unstructured-ingest 0.5.1__py3-none-any.whl → 0.5.2__py3-none-any.whl

test/integration/connectors/test_google_drive.py

@@ -1,6 +1,8 @@
 import os
+import uuid
 
 import pytest
+from googleapiclient.errors import HttpError
 
 from test.integration.connectors.utils.constants import (
     SOURCE_TAG,
@@ -13,6 +15,9 @@ from test.integration.connectors.utils.validation.source import (
     update_fixtures,
 )
 from test.integration.utils import requires_env
+from unstructured_ingest.error import (
+    SourceConnectionError,
+)
 from unstructured_ingest.v2.interfaces import Downloader, Indexer
 from unstructured_ingest.v2.processes.connectors.google_drive import (
     CONNECTOR_TYPE,
@@ -25,6 +30,49 @@ from unstructured_ingest.v2.processes.connectors.google_drive import (
 )
 
 
+@pytest.fixture
+def google_drive_connection_config():
+    """
+    Build a valid GoogleDriveConnectionConfig using the environment variables.
+    Expects:
+      - GOOGLE_DRIVE_ID
+      - GOOGLE_DRIVE_SERVICE_KEY
+    """
+    drive_id = os.getenv("GOOGLE_DRIVE_ID")
+    service_key = os.getenv("GOOGLE_DRIVE_SERVICE_KEY")
+    if not drive_id or not service_key:
+        pytest.skip("Google Drive credentials not provided in environment variables.")
+
+    access_config = GoogleDriveAccessConfig(service_account_key=service_key)
+    return GoogleDriveConnectionConfig(drive_id=drive_id, access_config=access_config)
+
+
+@pytest.fixture
+def google_drive_empty_folder(google_drive_connection_config):
+    """
+    Creates an empty folder on Google Drive for testing the "empty folder" case.
+    The folder is deleted after the test.
+    """
+    from google.oauth2 import service_account
+    from googleapiclient.discovery import build
+
+    access_config = google_drive_connection_config.access_config.get_secret_value()
+    creds = service_account.Credentials.from_service_account_info(access_config.service_account_key)
+    service = build("drive", "v3", credentials=creds)
+
+    # Create an empty folder.
+    file_metadata = {
+        "name": f"utic-empty-folder-{uuid.uuid4()}",
+        "mimeType": "application/vnd.google-apps.folder",
+    }
+    folder = service.files().create(body=file_metadata, fields="id, name").execute()
+    folder_id = folder.get("id")
+    try:
+        yield folder_id
+    finally:
+        service.files().delete(fileId=folder_id).execute()
+
+
 @requires_env("GOOGLE_DRIVE_SERVICE_KEY")
 @pytest.mark.tags(SOURCE_TAG, CONNECTOR_TYPE)
 def test_google_drive_source(temp_dir):
@@ -114,3 +162,96 @@ def source_connector_validation(
             save_downloads=configs.validate_downloaded_files,
             save_filedata=configs.validate_file_data,
         )
+
+
+# Precheck fails when the drive ID has an appended parameter (simulate copy-paste error)
+@pytest.mark.tags("google-drive", "precheck")
+@requires_env("GOOGLE_DRIVE_ID", "GOOGLE_DRIVE_SERVICE_KEY")
+def test_google_drive_precheck_invalid_parameter(google_drive_connection_config):
+    # Append a query parameter as often happens when copying from a URL.
+    invalid_drive_id = google_drive_connection_config.drive_id + "?usp=sharing"
+    connection_config = GoogleDriveConnectionConfig(
+        drive_id=invalid_drive_id,
+        access_config=google_drive_connection_config.access_config,
+    )
+    index_config = GoogleDriveIndexerConfig(recursive=True)
+    indexer = GoogleDriveIndexer(connection_config=connection_config, index_config=index_config)
+    with pytest.raises(SourceConnectionError) as excinfo:
+        indexer.precheck()
+    assert "invalid" in str(excinfo.value).lower() or "not found" in str(excinfo.value).lower()
+
+
+# Precheck fails due to lack of permission (simulate via monkeypatching).
+@pytest.mark.tags("google-drive", "precheck")
+@requires_env("GOOGLE_DRIVE_ID", "GOOGLE_DRIVE_SERVICE_KEY")
+def test_google_drive_precheck_no_permission(google_drive_connection_config, monkeypatch):
+    index_config = GoogleDriveIndexerConfig(recursive=True)
+    indexer = GoogleDriveIndexer(
+        connection_config=google_drive_connection_config,
+        index_config=index_config,
+    )
+
+    # Monkeypatch get_root_info to always raise an HTTP 403 error.
+    def fake_get_root_info(files_client, object_id):
+        raise HttpError(
+            resp=type("Response", (), {"status": 403, "reason": "Forbidden"})(),
+            content=b"Forbidden",
+        )
+
+    monkeypatch.setattr(indexer, "get_root_info", fake_get_root_info)
+    with pytest.raises(SourceConnectionError) as excinfo:
+        indexer.precheck()
+    assert "forbidden" in str(excinfo.value).lower() or "permission" in str(excinfo.value).lower()
+
+
+# Precheck fails when the folder is empty.
+# @pytest.mark.tags("google-drive", "precheck")
+# @requires_env("GOOGLE_DRIVE_ID", "GOOGLE_DRIVE_SERVICE_KEY")
+# def test_google_drive_precheck_empty_folder(
+#     google_drive_connection_config, google_drive_empty_folder
+# ):
+#     # Use the empty folder's ID as the target.
+#     connection_config = GoogleDriveConnectionConfig(
+#         drive_id=google_drive_empty_folder,
+#         access_config=google_drive_connection_config.access_config,
+#     )
+
+#     index_config = GoogleDriveIndexerConfig(recursive=True)
+#     indexer = GoogleDriveIndexer(connection_config=connection_config, index_config=index_config)
+#     with pytest.raises(SourceConnectionError) as excinfo:
+#         indexer.precheck()
+#     assert "empty folder" in str(excinfo.value).lower()
+
+
+@pytest.mark.tags("google-drive", "count", "integration")
+@requires_env("GOOGLE_DRIVE_ID", "GOOGLE_DRIVE_SERVICE_KEY")
+def test_google_drive_count_files(google_drive_connection_config):
+    """
+    This test verifies that the count_files_recursively method returns the expected count of files.
+    According to the test credentials, there are 3 files in the root directory and 1 nested file,
+    so the total count should be 4.
+    """
+    # I assumed that we're applying the same extension filter as with other tests
+    # However there's 6 files in total in the test dir
+    extensions_filter = ["pdf", "docx"]
+    with google_drive_connection_config.get_client() as client:
+        count = GoogleDriveIndexer.count_files_recursively(
+            client, google_drive_connection_config.drive_id, extensions_filter
+        )
+    assert count == 4, f"Expected file count of 4, but got {count}"
+
+
+# Precheck fails with a completely invalid drive ID.
+@pytest.mark.tags("google-drive", "precheck")
+@requires_env("GOOGLE_DRIVE_ID", "GOOGLE_DRIVE_SERVICE_KEY")
+def test_google_drive_precheck_invalid_drive_id(google_drive_connection_config):
+    invalid_drive_id = "invalid_drive_id"
+    connection_config = GoogleDriveConnectionConfig(
+        drive_id=invalid_drive_id,
+        access_config=google_drive_connection_config.access_config,
+    )
+    index_config = GoogleDriveIndexerConfig(recursive=True)
+    indexer = GoogleDriveIndexer(connection_config=connection_config, index_config=index_config)
+    with pytest.raises(SourceConnectionError) as excinfo:
+        indexer.precheck()
+    assert "invalid" in str(excinfo.value).lower() or "not found" in str(excinfo.value).lower()

