unstructured-ingest 0.5.0__py3-none-any.whl → 0.5.1__py3-none-any.whl

test/integration/connectors/sql/test_vastdb.py

@@ -0,0 +1,34 @@
+from pathlib import Path
+
+import pytest
+from _pytest.fixtures import TopRequest
+
+from test.integration.connectors.utils.constants import DESTINATION_TAG, SQL_TAG
+from test.integration.connectors.utils.validation.destination import (
+    StagerValidationConfigs,
+    stager_validation,
+)
+from unstructured_ingest.v2.processes.connectors.sql.vastdb import (
+    CONNECTOR_TYPE,
+    VastdbUploadStager,
+    VastdbUploadStagerConfig,
+)
+
+
+@pytest.mark.tags(CONNECTOR_TYPE, DESTINATION_TAG, SQL_TAG)
+@pytest.mark.parametrize("upload_file_str", ["upload_file_ndjson", "upload_file"])
+def test_vast_stager(
+    request: TopRequest,
+    upload_file_str: str,
+    tmp_path: Path,
+):
+    upload_file: Path = request.getfixturevalue(upload_file_str)
+    stager = VastdbUploadStager(
+        upload_stager_config=VastdbUploadStagerConfig(rename_columns_map={"page_number": "page"})
+    )
+    stager_validation(
+        configs=StagerValidationConfigs(test_id=CONNECTOR_TYPE, expected_count=22),
+        input_file=upload_file,
+        stager=stager,
+        tmp_dir=tmp_path,
+    )

test/integration/connectors/test_google_drive.py

@@ -0,0 +1,116 @@
+import os
+
+import pytest
+
+from test.integration.connectors.utils.constants import (
+    SOURCE_TAG,
+    UNCATEGORIZED_TAG,
+)
+from test.integration.connectors.utils.validation.source import (
+    SourceValidationConfigs,
+    get_all_file_data,
+    run_all_validations,
+    update_fixtures,
+)
+from test.integration.utils import requires_env
+from unstructured_ingest.v2.interfaces import Downloader, Indexer
+from unstructured_ingest.v2.processes.connectors.google_drive import (
+    CONNECTOR_TYPE,
+    GoogleDriveAccessConfig,
+    GoogleDriveConnectionConfig,
+    GoogleDriveDownloader,
+    GoogleDriveDownloaderConfig,
+    GoogleDriveIndexer,
+    GoogleDriveIndexerConfig,
+)
+
+
+@requires_env("GOOGLE_DRIVE_SERVICE_KEY")
+@pytest.mark.tags(SOURCE_TAG, CONNECTOR_TYPE)
+def test_google_drive_source(temp_dir):
+    # Retrieve environment variables
+    service_account_key = os.environ["GOOGLE_DRIVE_SERVICE_KEY"]
+
+    # Create connection and indexer configurations
+    access_config = GoogleDriveAccessConfig(service_account_key=service_account_key)
+    connection_config = GoogleDriveConnectionConfig(
+        drive_id="1XidSOO76VpZ4m0i3gJN2m1X0Obol3UAi",
+        access_config=access_config,
+    )
+    index_config = GoogleDriveIndexerConfig(recursive=True)
+
+    download_config = GoogleDriveDownloaderConfig(download_dir=temp_dir)
+
+    # Instantiate indexer and downloader
+    indexer = GoogleDriveIndexer(
+        connection_config=connection_config,
+        index_config=index_config,
+    )
+    downloader = GoogleDriveDownloader(
+        connection_config=connection_config,
+        download_config=download_config,
+    )
+
+    # Run the source connector validation
+    source_connector_validation(
+        indexer=indexer,
+        downloader=downloader,
+        configs=SourceValidationConfigs(
+            test_id="google_drive_source",
+            expected_num_files=1,
+            validate_downloaded_files=True,
+        ),
+    )
+
+
+@pytest.mark.tags(SOURCE_TAG, CONNECTOR_TYPE, UNCATEGORIZED_TAG)
+def source_connector_validation(
+    indexer: Indexer,
+    downloader: Downloader,
+    configs: SourceValidationConfigs,
+    overwrite_fixtures: bool = os.getenv("OVERWRITE_FIXTURES", "False").lower() == "true",
+) -> None:
+    # Run common validations on the process of running a source connector, supporting dynamic
+    # validators that get passed in along with comparisons on the saved expected values.
+    # If overwrite_fixtures is st to True, will ignore all validators but instead overwrite the
+    # expected values with what gets generated by this test.
+    all_predownload_file_data = []
+    all_postdownload_file_data = []
+    indexer.precheck()
+    download_dir = downloader.download_config.download_dir
+    test_output_dir = configs.test_output_dir()
+
+    for file_data in indexer.run():
+        assert file_data
+        predownload_file_data = file_data.model_copy(deep=True)
+        all_predownload_file_data.append(predownload_file_data)
+        resp = downloader.run(file_data=file_data)
+        if isinstance(resp, list):
+            for r in resp:
+                postdownload_file_data = r["file_data"].model_copy(deep=True)
+                all_postdownload_file_data.append(postdownload_file_data)
+        else:
+            postdownload_file_data = resp["file_data"].model_copy(deep=True)
+            all_postdownload_file_data.append(postdownload_file_data)
+
+    if not overwrite_fixtures:
+        print("Running validation")
+        run_all_validations(
+            configs=configs,
+            predownload_file_data=all_predownload_file_data,
+            postdownload_file_data=all_postdownload_file_data,
+            download_dir=download_dir,
+            test_output_dir=test_output_dir,
+        )
+    else:
+        print("Running fixtures update")
+        update_fixtures(
+            output_dir=test_output_dir,
+            download_dir=download_dir,
+            all_file_data=get_all_file_data(
+                all_predownload_file_data=all_predownload_file_data,
+                all_postdownload_file_data=all_postdownload_file_data,
+            ),
+            save_downloads=configs.validate_downloaded_files,
+            save_filedata=configs.validate_file_data,
+        )

