion"
 Provides-Extra: onedrive
-Requires-Dist: bs4; extra == "onedrive"
-Requires-Dist: msal; extra == "onedrive"
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
+Requires-Dist: msal; extra == "onedrive"
+Requires-Dist: requests; extra == "onedrive"
 Requires-Dist: numpy; extra == "onedrive"
 Requires-Dist: pandas; extra == "onedrive"
 Provides-Extra: opensearch
@@ -239,8 +239,8 @@ Requires-Dist: opensearch-py; extra == "opensearch"
 Requires-Dist: numpy; extra == "opensearch"
 Requires-Dist: pandas; extra == "opensearch"
 Provides-Extra: outlook
-Requires-Dist: msal; extra == "outlook"
 Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
+Requires-Dist: msal; extra == "outlook"
 Requires-Dist: numpy; extra == "outlook"
 Requires-Dist: pandas; extra == "outlook"
 Provides-Extra: pinecone
@@ -269,8 +269,9 @@ Requires-Dist: s3fs; extra == "s3"
 Requires-Dist: numpy; extra == "s3"
 Requires-Dist: pandas; extra == "s3"
 Provides-Extra: sharepoint
-Requires-Dist: msal; extra == "sharepoint"
 Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
+Requires-Dist: msal; extra == "sharepoint"
+Requires-Dist: requests; extra == "sharepoint"
 Requires-Dist: numpy; extra == "sharepoint"
 Requires-Dist: pandas; extra == "sharepoint"
 Provides-Extra: salesforce
@@ -278,8 +279,8 @@ Requires-Dist: simple-salesforce; extra == "salesforce"
 Requires-Dist: numpy; extra == "salesforce"
 Requires-Dist: pandas; extra == "salesforce"
 Provides-Extra: sftp
-Requires-Dist: paramiko; extra == "sftp"
 Requires-Dist: fsspec; extra == "sftp"
+Requires-Dist: paramiko; extra == "sftp"
 Requires-Dist: numpy; extra == "sftp"
 Requires-Dist: pandas; extra == "sftp"
 Provides-Extra: slack
@@ -287,8 +288,8 @@ Requires-Dist: slack_sdk[optional]; extra == "slack"
 Requires-Dist: numpy; extra == "slack"
 Requires-Dist: pandas; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: snowflake-connector-python; extra == "snowflake"
+Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: numpy; extra == "snowflake"
 Requires-Dist: pandas; extra == "snowflake"
 Provides-Extra: wikipedia
@@ -312,21 +313,21 @@ Requires-Dist: singlestoredb; extra == "singlestore"
 Requires-Dist: numpy; extra == "singlestore"
 Requires-Dist: pandas; extra == "singlestore"
 Provides-Extra: vectara
-Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: httpx; extra == "vectara"
+Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"
 Requires-Dist: numpy; extra == "vectara"
 Requires-Dist: pandas; extra == "vectara"
 Provides-Extra: vastdb
 Requires-Dist: ibis; extra == "vastdb"
-Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: vastdb; extra == "vastdb"
+Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: numpy; extra == "vastdb"
 Requires-Dist: pandas; extra == "vastdb"
 Provides-Extra: zendesk
+Requires-Dist: aiofiles; extra == "zendesk"
 Requires-Dist: bs4; extra == "zendesk"
 Requires-Dist: httpx; extra == "zendesk"
-Requires-Dist: aiofiles; extra == "zendesk"
 Requires-Dist: numpy; extra == "zendesk"
 Requires-Dist: pandas; extra == "zendesk"
 Provides-Extra: embed-huggingface
@@ -356,8 +357,8 @@ Requires-Dist: tiktoken; extra == "openai"
 Requires-Dist: numpy; extra == "openai"
 Requires-Dist: pandas; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: boto3; extra == "bedrock"
 Requires-Dist: aioboto3; extra == "bedrock"
+Requires-Dist: boto3; extra == "bedrock"
 Requires-Dist: numpy; extra == "bedrock"
 Requires-Dist: pandas; extra == "bedrock"
 Provides-Extra: togetherai

unstructured_ingest-0.7.2/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.7.2"  # pragma: no cover