unstructured_ingest/__version__.py

@@ -1 +1 @@
-__version__ = "0.5.1"  # pragma: no cover
+__version__ = "0.5.2"  # pragma: no cover

unstructured_ingest/embed/bedrock.py

@@ -8,6 +8,7 @@ from typing import TYPE_CHECKING, AsyncIterable
 from pydantic import Field, SecretStr
 
 from unstructured_ingest.embed.interfaces import (
+    EMBEDDINGS_KEY,
     AsyncBaseEmbeddingEncoder,
     BaseEmbeddingEncoder,
     EmbeddingConfig,
@@ -145,9 +146,12 @@ class BedrockEmbeddingEncoder(BaseEmbeddingEncoder):
             return response_body.get("embedding")
 
     def embed_documents(self, elements: list[dict]) -> list[dict]:
-        embeddings = [self.embed_query(query=e.get("text", "")) for e in elements]
-        elements_with_embeddings = self._add_embeddings_to_elements(elements, embeddings)
-        return elements_with_embeddings
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        embeddings = [self.embed_query(query=e["text"]) for e in elements_with_text]
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements
 
 
 @dataclass
@@ -186,8 +190,11 @@ class AsyncBedrockEmbeddingEncoder(AsyncBaseEmbeddingEncoder):
             raise ValueError(f"Error raised by inference endpoint: {e}")
 
     async def embed_documents(self, elements: list[dict]) -> list[dict]:
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
         embeddings = await asyncio.gather(
-            *[self.embed_query(query=e.get("text", "")) for e in elements]
+            *[self.embed_query(query=e.get("text", "")) for e in elements_with_text]
         )
-        elements_with_embeddings = self._add_embeddings_to_elements(elements, embeddings)
-        return elements_with_embeddings
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements

unstructured_ingest/embed/huggingface.py

@@ -3,7 +3,11 @@ from typing import TYPE_CHECKING, Optional
 
 from pydantic import Field
 
-from unstructured_ingest.embed.interfaces import BaseEmbeddingEncoder, EmbeddingConfig
+from unstructured_ingest.embed.interfaces import (
+    EMBEDDINGS_KEY,
+    BaseEmbeddingEncoder,
+    EmbeddingConfig,
+)
 from unstructured_ingest.utils.dep_check import requires_dependencies
 
 if TYPE_CHECKING:
@@ -52,6 +56,9 @@ class HuggingFaceEmbeddingEncoder(BaseEmbeddingEncoder):
         return embeddings.tolist()
 
     def embed_documents(self, elements: list[dict]) -> list[dict]:
-        embeddings = self._embed_documents([e.get("text", "") for e in elements])
-        elements_with_embeddings = self._add_embeddings_to_elements(elements, embeddings)
-        return elements_with_embeddings
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        embeddings = self._embed_documents([e["text"] for e in elements_with_text])
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements

unstructured_ingest/embed/interfaces.py

@@ -6,6 +6,8 @@ from typing import Optional
 import numpy as np
 from pydantic import BaseModel, Field
 