test/unit/v2/connectors/motherduck/test_base.py

@@ -0,0 +1,74 @@
+from pathlib import Path
+
+import pytest
+from pytest_mock import MockerFixture
+
+from unstructured_ingest.v2.interfaces import FileData
+from unstructured_ingest.v2.interfaces.file_data import SourceIdentifiers
+from unstructured_ingest.v2.interfaces.upload_stager import UploadStagerConfig
+from unstructured_ingest.v2.processes.connectors.duckdb.base import BaseDuckDBUploadStager
+
+
+@pytest.fixture
+def mock_instance() -> BaseDuckDBUploadStager:
+    return BaseDuckDBUploadStager(UploadStagerConfig())
+
+
+@pytest.mark.parametrize(
+    ("input_filepath", "output_filename", "expected"),
+    [
+        (
+            "/path/to/input_file.ndjson",
+            "output_file.ndjson",
+            "output_file.ndjson",
+        ),
+        ("input_file.txt", "output_file.json", "output_file.txt"),
+        ("/path/to/input_file.json", "output_file", "output_file.json"),
+    ],
+)
+def test_run_output_filename_suffix(
+    mocker: MockerFixture,
+    mock_instance: BaseDuckDBUploadStager,
+    input_filepath: str,
+    output_filename: str,
+    expected: str,
+):
+    output_dir = Path("/tmp/test/output_dir")
+
+    # Mocks
+    mock_get_data = mocker.patch(
+        "unstructured_ingest.v2.processes.connectors.duckdb.base.get_data",
+        return_value=[{"key": "value"}, {"key": "value2"}],
+    )
+    mock_conform_dict = mocker.patch.object(
+        BaseDuckDBUploadStager,
+        "conform_dict",
+        side_effect=lambda element_dict, file_data: element_dict,
+    )
+    mock_get_output_path = mocker.patch.object(
+        BaseDuckDBUploadStager, "get_output_path", return_value=output_dir / expected
+    )
+    mock_write_output = mocker.patch(
+        "unstructured_ingest.v2.processes.connectors.duckdb.base.write_data", return_value=None
+    )
+
+    # Act
+    result = mock_instance.run(
+        elements_filepath=Path(input_filepath),
+        file_data=FileData(
+            identifier="test",
+            connector_type="test",
+            source_identifiers=SourceIdentifiers(filename=input_filepath, fullpath=input_filepath),
+        ),
+        output_dir=output_dir,
+        output_filename=output_filename,
+    )
+
+    # Assert
+    mock_get_data.assert_called_once_with(path=Path(input_filepath))
+    assert mock_conform_dict.call_count == 2
+    mock_get_output_path.assert_called_once_with(output_filename=expected, output_dir=output_dir)
+    mock_write_output.assert_called_once_with(
+        path=output_dir / expected, data=[{"key": "value"}, {"key": "value2"}]
+    )
+    assert result.name == expected