unstructured_ingest-0.7.2/unstructured_ingest/logger.py

@@ -0,0 +1,39 @@
+import logging
+
+logger = logging.getLogger("unstructured_ingest")
+
+
+def remove_root_handlers(logger: logging.Logger) -> None:
+    # NOTE(robinson): in some environments such as Google Colab, there is a root handler
+    # that doesn't not mask secrets, meaning sensitive info such as api keys appear in logs.
+    # Removing these when they exist prevents this behavior
+    if logger.root.hasHandlers():
+        for handler in logger.root.handlers:
+            logger.root.removeHandler(handler)
+
+
+def ingest_log_streaming_init(level: int) -> None:
+    handler = logging.StreamHandler()
+    handler.name = "ingest_log_handler"
+    formatter = logging.Formatter("%(asctime)s %(processName)-10s %(levelname)-8s %(message)s")
+    handler.setFormatter(formatter)
+
+    # Only want to add the handler once
+    if "ingest_log_handler" not in [h.name for h in logger.handlers]:
+        logger.addHandler(handler)
+
+    remove_root_handlers(logger)
+    logger.setLevel(level)
+
+
+def make_default_logger(level: int) -> logging.Logger:
+    """Return a custom logger."""
+    logger = logging.getLogger("unstructured_ingest")
+    handler = logging.StreamHandler()
+    handler.name = "ingest_log_handler"
+    formatter = logging.Formatter("%(asctime)s %(processName)-10s %(levelname)-8s %(message)s")
+    handler.setFormatter(formatter)
+    logger.addHandler(handler)
+    logger.setLevel(level)
+    remove_root_handlers(logger)
+    return logger

unstructured_ingest-0.7.2/unstructured_ingest/processes/connectors/assets/databricks_delta_table_schema.sql

@@ -0,0 +1,10 @@
+CREATE TABLE elements (
+    id STRING NOT NULL PRIMARY KEY,
+    record_id STRING NOT NULL,
+    element_id STRING NOT NULL,
+    text STRING,
+    embeddings ARRAY<FLOAT>,
+    type STRING,
+    metadata VARIANT
+);
+

unstructured_ingest-0.7.2/unstructured_ingest/processes/connectors/assets/weaviate_collection_config.json

@@ -0,0 +1,23 @@
+{
+    "properties": [
+        {
+            "dataType": [
+                "text"
+            ],
+            "indexFilterable": true,
+            "indexSearchable": true,
+            "name": "record_id",
+            "tokenization": "word"
+        },
+        {
+            "dataType": [
+                "text"
+            ],
+            "indexFilterable": true,
+            "indexSearchable": true,
+            "name": "text",
+            "tokenization": "word"
+        }
+    ],
+    "vectorizer": "none"
+}

{unstructured_ingest-0.7.0 → unstructured_ingest-0.7.2}/unstructured_ingest/processes/connectors/onedrive.py

@@ -53,11 +53,14 @@ MAX_BYTES_SIZE = 512_000_000
 
 class OnedriveAccessConfig(AccessConfig):
     client_cred: str = Field(description="Microsoft App client secret")
+    password: Optional[str] = Field(description="Service account password", default=None)
 
 
 class OnedriveConnectionConfig(ConnectionConfig):
     client_id: str = Field(description="Microsoft app client ID")
-    user_pname: str = Field(description="User principal name, usually is your Azure AD email.")
+    user_pname: str = Field(
+        description="User principal name or service account, usually your Azure AD email."
+    )
     tenant: str = Field(
         repr=False, description="ID or domain name associated with your Azure AD instance"
     )
@@ -74,25 +77,50 @@ class OnedriveConnectionConfig(ConnectionConfig):
         drive = client.users[self.user_pname].drive
         return drive
 
-    @requires_dependencies(["msal"], extras="onedrive")
+    @requires_dependencies(["msal", "requests"], extras="onedrive")
     def get_token(self):
         from msal import ConfidentialClientApplication
+        from requests import post
+
+        if self.access_config.get_secret_value().password:
+            url = f"https://login.microsoftonline.com/{self.tenant}/oauth2/v2.0/token"
+            headers = {"Content-Type": "application/x-www-form-urlencoded"}
+            data = {
+                "grant_type": "password",
+                "username": self.user_pname,
+                "password": self.access_config.get_secret_value().password,
+                "client_id": self.client_id,
+                "client_secret": self.access_config.get_secret_value().client_cred,
+                "scope": "https://graph.microsoft.com/.default",
+            }
+            response = post(url, headers=headers, data=data)
+            if response.status_code == 200:
+                return response.json()
+            else:
+                raise SourceConnectionError(
+                    f"Oauth2 authentication failed with {response.status_code}: {response.text}"
+                )
 