+EMBEDDINGS_KEY = "embeddings"
+
 
 class EmbeddingConfig(BaseModel):
     batch_size: Optional[int] = Field(
@@ -26,27 +28,6 @@ class BaseEncoder(ABC):
         if possible"""
         return e
 
-    @staticmethod
-    def _add_embeddings_to_elements(
-        elements: list[dict], embeddings: list[list[float]]
-    ) -> list[dict]:
-        """
-        Add embeddings to elements.
-
-        Args:
-            elements (list[Element]): List of elements.
-            embeddings (list[list[float]]): List of embeddings.
-
-        Returns:
-            list[Element]: Elements with embeddings added.
-        """
-        assert len(elements) == len(embeddings)
-        elements_w_embedding = []
-        for i, element in enumerate(elements):
-            element["embeddings"] = embeddings[i]
-            elements_w_embedding.append(element)
-        return elements
-
 
 @dataclass
 class BaseEmbeddingEncoder(BaseEncoder, ABC):

unstructured_ingest/embed/mixedbreadai.py

@@ -6,6 +6,7 @@ from typing import TYPE_CHECKING
 from pydantic import Field, SecretStr
 
 from unstructured_ingest.embed.interfaces import (
+    EMBEDDINGS_KEY,
     AsyncBaseEmbeddingEncoder,
     BaseEmbeddingEncoder,
     EmbeddingConfig,
@@ -134,8 +135,12 @@ class MixedbreadAIEmbeddingEncoder(BaseEmbeddingEncoder):
         Returns:
             list[Element]: Elements with embeddings.
         """
-        embeddings = self._embed([e.get("text", "") for e in elements])
-        return self._add_embeddings_to_elements(elements, embeddings)
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        embeddings = self._embed([e["text"] for e in elements_with_text])
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements
 
     def embed_query(self, query: str) -> list[float]:
         """
@@ -209,8 +214,12 @@ class AsyncMixedbreadAIEmbeddingEncoder(AsyncBaseEmbeddingEncoder):
         Returns:
             list[Element]: Elements with embeddings.
         """
-        embeddings = await self._embed([e.get("text", "") for e in elements])
-        return self._add_embeddings_to_elements(elements, embeddings)
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        embeddings = await self._embed([e["text"] for e in elements_with_text])
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements
 
     async def embed_query(self, query: str) -> list[float]:
         """

unstructured_ingest/embed/octoai.py

@@ -4,6 +4,7 @@ from typing import TYPE_CHECKING
 from pydantic import Field, SecretStr
 
 from unstructured_ingest.embed.interfaces import (
+    EMBEDDINGS_KEY,
     AsyncBaseEmbeddingEncoder,
     BaseEmbeddingEncoder,
     EmbeddingConfig,
@@ -89,7 +90,9 @@ class OctoAIEmbeddingEncoder(BaseEmbeddingEncoder):
         return response.data[0].embedding
 
     def embed_documents(self, elements: list[dict]) -> list[dict]:
-        texts = [e.get("text", "") for e in elements]
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        texts = [e["text"] for e in elements_with_text]
         embeddings = []
         client = self.config.get_client()
         try:
@@ -100,8 +103,9 @@ class OctoAIEmbeddingEncoder(BaseEmbeddingEncoder):
                 embeddings.extend([data.embedding for data in response.data])
         except Exception as e:
             raise self.wrap_error(e=e)
-        elements_with_embeddings = self._add_embeddings_to_elements(elements, embeddings)
-        return elements_with_embeddings
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements
 
 
 @dataclass
@@ -122,7 +126,9 @@ class AsyncOctoAIEmbeddingEncoder(AsyncBaseEmbeddingEncoder):
         return response.data[0].embedding
 
     async def embed_documents(self, elements: list[dict]) -> list[dict]:
-        texts = [e.get("text", "") for e in elements]
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        texts = [e["text"] for e in elements_with_text]
         client = self.config.get_async_client()
         embeddings = []
         try:
@@ -133,5 +139,6 @@ class AsyncOctoAIEmbeddingEncoder(AsyncBaseEmbeddingEncoder):
                 embeddings.extend([data.embedding for data in response.data])
         except Exception as e:
             raise self.wrap_error(e=e)
-        elements_with_embeddings = self._add_embeddings_to_elements(elements, embeddings)
-        return elements_with_embeddings
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements

unstructured_ingest/embed/openai.py

@@ -4,6 +4,7 @@ from typing import TYPE_CHECKING
 from pydantic import Field, SecretStr
 
 from unstructured_ingest.embed.interfaces import (
+    EMBEDDINGS_KEY,
     AsyncBaseEmbeddingEncoder,
     BaseEmbeddingEncoder,
     EmbeddingConfig,
@@ -82,7 +83,9 @@ class OpenAIEmbeddingEncoder(BaseEmbeddingEncoder):
 
     def embed_documents(self, elements: list[dict]) -> list[dict]:
         client = self.config.get_client()
-        texts = [e.get("text", "") for e in elements]
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        texts = [e["text"] for e in elements_with_text]
         embeddings = []
         try:
             for batch in batch_generator(texts, batch_size=self.config.batch_size or len(texts)):
@@ -92,8 +95,9 @@ class OpenAIEmbeddingEncoder(BaseEmbeddingEncoder):
                 embeddings.extend([data.embedding for data in response.data])
         except Exception as e:
             raise self.wrap_error(e=e)
-        elements_with_embeddings = self._add_embeddings_to_elements(elements, embeddings)
-        return elements_with_embeddings
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements
 