unstructured_ingest/__version__.py

@@ -1 +1 @@
-__version__ = "0.5.0"  # pragma: no cover
+__version__ = "0.5.1"  # pragma: no cover

unstructured_ingest/v2/processes/connectors/duckdb/base.py

@@ -81,6 +81,8 @@ class BaseDuckDBUploadStager(UploadStager):
         **kwargs: Any,
     ) -> Path:
         elements_contents = get_data(path=elements_filepath)
+        output_filename_suffix = Path(elements_filepath).suffix
+        output_filename = f"{Path(output_filename).stem}{output_filename_suffix}"
         output_path = self.get_output_path(output_filename=output_filename, output_dir=output_dir)
 
         output = [

unstructured_ingest/v2/processes/connectors/duckdb/motherduck.py

@@ -61,7 +61,7 @@ class MotherDuckConnectionConfig(ConnectionConfig):
                 "custom_user_agent": f"unstructured-io-ingest/{unstructured_io_ingest_version}"
             },
         ) as conn:
-            conn.sql(f"USE {self.database}")
+            conn.sql(f'USE "{self.database}"')
             yield conn
 
     @contextmanager
@@ -102,11 +102,12 @@ class MotherDuckUploader(Uploader):
 
     def upload_dataframe(self, df: pd.DataFrame) -> None:
         logger.debug(f"uploading {len(df)} entries to {self.connection_config.database} ")
+        database = self.connection_config.database
+        db_schema = self.connection_config.db_schema
+        table = self.connection_config.table
 
         with self.connection_config.get_client() as conn:
-            conn.query(
-                f"INSERT INTO {self.connection_config.db_schema}.{self.connection_config.table} BY NAME SELECT * FROM df"  # noqa: E501
-            )
+            conn.query(f'INSERT INTO "{database}"."{db_schema}"."{table}" BY NAME SELECT * FROM df')
 
     def run_data(self, data: list[dict], file_data: FileData, **kwargs: Any) -> None:
         df = pd.DataFrame(data=data)

unstructured_ingest/v2/processes/connectors/google_drive.py

@@ -310,20 +310,22 @@ class GoogleDriveDownloader(Downloader):
         from googleapiclient.http import MediaIoBaseDownload
 
         logger.debug(f"fetching file: {file_data.source_identifiers.fullpath}")
-        mime_type = file_data.additional_metadata["mimeType"]
         record_id = file_data.identifier
+        mime_type = file_data.additional_metadata["mimeType"]
+        if not mime_type:
+            raise TypeError(
+                f"File not supported. Name: {file_data.source_identifiers.filename} "
+                f"ID: {record_id} "
+                f"MimeType: {mime_type}"
+            )
         with self.connection_config.get_client() as client:
-            if mime_type.startswith("application/vnd.google-apps"):
+            if (
+                mime_type.startswith("application/vnd.google-apps")
+                and mime_type in GOOGLE_DRIVE_EXPORT_TYPES
+            ):
                 export_mime = GOOGLE_DRIVE_EXPORT_TYPES.get(
-                    self.meta.get("mimeType"),  # type: ignore
+                    mime_type,  # type: ignore
                 )
-                if not export_mime:
-                    raise TypeError(
-                        f"File not supported. Name: {file_data.source_identifiers.filename} "
-                        f"ID: {record_id} "
-                        f"MimeType: {mime_type}"
-                    )
-
                 request = client.export_media(
                     fileId=record_id,
                     mimeType=export_mime,

unstructured_ingest/v2/processes/connectors/pinecone.py

@@ -81,6 +81,7 @@ ALLOWED_FIELDS = (
     "link_urls",
     "link_texts",
     "text_as_html",
+    "entities",
 )
 
 

unstructured_ingest/v2/processes/connectors/sql/sql.py

@@ -38,48 +38,6 @@ from unstructured_ingest.v2.interfaces import (
 from unstructured_ingest.v2.logger import logger
 from unstructured_ingest.v2.utils import get_enhanced_element_id
 