-        try:
-            app = ConfidentialClientApplication(
-                authority=f"{self.authority_url}/{self.tenant}",
-                client_id=self.client_id,
-                client_credential=self.access_config.get_secret_value().client_cred,
-            )
-            token = app.acquire_token_for_client(scopes=["https://graph.microsoft.com/.default"])
-        except ValueError as exc:
-            logger.error("Couldn't set up credentials for OneDrive")
-            raise exc
-        if "error" in token:
-            raise SourceConnectionNetworkError(
-                "failed to fetch token, {}: {}".format(token["error"], token["error_description"])
-            )
-        return token
+        else:
+            try:
+                app = ConfidentialClientApplication(
+                    authority=f"{self.authority_url}/{self.tenant}",
+                    client_id=self.client_id,
+                    client_credential=self.access_config.get_secret_value().client_cred,
+                )
+                token = app.acquire_token_for_client(
+                    scopes=["https://graph.microsoft.com/.default"]
+                )
+            except ValueError as exc:
+                logger.error("Couldn't set up credentials.")
+                raise exc
+            if "error" in token:
+                raise SourceConnectionNetworkError(
+                    "failed to fetch token, {}: {}".format(
+                        token["error"], token["error_description"]
+                    )
+                )
+            return token
 
     @requires_dependencies(["office365"], extras="onedrive")
     def get_client(self) -> "GraphClient":

{unstructured_ingest-0.7.0 → unstructured_ingest-0.7.2}/unstructured_ingest/processes/connectors/sharepoint.py

@@ -100,7 +100,7 @@ class SharepointDownloader(OnedriveDownloader):
     connector_type: str = CONNECTOR_TYPE
 
     @SourceConnectionNetworkError.wrap
-    @requires_dependencies(["office365"], extras="onedrive")
+    @requires_dependencies(["office365"], extras="sharepoint")
     def _fetch_file(self, file_data: FileData) -> DriveItem:
         from office365.runtime.client_request_exception import ClientRequestException
 

{unstructured_ingest-0.7.0 → unstructured_ingest-0.7.2}/unstructured_ingest/utils/string_and_date_utils.py

@@ -1,14 +1,14 @@
 import json
 import re
-import typing as t
 from datetime import datetime
+from typing import Any, Union
 
 from dateutil import parser
 
 from unstructured_ingest.logger import logger
 
 
-def json_to_dict(json_string: str) -> t.Union[str, t.Dict[str, t.Any]]:
+def json_to_dict(json_string: str) -> Union[str, dict[str, Any]]:
     """Helper function attempts to deserialize json string to a dictionary."""
     try:
         return json.loads(json_string)
@@ -24,7 +24,7 @@ def json_to_dict(json_string: str) -> t.Union[str, t.Dict[str, t.Any]]:
     return json_string
 
 
-def ensure_isoformat_datetime(timestamp: t.Union[datetime, str]) -> str:
+def ensure_isoformat_datetime(timestamp: Union[datetime, str]) -> str:
     """
     Ensures that the input value is converted to an ISO format datetime string.
     Handles both datetime objects and strings.