 
 @dataclass
@@ -115,7 +119,9 @@ class AsyncOpenAIEmbeddingEncoder(AsyncBaseEmbeddingEncoder):
 
     async def embed_documents(self, elements: list[dict]) -> list[dict]:
         client = self.config.get_async_client()
-        texts = [e.get("text", "") for e in elements]
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        texts = [e["text"] for e in elements_with_text]
         embeddings = []
         try:
             for batch in batch_generator(texts, batch_size=self.config.batch_size or len(texts)):
@@ -125,5 +131,6 @@ class AsyncOpenAIEmbeddingEncoder(AsyncBaseEmbeddingEncoder):
                 embeddings.extend([data.embedding for data in response.data])
         except Exception as e:
             raise self.wrap_error(e=e)
-        elements_with_embeddings = self._add_embeddings_to_elements(elements, embeddings)
-        return elements_with_embeddings
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements

unstructured_ingest/embed/togetherai.py

@@ -4,6 +4,7 @@ from typing import TYPE_CHECKING
 from pydantic import Field, SecretStr
 
 from unstructured_ingest.embed.interfaces import (
+    EMBEDDINGS_KEY,
     AsyncBaseEmbeddingEncoder,
     BaseEmbeddingEncoder,
     EmbeddingConfig,
@@ -67,8 +68,12 @@ class TogetherAIEmbeddingEncoder(BaseEmbeddingEncoder):
         return self._embed_documents(elements=[query])[0]
 
     def embed_documents(self, elements: list[dict]) -> list[dict]:
-        embeddings = self._embed_documents([e.get("text", "") for e in elements])
-        return self._add_embeddings_to_elements(elements, embeddings)
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        embeddings = self._embed_documents([e["text"] for e in elements_with_text])
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements
 
     def _embed_documents(self, elements: list[str]) -> list[list[float]]:
         client = self.config.get_client()
@@ -98,8 +103,12 @@ class AsyncTogetherAIEmbeddingEncoder(AsyncBaseEmbeddingEncoder):
         return embedding[0]
 
     async def embed_documents(self, elements: list[dict]) -> list[dict]:
-        embeddings = await self._embed_documents([e.get("text", "") for e in elements])
-        return self._add_embeddings_to_elements(elements, embeddings)
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        embeddings = await self._embed_documents([e["text"] for e in elements_with_text])
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements
 
     async def _embed_documents(self, elements: list[str]) -> list[list[float]]:
         client = self.config.get_async_client()

unstructured_ingest/embed/vertexai.py

@@ -9,6 +9,7 @@ from pydantic import Field, Secret, ValidationError
 from pydantic.functional_validators import BeforeValidator
 
 from unstructured_ingest.embed.interfaces import (
+    EMBEDDINGS_KEY,
     AsyncBaseEmbeddingEncoder,
     BaseEmbeddingEncoder,
     EmbeddingConfig,
@@ -75,9 +76,12 @@ class VertexAIEmbeddingEncoder(BaseEmbeddingEncoder):
         return self._embed_documents(elements=[query])[0]
 
     def embed_documents(self, elements: list[dict]) -> list[dict]:
-        embeddings = self._embed_documents([e.get("text", "") for e in elements])
-        elements_with_embeddings = self._add_embeddings_to_elements(elements, embeddings)
-        return elements_with_embeddings
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        embeddings = self._embed_documents([e["text"] for e in elements_with_text])
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements
 
     @requires_dependencies(
         ["vertexai"],
@@ -110,9 +114,12 @@ class AsyncVertexAIEmbeddingEncoder(AsyncBaseEmbeddingEncoder):
         return embedding[0]
 
     async def embed_documents(self, elements: list[dict]) -> list[dict]:
-        embeddings = await self._embed_documents([e.get("text", "") for e in elements])
-        elements_with_embeddings = self._add_embeddings_to_elements(elements, embeddings)
-        return elements_with_embeddings
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        embeddings = await self._embed_documents([e["text"] for e in elements_with_text])
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements
 