-_COLUMNS = (
-    "id",
-    "element_id",
-    "text",
-    "embeddings",
-    "type",
-    "system",
-    "layout_width",
-    "layout_height",
-    "points",
-    "url",
-    "version",
-    "date_created",
-    "date_modified",
-    "date_processed",
-    "permissions_data",
-    "record_locator",
-    "category_depth",
-    "parent_id",
-    "attached_filename",
-    "filetype",
-    "last_modified",
-    "file_directory",
-    "filename",
-    "languages",
-    "page_number",
-    "links",
-    "page_name",
-    "link_urls",
-    "link_texts",
-    "sent_from",
-    "sent_to",
-    "subject",
-    "section",
-    "header_footer_type",
-    "emphasized_text_contents",
-    "emphasized_text_tags",
-    "text_as_html",
-    "regex_metadata",
-    "detection_class_prob",
-)
-
 _DATE_COLUMNS = ("date_created", "date_modified", "date_processed", "last_modified")
 
 
@@ -270,10 +228,8 @@ class SQLUploadStager(UploadStager):
 
         data["id"] = get_enhanced_element_id(element_dict=data, file_data=file_data)
 
-        # remove extraneous, not supported columns
-        element = {k: v for k, v in data.items() if k in _COLUMNS}
-        element[RECORD_ID_LABEL] = file_data.identifier
-        return element
+        data[RECORD_ID_LABEL] = file_data.identifier
+        return data
 
     def conform_dataframe(self, df: pd.DataFrame) -> pd.DataFrame:
         for column in filter(lambda x: x in df.columns, _DATE_COLUMNS):
@@ -375,7 +331,7 @@ class SQLUploader(Uploader):
         missing_columns = schema_fields - columns
 
         if columns_to_drop:
-            logger.warning(
+            logger.info(
                 "Following columns will be dropped to match the table's schema: "
                 f"{', '.join(columns_to_drop)}"
             )

unstructured_ingest/v2/processes/connectors/sql/vastdb.py

@@ -19,7 +19,6 @@ from unstructured_ingest.v2.processes.connector_registry import (
     SourceRegistryEntry,
 )
 from unstructured_ingest.v2.processes.connectors.sql.sql import (
-    _COLUMNS,
     SQLAccessConfig,
     SqlBatchFileData,
     SQLConnectionConfig,
@@ -149,13 +148,11 @@ class VastdbUploadStagerConfig(SQLUploadStagerConfig):
         default=None,
         description="Map of column names to rename, ex: {'old_name': 'new_name'}",
     )
-    additional_columns: Optional[list[str]] = Field(
-        default_factory=list, description="Additional columns to include in the upload"
-    )
 
 
+@dataclass
 class VastdbUploadStager(SQLUploadStager):
-    upload_stager_config: VastdbUploadStagerConfig
+    upload_stager_config: VastdbUploadStagerConfig = field(default_factory=VastdbUploadStagerConfig)
 
     def conform_dict(self, element_dict: dict, file_data: FileData) -> dict:
         data = element_dict.copy()
@@ -168,13 +165,8 @@ class VastdbUploadStager(SQLUploadStager):
         data.update(coordinates)
 
         data["id"] = get_enhanced_element_id(element_dict=data, file_data=file_data)
-
-        # remove extraneous, not supported columns
-        # but also allow for additional columns
-        approved_columns = set(_COLUMNS).union(self.upload_stager_config.additional_columns)
-        element = {k: v for k, v in data.items() if k in approved_columns}
-        element[RECORD_ID_LABEL] = file_data.identifier
-        return element
+        data[RECORD_ID_LABEL] = file_data.identifier
+        return data
 
     def conform_dataframe(self, df: pd.DataFrame) -> pd.DataFrame:
         df = super().conform_dataframe(df=df)