{unstructured_ingest-0.7.0 → unstructured_ingest-0.7.2/unstructured_ingest.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.7.0
+Version: 0.7.2
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,12 +22,12 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
+Requires-Dist: click
+Requires-Dist: pydantic>=2.7
+Requires-Dist: opentelemetry-sdk
 Requires-Dist: tqdm
 Requires-Dist: python-dateutil
-Requires-Dist: click
 Requires-Dist: dataclasses_json
-Requires-Dist: opentelemetry-sdk
-Requires-Dist: pydantic>=2.7
 Requires-Dist: numpy
 Requires-Dist: pandas
 Provides-Extra: remote
@@ -103,8 +103,8 @@ Requires-Dist: astrapy; extra == "astradb"
 Requires-Dist: numpy; extra == "astradb"
 Requires-Dist: pandas; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: fsspec; extra == "azure"
+Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: numpy; extra == "azure"
 Requires-Dist: pandas; extra == "azure"
 Provides-Extra: azure-ai-search
@@ -139,8 +139,8 @@ Requires-Dist: couchbase; extra == "couchbase"
 Requires-Dist: numpy; extra == "couchbase"
 Requires-Dist: pandas; extra == "couchbase"
 Provides-Extra: delta-table
-Requires-Dist: boto3; extra == "delta-table"
 Requires-Dist: deltalake; extra == "delta-table"
+Requires-Dist: boto3; extra == "delta-table"
 Requires-Dist: numpy; extra == "delta-table"
 Requires-Dist: pandas; extra == "delta-table"
 Provides-Extra: discord
@@ -148,8 +148,8 @@ Requires-Dist: discord.py; extra == "discord"
 Requires-Dist: numpy; extra == "discord"
 Requires-Dist: pandas; extra == "discord"
 Provides-Extra: dropbox
-Requires-Dist: dropboxdrivefs; extra == "dropbox"
 Requires-Dist: fsspec; extra == "dropbox"
+Requires-Dist: dropboxdrivefs; extra == "dropbox"
 Requires-Dist: numpy; extra == "dropbox"
 Requires-Dist: pandas; extra == "dropbox"
 Provides-Extra: duckdb
@@ -161,9 +161,9 @@ Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Requires-Dist: numpy; extra == "elasticsearch"
 Requires-Dist: pandas; extra == "elasticsearch"
 Provides-Extra: gcs
+Requires-Dist: fsspec; extra == "gcs"
 Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: gcsfs; extra == "gcs"
-Requires-Dist: fsspec; extra == "gcs"
 Requires-Dist: numpy; extra == "gcs"
 Requires-Dist: pandas; extra == "gcs"
 Provides-Extra: github
@@ -180,15 +180,15 @@ Requires-Dist: google-api-python-client; extra == "google-drive"
 Requires-Dist: numpy; extra == "google-drive"
 Requires-Dist: pandas; extra == "google-drive"
 Provides-Extra: hubspot
-Requires-Dist: hubspot-api-client; extra == "hubspot"
 Requires-Dist: urllib3; extra == "hubspot"
+Requires-Dist: hubspot-api-client; extra == "hubspot"
 Requires-Dist: numpy; extra == "hubspot"
 Requires-Dist: pandas; extra == "hubspot"
 Provides-Extra: ibm-watsonx-s3
 Requires-Dist: pyiceberg; extra == "ibm-watsonx-s3"
 Requires-Dist: tenacity; extra == "ibm-watsonx-s3"
-Requires-Dist: httpx; extra == "ibm-watsonx-s3"
 Requires-Dist: pyarrow; extra == "ibm-watsonx-s3"
+Requires-Dist: httpx; extra == "ibm-watsonx-s3"
 Requires-Dist: numpy; extra == "ibm-watsonx-s3"
 Requires-Dist: pandas; extra == "ibm-watsonx-s3"
 Provides-Extra: jira
@@ -216,22 +216,22 @@ Requires-Dist: pymongo; extra == "mongodb"
 Requires-Dist: numpy; extra == "mongodb"
 Requires-Dist: pandas; extra == "mongodb"
 Provides-Extra: neo4j
-Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: cymple; extra == "neo4j"
+Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Requires-Dist: numpy; extra == "neo4j"
 Requires-Dist: pandas; extra == "neo4j"
 Provides-Extra: notion
-Requires-Dist: backoff; extra == "notion"
-Requires-Dist: htmlBuilder; 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: numpy; extra == "notion"
 Requires-Dist: pandas; extra == "notion"
 Provides-Extra: onedrive
-Requires-Dist: bs4; extra == "onedrive"
-Requires-Dist: msal; extra == "onedrive"
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
+Requires-Dist: msal; extra == "onedrive"
+Requires-Dist: requests; extra == "onedrive"
 Requires-Dist: numpy; extra == "onedrive"
 Requires-Dist: pandas; extra == "onedrive"