     @requires_dependencies(
         ["vertexai"],

unstructured_ingest/embed/voyageai.py

@@ -4,6 +4,7 @@ from typing import TYPE_CHECKING, Optional
 from pydantic import Field, SecretStr
 
 from unstructured_ingest.embed.interfaces import (
+    EMBEDDINGS_KEY,
     AsyncBaseEmbeddingEncoder,
     BaseEmbeddingEncoder,
     EmbeddingConfig,
@@ -107,8 +108,12 @@ class VoyageAIEmbeddingEncoder(BaseEmbeddingEncoder):
         return embeddings
 
     def embed_documents(self, elements: list[dict]) -> list[dict]:
-        embeddings = self._embed_documents([e.get("text", "") for e in elements])
-        return self._add_embeddings_to_elements(elements, embeddings)
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        embeddings = self._embed_documents([e["text"] for e in elements_with_text])
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements
 
     def embed_query(self, query: str) -> list[float]:
         return self._embed_documents(elements=[query])[0]
@@ -135,8 +140,12 @@ class AsyncVoyageAIEmbeddingEncoder(AsyncBaseEmbeddingEncoder):
         return embeddings
 
     async def embed_documents(self, elements: list[dict]) -> list[dict]:
-        embeddings = await self._embed_documents([e.get("text", "") for e in elements])
-        return self._add_embeddings_to_elements(elements, embeddings)
+        elements = elements.copy()
+        elements_with_text = [e for e in elements if e.get("text")]
+        embeddings = await self._embed_documents([e["text"] for e in elements_with_text])
+        for element, embedding in zip(elements_with_text, embeddings):
+            element[EMBEDDINGS_KEY] = embedding
+        return elements
 
     async def embed_query(self, query: str) -> list[float]:
         embedding = await self._embed_documents(elements=[query])

unstructured_ingest/v2/processes/connectors/google_drive.py

@@ -132,12 +132,141 @@ class GoogleDriveIndexer(Indexer):
         ]
     )
 
+    @staticmethod
+    def verify_drive_api_enabled(client) -> None:
+        from googleapiclient.errors import HttpError
+
+        """
+        Makes a lightweight API call to verify that the Drive API is enabled.
+        If the API is not enabled, an HttpError should be raised.
+        """
+        try:
+            # A very minimal call: list 1 file from the drive.
+            client.list(spaces="drive", pageSize=1, fields="files(id)").execute()
+        except HttpError as e:
+            error_content = e.content.decode() if hasattr(e, "content") else ""
+            lower_error = error_content.lower()
+            if "drive api" in lower_error and (
+                "not enabled" in lower_error or "not been used" in lower_error
+            ):
+                raise SourceConnectionError(
+                    "Google Drive API is not enabled for your project. \
+                    Please enable it in the Google Cloud Console."
+                )
+            else:
+                raise SourceConnectionError("Google drive API unreachable for an unknown reason!")
+
+    @staticmethod
+    def count_files_recursively(files_client, folder_id: str, extensions: list[str] = None) -> int:
+        """
+        Count non-folder files recursively under the given folder.
+        If `extensions` is provided, only count files
+        whose `fileExtension` matches one of the values.
+        """
+        count = 0
+        stack = [folder_id]
+        while stack:
+            current_folder = stack.pop()
+            # Always list all items under the current folder.
+            query = f"'{current_folder}' in parents"
+            page_token = None
+            while True:
+                response = files_client.list(
+                    spaces="drive",
+                    q=query,
+                    fields="nextPageToken, files(id, mimeType, fileExtension)",
+                    pageToken=page_token,
+                    pageSize=1000,
+                ).execute()
+                for item in response.get("files", []):
+                    if item.get("mimeType") == "application/vnd.google-apps.folder":
+                        # Always traverse sub-folders regardless of extension filter.
+                        stack.append(item["id"])
+                    else:
+                        if extensions:
+                            # Use a case-insensitive comparison for the file extension.
+                            file_ext = (item.get("fileExtension") or "").lower()
+                            valid_exts = [e.lower() for e in extensions]
+                            if file_ext in valid_exts:
+                                count += 1
+                        else:
+                            count += 1
+                page_token = response.get("nextPageToken")
+                if not page_token:
+                    break
+        return count
+
     def precheck(self) -> None:
+        """
+        Enhanced precheck that verifies not only connectivity
+        but also that the provided drive_id is valid and accessible.
+        """
         try:
-            self.connection_config.get_client()
+            with self.connection_config.get_client() as client:
+                # First, verify that the Drive API is enabled.
+                self.verify_drive_api_enabled(client)
+
+                # Try to retrieve metadata for the drive id.
+                # This will catch errors such as an invalid drive id or insufficient permissions.
+                root_info = self.get_root_info(
+                    files_client=client, object_id=self.connection_config.drive_id
+                )
+                logger.info(
+                    f"Successfully retrieved drive root info: "
+                    f"{root_info.get('name', 'Unnamed')} (ID: {root_info.get('id')})"
+                )
+
+            # If the target is a folder, perform file count check.
+            if self.is_dir(root_info):
+                if self.index_config.recursive:
+                    file_count = self.count_files_recursively(
+                        client,
+                        self.connection_config.drive_id,
+                        extensions=self.index_config.extensions,
+                    )
+                    if file_count == 0:
+                        logger.warning(
+                            "Empty folder: no files found recursively in the folder. \
+                             Please verify that the folder contains files and \
+                             that the service account has proper permissions."
+                        )
+                        # raise SourceConnectionError(
+                        #     "Empty folder: no files found recursively in the folder. "
+                        #     "Please verify that the folder contains files and \
+                        #     that the service account has proper permissions."
+                        # )
+                    else:
+                        logger.info(f"Found {file_count} files recursively in the folder.")
+                else:
+                    # Non-recursive: check for at least one immediate non-folder child.
+                    response = client.list(
+                        spaces="drive",
+                        fields="files(id)",
+                        pageSize=1,
+                        q=f"'{self.connection_config.drive_id}' in parents",
+                    ).execute()
+                    if not response.get("files"):
+                        logger.warning(
+                            "Empty folder: no files found at the folder's root level. "
+                            "Please verify that the folder contains files and \
+                            that the service account has proper permissions."
+                        )
+                        # raise SourceConnectionError(
+                        #     "Empty folder: no files found at the folder's root level. "
+                        #     "Please verify that the folder contains files and \
+                        #     that the service account has proper permissions."
+                        # )
+                    else:
+                        logger.info("Found files at the folder's root level.")
+            else:
+                # If the target is a file, precheck passes.
+                logger.info("Drive ID corresponds to a file. Precheck passed.")
+
         except Exception as e:
-            logger.error(f"failed to validate connection: {e}", exc_info=True)
-            raise SourceConnectionError(f"failed to validate connection: {e}")
+            logger.error(
+                "Failed to validate Google Drive connection during precheck", exc_info=True
+            )
+            raise SourceConnectionError(f"Precheck failed: {e}")
 