{unstructured_ingest-0.5.0.dist-info → unstructured_ingest-0.5.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unstructured-ingest
-Version: 0.5.0
+Version: 0.5.1
 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: pandas
 Requires-Dist: dataclasses-json
-Requires-Dist: pydantic>=2.7
 Requires-Dist: click
-Requires-Dist: tqdm
-Requires-Dist: python-dateutil
 Requires-Dist: opentelemetry-sdk
+Requires-Dist: pydantic>=2.7
+Requires-Dist: python-dateutil
+Requires-Dist: pandas
+Requires-Dist: tqdm
 Provides-Extra: airtable
 Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
@@ -52,8 +52,8 @@ Requires-Dist: chromadb; extra == "chroma"
 Provides-Extra: clarifai
 Requires-Dist: clarifai; extra == "clarifai"
 Provides-Extra: confluence
-Requires-Dist: requests; extra == "confluence"
 Requires-Dist: atlassian-python-api; extra == "confluence"
+Requires-Dist: requests; extra == "confluence"
 Provides-Extra: couchbase
 Requires-Dist: couchbase; extra == "couchbase"
 Provides-Extra: csv
@@ -63,8 +63,8 @@ Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
 Provides-Extra: databricks-volumes
 Requires-Dist: databricks-sdk; extra == "databricks-volumes"
 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: doc
@@ -83,8 +83,8 @@ Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-mixedbreadai
 Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
 Provides-Extra: embed-octoai
-Requires-Dist: tiktoken; extra == "embed-octoai"
 Requires-Dist: openai; extra == "embed-octoai"
+Requires-Dist: tiktoken; extra == "embed-octoai"
 Provides-Extra: embed-vertexai
 Requires-Dist: vertexai; extra == "embed-vertexai"
 Provides-Extra: embed-voyageai
@@ -96,8 +96,8 @@ 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"
 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
@@ -122,23 +122,23 @@ Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: msg
 Requires-Dist: unstructured[msg]; extra == "msg"
 Provides-Extra: neo4j
-Requires-Dist: networkx; extra == "neo4j"
-Requires-Dist: cymple; extra == "neo4j"
 Requires-Dist: neo4j; extra == "neo4j"
+Requires-Dist: cymple; extra == "neo4j"
+Requires-Dist: networkx; extra == "neo4j"
 Provides-Extra: notion
-Requires-Dist: httpx; extra == "notion"
 Requires-Dist: backoff; extra == "notion"
-Requires-Dist: notion-client; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
+Requires-Dist: httpx; extra == "notion"
+Requires-Dist: notion-client; extra == "notion"
 Provides-Extra: odt
 Requires-Dist: unstructured[odt]; extra == "odt"
 Provides-Extra: onedrive
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
-Requires-Dist: bs4; extra == "onedrive"
 Requires-Dist: msal; extra == "onedrive"
+Requires-Dist: bs4; extra == "onedrive"
 Provides-Extra: openai
-Requires-Dist: tiktoken; extra == "openai"
 Requires-Dist: openai; extra == "openai"
+Requires-Dist: tiktoken; extra == "openai"
 Provides-Extra: opensearch
 Requires-Dist: opensearch-py; extra == "opensearch"
 Provides-Extra: org
@@ -169,8 +169,8 @@ Requires-Dist: unstructured[rst]; extra == "rst"
 Provides-Extra: rtf
 Requires-Dist: unstructured[rtf]; extra == "rtf"
 Provides-Extra: s3
-Requires-Dist: s3fs; extra == "s3"
 Requires-Dist: fsspec; extra == "s3"
+Requires-Dist: s3fs; extra == "s3"
 Provides-Extra: salesforce
 Requires-Dist: simple-salesforce; extra == "salesforce"
 Provides-Extra: sftp
@@ -184,16 +184,16 @@ Requires-Dist: singlestoredb; extra == "singlestore"
 Provides-Extra: slack
 Requires-Dist: slack-sdk[optional]; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: snowflake-connector-python; extra == "snowflake"
+Requires-Dist: psycopg2-binary; extra == "snowflake"
 Provides-Extra: togetherai
 Requires-Dist: together; extra == "togetherai"
 Provides-Extra: tsv
 Requires-Dist: unstructured[tsv]; extra == "tsv"
 Provides-Extra: vastdb
+Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: vastdb; extra == "vastdb"
 Requires-Dist: ibis; extra == "vastdb"
-Requires-Dist: pyarrow; extra == "vastdb"
 Provides-Extra: vectara
 Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"

{unstructured_ingest-0.5.0.dist-info → unstructured_ingest-0.5.1.dist-info}/RECORD