 Provides-Extra: opensearch
@@ -239,8 +239,8 @@ Requires-Dist: opensearch-py; extra == "opensearch"
 Requires-Dist: numpy; extra == "opensearch"
 Requires-Dist: pandas; extra == "opensearch"
 Provides-Extra: outlook
-Requires-Dist: msal; extra == "outlook"
 Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
+Requires-Dist: msal; extra == "outlook"
 Requires-Dist: numpy; extra == "outlook"
 Requires-Dist: pandas; extra == "outlook"
 Provides-Extra: pinecone
@@ -269,8 +269,9 @@ Requires-Dist: s3fs; extra == "s3"
 Requires-Dist: numpy; extra == "s3"
 Requires-Dist: pandas; extra == "s3"
 Provides-Extra: sharepoint
-Requires-Dist: msal; extra == "sharepoint"
 Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
+Requires-Dist: msal; extra == "sharepoint"
+Requires-Dist: requests; extra == "sharepoint"
 Requires-Dist: numpy; extra == "sharepoint"
 Requires-Dist: pandas; extra == "sharepoint"
 Provides-Extra: salesforce
@@ -278,8 +279,8 @@ Requires-Dist: simple-salesforce; extra == "salesforce"
 Requires-Dist: numpy; extra == "salesforce"
 Requires-Dist: pandas; extra == "salesforce"
 Provides-Extra: sftp
-Requires-Dist: paramiko; extra == "sftp"
 Requires-Dist: fsspec; extra == "sftp"
+Requires-Dist: paramiko; extra == "sftp"
 Requires-Dist: numpy; extra == "sftp"
 Requires-Dist: pandas; extra == "sftp"
 Provides-Extra: slack
@@ -287,8 +288,8 @@ Requires-Dist: slack_sdk[optional]; extra == "slack"
 Requires-Dist: numpy; extra == "slack"
 Requires-Dist: pandas; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: snowflake-connector-python; extra == "snowflake"
+Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: numpy; extra == "snowflake"
 Requires-Dist: pandas; extra == "snowflake"
 Provides-Extra: wikipedia
@@ -312,21 +313,21 @@ Requires-Dist: singlestoredb; extra == "singlestore"
 Requires-Dist: numpy; extra == "singlestore"
 Requires-Dist: pandas; extra == "singlestore"
 Provides-Extra: vectara
-Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: httpx; extra == "vectara"
+Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"
 Requires-Dist: numpy; extra == "vectara"
 Requires-Dist: pandas; extra == "vectara"
 Provides-Extra: vastdb
 Requires-Dist: ibis; extra == "vastdb"
-Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: vastdb; extra == "vastdb"
+Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: numpy; extra == "vastdb"
 Requires-Dist: pandas; extra == "vastdb"
 Provides-Extra: zendesk
+Requires-Dist: aiofiles; extra == "zendesk"
 Requires-Dist: bs4; extra == "zendesk"
 Requires-Dist: httpx; extra == "zendesk"
-Requires-Dist: aiofiles; extra == "zendesk"
 Requires-Dist: numpy; extra == "zendesk"
 Requires-Dist: pandas; extra == "zendesk"
 Provides-Extra: embed-huggingface
@@ -356,8 +357,8 @@ Requires-Dist: tiktoken; extra == "openai"
 Requires-Dist: numpy; extra == "openai"
 Requires-Dist: pandas; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: boto3; extra == "bedrock"
 Requires-Dist: aioboto3; extra == "bedrock"
+Requires-Dist: boto3; extra == "bedrock"
 Requires-Dist: numpy; extra == "bedrock"
 Requires-Dist: pandas; extra == "bedrock"
 Provides-Extra: togetherai

{unstructured_ingest-0.7.0 → unstructured_ingest-0.7.2}/unstructured_ingest.egg-info/SOURCES.txt

@@ -107,7 +107,6 @@ test/unit/__init__.py
 test/unit/test_error.py
 test/unit/test_html.py
 test/unit/test_interfaces.py
-test/unit/test_logger.py
 test/unit/test_utils.py
 test/unit/chunkers/__init__.py
 test/unit/chunkers/test_chunkers.py
@@ -234,6 +233,8 @@ unstructured_ingest/processes/connectors/slack.py
 unstructured_ingest/processes/connectors/utils.py
 unstructured_ingest/processes/connectors/vectara.py
 unstructured_ingest/processes/connectors/assets/__init__.py
+unstructured_ingest/processes/connectors/assets/databricks_delta_table_schema.sql
+unstructured_ingest/processes/connectors/assets/weaviate_collection_config.json
 unstructured_ingest/processes/connectors/databricks/__init__.py
 unstructured_ingest/processes/connectors/databricks/volumes.py
 unstructured_ingest/processes/connectors/databricks/volumes_aws.py