     @staticmethod
     def is_dir(record: dict) -> bool:

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

@@ -1,6 +1,7 @@
+import json
 from contextlib import contextmanager
 from dataclasses import dataclass, field
-from typing import TYPE_CHECKING, Generator, Optional
+from typing import TYPE_CHECKING, Any, Generator, Optional
 
 import numpy as np
 import pandas as pd
@@ -15,6 +16,7 @@ from unstructured_ingest.v2.processes.connector_registry import (
     SourceRegistryEntry,
 )
 from unstructured_ingest.v2.processes.connectors.sql.sql import (
+    _DATE_COLUMNS,
     SQLAccessConfig,
     SqlBatchFileData,
     SQLConnectionConfig,
@@ -26,6 +28,7 @@ from unstructured_ingest.v2.processes.connectors.sql.sql import (
     SQLUploaderConfig,
     SQLUploadStager,
     SQLUploadStagerConfig,
+    parse_date_string,
 )
 
 if TYPE_CHECKING:
@@ -34,6 +37,17 @@ if TYPE_CHECKING:
 
 CONNECTOR_TYPE = "snowflake"
 
+_ARRAY_COLUMNS = (
+    "embeddings",
+    "languages",
+    "link_urls",
+    "link_texts",
+    "sent_from",
+    "sent_to",
+    "emphasized_text_contents",
+    "emphasized_text_tags",
+)
+
 
 class SnowflakeAccessConfig(SQLAccessConfig):
     password: Optional[str] = Field(default=None, description="DB password")
@@ -160,6 +174,42 @@ class SnowflakeUploader(SQLUploader):
     connector_type: str = CONNECTOR_TYPE
     values_delimiter: str = "?"
 
+    def prepare_data(
+        self, columns: list[str], data: tuple[tuple[Any, ...], ...]
+    ) -> list[tuple[Any, ...]]:
+        output = []
+        for row in data:
+            parsed = []
+            for column_name, value in zip(columns, row):
+                if column_name in _DATE_COLUMNS:
+                    if value is None or pd.isna(value):  # pandas is nan
+                        parsed.append(None)
+                    else:
+                        parsed.append(parse_date_string(value))
+                elif column_name in _ARRAY_COLUMNS:
+                    if not isinstance(value, list) and (
+                        value is None or pd.isna(value)
+                    ):  # pandas is nan
+                        parsed.append(None)
+                    else:
+                        parsed.append(json.dumps(value))
+                else:
+                    parsed.append(value)
+            output.append(tuple(parsed))
+        return output
+
+    def _parse_values(self, columns: list[str]) -> str:
+        return ",".join(
+            [
+                (
+                    f"PARSE_JSON({self.values_delimiter})"
+                    if col in _ARRAY_COLUMNS
+                    else self.values_delimiter
+                )
+                for col in columns
+            ]
+        )
+
     def upload_dataframe(self, df: pd.DataFrame, file_data: FileData) -> None:
         if self.can_delete():
             self.delete_by_record_id(file_data=file_data)
@@ -173,10 +223,10 @@ class SnowflakeUploader(SQLUploader):
         self._fit_to_schema(df=df)
 
         columns = list(df.columns)
-        stmt = "INSERT INTO {table_name} ({columns}) VALUES({values})".format(
+        stmt = "INSERT INTO {table_name} ({columns}) SELECT {values}".format(
             table_name=self.upload_config.table_name,
             columns=",".join(columns),
-            values=",".join([self.values_delimiter for _ in columns]),
+            values=self._parse_values(columns),
         )
         logger.info(
             f"writing a total of {len(df)} elements via"