@@ -10,6 +10,7 @@ test/integration/connectors/test_azure_ai_search.py,sha256=MxFwk84vI_HT4taQTGrNp
 test/integration/connectors/test_chroma.py,sha256=NuQv0PWPM0_LQfdPeUd6IYKqaKKXWmVaHGWjq5aBfOY,3721
 test/integration/connectors/test_confluence.py,sha256=Ju0gRQbD2g9l9iRf2HDZKi7RyPnBGtFRWcGpsqhO3F8,3588
 test/integration/connectors/test_delta_table.py,sha256=4qm2Arfc9Eb7SOZOnOlLF-vNpHy6Eqvr5Q45svfX1PY,6911
+test/integration/connectors/test_google_drive.py,sha256=0zJZ4UJOq4TkfU-bkc556_abV7q6zVS9ZgIvW9qcTU4,4204
 test/integration/connectors/test_lancedb.py,sha256=8MBxK_CUtOt87-4B7svDDK82NFII5psceo5cNN8HJMs,9228
 test/integration/connectors/test_milvus.py,sha256=7mI6zznN0PTxDL9DLogH1k3dxx6R8DgGzlpyevsFu2w,7173
 test/integration/connectors/test_mongodb.py,sha256=0A6DvF-iTCSZzOefisd_i20j9li8uNWTF2wyLGwlhco,12446
@@ -40,6 +41,7 @@ test/integration/connectors/sql/test_postgres.py,sha256=bGDyzLRpgrXO7nl0U8nF2zSN
 test/integration/connectors/sql/test_singlestore.py,sha256=XeU2s4Kt_3tGyaDYYKTgYjdOyb8j2dnz4TgSMwFUjWs,6153
 test/integration/connectors/sql/test_snowflake.py,sha256=LEwsRDoC6-rRiwYsqeo5B9Eo6RYygLLGAUsrtrgI9pM,7494
 test/integration/connectors/sql/test_sqlite.py,sha256=MHvhFRx1y_LTgfS-aPz-Zn9yOGsm-TF_s0t1seBzV1k,5956
+test/integration/connectors/sql/test_vastdb.py,sha256=66T-o_y7NaDKGmKFkT778AB-nanlLv9KdtgUGPOdnLs,1069
 test/integration/connectors/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/integration/connectors/utils/constants.py,sha256=JhTk6YNw7JVpkk-Pl8zn2YYkExeL1oE9VBWm_kMYGfo,369
 test/integration/connectors/utils/docker.py,sha256=4g1STiSbYN5qcmDTXyPxVJgwx97O6wk7n-DJ-zgzgag,4971
@@ -87,6 +89,8 @@ test/unit/v2/connectors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG
 test/unit/v2/connectors/test_confluence.py,sha256=bXrn_kRb4IQdqkk4rc-P2gJAtPba7n7pNplQgfbqZDY,1047
 test/unit/v2/connectors/databricks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/unit/v2/connectors/databricks/test_volumes_table.py,sha256=-R_EJHqv1BseGRK9VRAZhF-2EXA64LAlhycoyIu556U,1078
+test/unit/v2/connectors/motherduck/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+test/unit/v2/connectors/motherduck/test_base.py,sha256=f3W7hppEZ904_I_fKax-5LVDp-0yj04DjF1ccZ4k5O8,2503
 test/unit/v2/connectors/sql/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/unit/v2/connectors/sql/test_sql.py,sha256=51-AKUBxw6ThO68bjenLopUUuxM88YZb2rMUV8L6YwY,2464
 test/unit/v2/embedders/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -103,7 +107,7 @@ test/unit/v2/partitioners/test_partitioner.py,sha256=iIYg7IpftV3LusoO4H8tr1IHY1U
 test/unit/v2/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/unit/v2/utils/data_generator.py,sha256=UoYVNjG4S4wlaA9gceQ82HIpF9_6I1UTHD1_GrQBHp0,973
 unstructured_ingest/__init__.py,sha256=U4S_2y3zgLZVfMenHRaJFBW8yqh2mUBuI291LGQVOJ8,35
-unstructured_ingest/__version__.py,sha256=A09Ks7MDqP-QtYP9TIQMxydOZeCTtu9i7xoq5wdy4As,42
+unstructured_ingest/__version__.py,sha256=LXdgOM6QWErpDu1oCqJrypfmAkBaXzRxVPcjHL8yPrI,42
 unstructured_ingest/error.py,sha256=qDncnJgbf5ils956RcO2CGlAKYDT5OaEM9Clv1JVTNc,1448