{unstructured_ingest-0.5.1.dist-info → unstructured_ingest-0.5.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unstructured-ingest
-Version: 0.5.1
+Version: 0.5.2
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,31 +22,31 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: dataclasses-json
-Requires-Dist: click
-Requires-Dist: opentelemetry-sdk
+Requires-Dist: pandas
 Requires-Dist: pydantic>=2.7
+Requires-Dist: dataclasses-json
 Requires-Dist: python-dateutil
-Requires-Dist: pandas
+Requires-Dist: opentelemetry-sdk
+Requires-Dist: click
 Requires-Dist: tqdm
 Provides-Extra: airtable
 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: bedrock
-Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"
+Requires-Dist: aioboto3; extra == "bedrock"
 Provides-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
@@ -92,12 +92,12 @@ Requires-Dist: voyageai; extra == "embed-voyageai"
 Provides-Extra: epub
 Requires-Dist: unstructured[epub]; extra == "epub"
 Provides-Extra: gcs
-Requires-Dist: gcsfs; extra == "gcs"
-Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: fsspec; extra == "gcs"
+Requires-Dist: bs4; extra == "gcs"
+Requires-Dist: gcsfs; extra == "gcs"
 Provides-Extra: github
-Requires-Dist: requests; extra == "github"
 Requires-Dist: pygithub>1.58.0; extra == "github"
+Requires-Dist: requests; extra == "github"
 Provides-Extra: gitlab
 Requires-Dist: python-gitlab; extra == "gitlab"
 Provides-Extra: google-drive
@@ -122,20 +122,20 @@ Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: msg
 Requires-Dist: unstructured[msg]; extra == "msg"
 Provides-Extra: neo4j
-Requires-Dist: neo4j; extra == "neo4j"
-Requires-Dist: cymple; extra == "neo4j"
 Requires-Dist: networkx; extra == "neo4j"
+Requires-Dist: cymple; extra == "neo4j"
+Requires-Dist: neo4j; extra == "neo4j"
 Provides-Extra: notion
-Requires-Dist: backoff; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
-Requires-Dist: httpx; extra == "notion"
+Requires-Dist: backoff; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
+Requires-Dist: httpx; extra == "notion"
 Provides-Extra: odt
 Requires-Dist: unstructured[odt]; extra == "odt"
 Provides-Extra: onedrive
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
-Requires-Dist: msal; extra == "onedrive"
 Requires-Dist: bs4; extra == "onedrive"
+Requires-Dist: msal; extra == "onedrive"
 Provides-Extra: openai
 Requires-Dist: openai; extra == "openai"
 Requires-Dist: tiktoken; extra == "openai"
@@ -169,13 +169,13 @@ Requires-Dist: unstructured[rst]; extra == "rst"
 Provides-Extra: rtf
 Requires-Dist: unstructured[rtf]; extra == "rtf"
 Provides-Extra: s3
-Requires-Dist: fsspec; extra == "s3"
 Requires-Dist: s3fs; extra == "s3"
+Requires-Dist: fsspec; extra == "s3"
 Provides-Extra: salesforce
 Requires-Dist: simple-salesforce; extra == "salesforce"
 Provides-Extra: sftp
-Requires-Dist: paramiko; extra == "sftp"
 Requires-Dist: fsspec; extra == "sftp"
+Requires-Dist: paramiko; extra == "sftp"
 Provides-Extra: sharepoint
 Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
 Requires-Dist: msal; extra == "sharepoint"
@@ -184,19 +184,19 @@ Requires-Dist: singlestoredb; extra == "singlestore"
 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: 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: pyarrow; extra == "vastdb"
 Requires-Dist: ibis; extra == "vastdb"
 Provides-Extra: vectara
-Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"
+Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: aiofiles; extra == "vectara"
 Provides-Extra: weaviate
 Requires-Dist: weaviate-client; extra == "weaviate"

{unstructured_ingest-0.5.1.dist-info → unstructured_ingest-0.5.2.dist-info}/RECORD

@@ -10,7 +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_google_drive.py,sha256=ubjn3wvMhgpGHQs-wT_5icGgTIx2coS6hwNkAHOCEI8,10306
 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
@@ -107,7 +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=LXdgOM6QWErpDu1oCqJrypfmAkBaXzRxVPcjHL8yPrI,42
+unstructured_ingest/__version__.py,sha256=vh_Kp5pxLwbO2jsp-9Z1oAftmDaQZ9nkLMwneOowYbU,42
 unstructured_ingest/error.py,sha256=qDncnJgbf5ils956RcO2CGlAKYDT5OaEM9Clv1JVTNc,1448
 unstructured_ingest/interfaces.py,sha256=7DOnDpGvUNlCoFR7UPRGmOarqH5sFtuUOO5vf8X3oTM,31489
 unstructured_ingest/logger.py,sha256=S5nSqGcABoQyeicgRnBQFjDScCaTvFVivOCvbo-laL0,4479
@@ -276,15 +276,15 @@ unstructured_ingest/connector/notion/types/database_properties/url.py,sha256=iXQ
 unstructured_ingest/connector/notion/types/database_properties/verification.py,sha256=J_DLjY-v2T6xDGMQ7FkI0YMKMA6SG6Y3yYW7qUD1hKA,2334
 unstructured_ingest/embed/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 unstructured_ingest/embed/azure_openai.py,sha256=u9reyZzY6BtsT5U_TdIfS6vH_42lvohVBwKMPQAqvkI,1528
-unstructured_ingest/embed/bedrock.py,sha256=50G8PBEdW3ILwyWXAWl4w-gUA9I0AR7LuFq6NLz-sWI,7284
-unstructured_ingest/embed/huggingface.py,sha256=Avcc16st9Cp2xGScG6TeNEEd3T8YjjnESNN4OdIlnh0,2119
-unstructured_ingest/embed/interfaces.py,sha256=7jsQ3rLOXy1hq__muf-EPcLnv17XzNQaD05AyGbZeNo,3739
-unstructured_ingest/embed/mixedbreadai.py,sha256=OhF5cMxWMq8-0mt8_-Xe3ZkjGjf2u6QYzfzgHnOEYtU,6838
-unstructured_ingest/embed/octoai.py,sha256=oLNlM02W1CNUYRG_j6qWyI7yE24vYGKYradNzeeP6mE,5062
-unstructured_ingest/embed/openai.py,sha256=H1sURGuRvXBUSXJcAVzrLObV5wSCVM29tkaXJ-9ZR30,4727
-unstructured_ingest/embed/togetherai.py,sha256=SUd16JEUPlR8aCrd4q_T3CHwMTRUi-1yenq_r1AWlak,4266
-unstructured_ingest/embed/vertexai.py,sha256=CPptS7U5W1CgvxIN8CgVz5J1Ia4FctV6BsmpN9c92A0,4890
-unstructured_ingest/embed/voyageai.py,sha256=lydMASUDcTuyfWBPS3uIqDJPQbjf95bEI5Kr4tytONs,5111
+unstructured_ingest/embed/bedrock.py,sha256=LnlxU2cC7mrq5wLiZ6D_7lv0_z_O2YtmY_8oRMu1N8E,7548
+unstructured_ingest/embed/huggingface.py,sha256=4ytvdGrXur-PllLaNdKGQ4BhxxOJlHNzj4NfBwTUEsk,2270
+unstructured_ingest/embed/interfaces.py,sha256=-SLdQKX6-KIa2Jq_-rz14noBnH9VuV8flOUKr8WJKMM,3109
+unstructured_ingest/embed/mixedbreadai.py,sha256=ALRedRFg9xzFkYuV26uSjLGU4_3kHS46P8uSWeNdfoY,7214
+unstructured_ingest/embed/octoai.py,sha256=lvfgs5Bnpn6lb_q4LenhFZ6IXC_L8xYilGC03ecJIGc,5318
+unstructured_ingest/embed/openai.py,sha256=3QWindgIsziI5ChQ6Zzqt4hQ9g-qKeTFDZvt55YsA1k,4983
+unstructured_ingest/embed/togetherai.py,sha256=lhUgiC24xuXbzmVlqgjrqtU4cJs-sIP-myxkaRK_tnk,4642
+unstructured_ingest/embed/vertexai.py,sha256=LSLR9iOBX07e7bsIcMyU5kgmHm0zgC4GZ_gO6WL4xYY,5146
+unstructured_ingest/embed/voyageai.py,sha256=M9LZ-YP54FSXzLt7XyWP4UoLb0naP6acpUNdQS-MucQ,5487
 unstructured_ingest/enhanced_dataclass/__init__.py,sha256=gDZOUsv5eo-8jm4Yu7DdDwi101aGbfG7JctTdOYnTOM,151
 unstructured_ingest/enhanced_dataclass/core.py,sha256=d6aUkDynuKX87cHx9_N5UDUWrvISR4jYRFRTvd_avlI,3038
 unstructured_ingest/enhanced_dataclass/dataclasses.py,sha256=aZMsoCzAGRb8Rmh3BTSBFtNr6FmFTY93KYGLk3gYJKQ,1949
@@ -432,7 +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=tSbyibwm9RQyXD-HJGZa1Y9lBSCXaEFnvxpf6bHwBSE,13394
+unstructured_ingest/v2/processes/connectors/google_drive.py,sha256=QzcHNelUbnubsDtanFIgDCRzmYTuP-GjJ_g9y8fButE,19623
 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
@@ -558,7 +558,7 @@ unstructured_ingest/v2/processes/connectors/sql/__init__.py,sha256=NSEZwJDHh_9kF
 unstructured_ingest/v2/processes/connectors/sql/databricks_delta_tables.py,sha256=xbZ90rmehiCnBoqFXMz-3ZMXeYb0PzWB6iobCNSHTmQ,8955
 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/snowflake.py,sha256=0hfiX_u7V38k_RfoeDmXJp8WIHZ19ilIHnrgZVSleKw,9270
 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=0rxrb1ByXIefB9umzMTEJbpvzdTttXHK5DjRY97-GG8,9618
@@ -567,9 +567,9 @@ unstructured_ingest/v2/processes/connectors/weaviate/cloud.py,sha256=bXtfEYLquR-
 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-0.5.1.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,,
+unstructured_ingest-0.5.2.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
+unstructured_ingest-0.5.2.dist-info/METADATA,sha256=SiWzXim0-JmdQF6rlC6RbnmRBHcheGOk2VMlKN2A2ms,8051
+unstructured_ingest-0.5.2.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+unstructured_ingest-0.5.2.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
+unstructured_ingest-0.5.2.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
+unstructured_ingest-0.5.2.dist-info/RECORD,,