 unstructured_ingest/interfaces.py,sha256=7DOnDpGvUNlCoFR7UPRGmOarqH5sFtuUOO5vf8X3oTM,31489
 unstructured_ingest/logger.py,sha256=S5nSqGcABoQyeicgRnBQFjDScCaTvFVivOCvbo-laL0,4479
@@ -428,7 +432,7 @@ unstructured_ingest/v2/processes/connectors/couchbase.py,sha256=i7vuNKsUkN93JRVm
 unstructured_ingest/v2/processes/connectors/delta_table.py,sha256=SotSXZQ85_6TO906YvFi3yTml8jE9A_zV6nBJ4oTx8A,7075
 unstructured_ingest/v2/processes/connectors/discord.py,sha256=-e4-cBK4TnHkknK1qIb86AIVMy81lBgC288_iLpTzM8,5246
 unstructured_ingest/v2/processes/connectors/gitlab.py,sha256=ufE65Z8q_tC4oppGg5BsGXwSaL7RbEXcaagJQYsylNo,9984
-unstructured_ingest/v2/processes/connectors/google_drive.py,sha256=5k7pdAzJGXSdyPCzW9vu2OaAjGVTo2JevDyGaXM1Hvk,13370
+unstructured_ingest/v2/processes/connectors/google_drive.py,sha256=tSbyibwm9RQyXD-HJGZa1Y9lBSCXaEFnvxpf6bHwBSE,13394
 unstructured_ingest/v2/processes/connectors/kdbai.py,sha256=VRDAiou_7oWOIAgQTdOGQWxudzQEDopXM8XkfkQ2j6g,5004
 unstructured_ingest/v2/processes/connectors/local.py,sha256=ZvWTj6ZYkwnvQMNFsZWoaQyp9zp0WVqAywMaHJ2kcAc,7153
 unstructured_ingest/v2/processes/connectors/milvus.py,sha256=wmcu9NVy3gYlQGT25inN5w_QrhFoL8-hRq0pJFSNw8g,8866
@@ -436,7 +440,7 @@ unstructured_ingest/v2/processes/connectors/mongodb.py,sha256=cL0QUQZF_s2brh3nNN
 unstructured_ingest/v2/processes/connectors/neo4j.py,sha256=HU1IwchTM7Q1kkeIFVe-Lg6gInMItBpgkDkVwuTvkGY,14259
 unstructured_ingest/v2/processes/connectors/onedrive.py,sha256=EM9fq67RsiudZvZbi6nDXkS-i6W0xLvbkNvD0G-Ni5E,17779
 unstructured_ingest/v2/processes/connectors/outlook.py,sha256=KgNGM8hImRhy6_SpswRP2VwRD4VOrqqJoySgxf2oduI,9290
-unstructured_ingest/v2/processes/connectors/pinecone.py,sha256=bQDCch7OGiQgpWO3n3ncLuQ4XCWqDc7ZWEB-Qrqkss8,10730
+unstructured_ingest/v2/processes/connectors/pinecone.py,sha256=U5gSa8S08JvCwmAhE8aV0yxGTIFnUlKVsQDybE8Fqb8,10746
 unstructured_ingest/v2/processes/connectors/redisdb.py,sha256=p0AY4ukBNpwAemV4bWzpScvVbLTVlI3DzsCNUKiBI5M,6757
 unstructured_ingest/v2/processes/connectors/salesforce.py,sha256=2CiO2ZZiZ1Y1-nB7wcDlDVcpW2B7ut9wCj66rkkqho0,11616
 unstructured_ingest/v2/processes/connectors/sharepoint.py,sha256=f0F7KioXgucVc3tVASTa67ynlTa4s9_FKGPHop6Xm0A,4563
@@ -453,9 +457,9 @@ unstructured_ingest/v2/processes/connectors/databricks/volumes_gcp.py,sha256=tR8
 unstructured_ingest/v2/processes/connectors/databricks/volumes_native.py,sha256=dJLD1fueXf8_0AfC4cg0G7siJZVefz68iuEx2Kq7rMs,2890
 unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py,sha256=2KNLwDZJDhsMAUGCzktEIn4Lvb0nxLWabBOPJbgyoEE,5010
 unstructured_ingest/v2/processes/connectors/duckdb/__init__.py,sha256=5sVvJCWhU-YkjHIwk4W6BZCanFYK5W4xTpWtQ8xzeB4,561
-unstructured_ingest/v2/processes/connectors/duckdb/base.py,sha256=0YBdOpTX5mbRLhP00lRHSMpl2-LfuRpqB1XPMJMxn04,2647
+unstructured_ingest/v2/processes/connectors/duckdb/base.py,sha256=IHaY1mWuidt6GDEJhB1c_orwmjeyXuRCVJ88djYDciM,2793
 unstructured_ingest/v2/processes/connectors/duckdb/duckdb.py,sha256=oUHHaLpO2pWW2Lu4Mc-XFjrA0ze97205WQ_xP95ua4M,4296
-unstructured_ingest/v2/processes/connectors/duckdb/motherduck.py,sha256=mU5x6SnbFgRsVicNGh4y4gtR6ek7eQFinI0dQQmzMds,4481
+unstructured_ingest/v2/processes/connectors/duckdb/motherduck.py,sha256=OsRy-rcrP4_KSustpxlEKoZ_FmJNFMyMmIfFk6WJ3UY,4559
 unstructured_ingest/v2/processes/connectors/elasticsearch/__init__.py,sha256=Zzc0JNPP-eFqpwWw1Gp-XC8H-s__IgkYKzoagECycZY,829
 unstructured_ingest/v2/processes/connectors/elasticsearch/elasticsearch.py,sha256=MEKU64OsiQmbLPb3ken-WWCIV6-pnFbs_6kjJweG-SY,18813
 unstructured_ingest/v2/processes/connectors/elasticsearch/opensearch.py,sha256=qRz8Fyr2RSZIPZGkhPeme6AZxM0aX-c_xOa1ZtSr2Kg,6781
@@ -555,17 +559,17 @@ unstructured_ingest/v2/processes/connectors/sql/databricks_delta_tables.py,sha25
 unstructured_ingest/v2/processes/connectors/sql/postgres.py,sha256=BATfX1PQGT2kl8jAbdNKXTojYKJxh3pJV9-h3OBnHGo,5124
 unstructured_ingest/v2/processes/connectors/sql/singlestore.py,sha256=OPBDQ2c_5KjWHEFfqXxf3pQ2tWC-N4MtslMulMgP1Wc,5503
 unstructured_ingest/v2/processes/connectors/sql/snowflake.py,sha256=QE-WBqrPVjCgcxR5EdVD9iTHBjgDSSSQgWYvq5N61qU,7746
-unstructured_ingest/v2/processes/connectors/sql/sql.py,sha256=O2XBu_E2WqNia9OUTdhTWkYo0xhoMMm6ZuanTz-0V9s,16192
+unstructured_ingest/v2/processes/connectors/sql/sql.py,sha256=F5PPUxt2W8JaAQGfz5Od0FvKqYa15RfwMIlnrdJu1nk,15317
 unstructured_ingest/v2/processes/connectors/sql/sqlite.py,sha256=PRjN_S7UQv0k4ZpSyclW1AJrsrugyxbR-GoOrHvBpks,5200
-unstructured_ingest/v2/processes/connectors/sql/vastdb.py,sha256=4DckpVAXpmMTcoKrWiJbnFQQlcrwMA-GMaDsAYchTUs,9992
+unstructured_ingest/v2/processes/connectors/sql/vastdb.py,sha256=0rxrb1ByXIefB9umzMTEJbpvzdTttXHK5DjRY97-GG8,9618
 unstructured_ingest/v2/processes/connectors/weaviate/__init__.py,sha256=NMiwnVWan69KnzVELvaqX34tMhCytIa-C8EDsXVKsEo,856
 unstructured_ingest/v2/processes/connectors/weaviate/cloud.py,sha256=bXtfEYLquR-BszZ5S_lQ4JbETNs9Vozgpfm8x9egAmE,6251
 unstructured_ingest/v2/processes/connectors/weaviate/embedded.py,sha256=S8Zg8StuZT-k7tCg1D5YShO1-vJYYk9-M1bE1fIqx64,3014
 unstructured_ingest/v2/processes/connectors/weaviate/local.py,sha256=LuTBKPseVewsz8VqxRPRLfGEm3BeI9nBZxpy7ZU5tOA,2201
 unstructured_ingest/v2/processes/connectors/weaviate/weaviate.py,sha256=yJza_jBSEFnzZRq5L6vJ0Mm3uS1uxkOiKIimPpUyQds,12418
-unstructured_ingest-0.5.0.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
-unstructured_ingest-0.5.0.dist-info/METADATA,sha256=dyxZ7tfjq1tkZPJgaK6ZanQwB6pteSIznmfUhAgnT64,8051
-unstructured_ingest-0.5.0.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-unstructured_ingest-0.5.0.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
-unstructured_ingest-0.5.0.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
-unstructured_ingest-0.5.0.dist-info/RECORD,,
+unstructured_ingest-0.5.1.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
+unstructured_ingest-0.5.1.dist-info/METADATA,sha256=4fo4K5ac0RNRlWGGyNumZ5gXJf-0PwknZWjS6HvAD6w,8051
+unstructured_ingest-0.5.1.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+unstructured_ingest-0.5.1.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
+unstructured_ingest-0.5.1.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
+unstructured_ingest-0.5.1.dist-info/RECORD,,