unstructured-ingest 0.3.14__py3-none-any.whl → 0.3.15__py3-none-any.whl

test/integration/connectors/sql/test_databricks_delta_tables.py

@@ -0,0 +1,142 @@
+import json
+import os
+import time
+from contextlib import contextmanager
+from pathlib import Path
+from uuid import uuid4
+
+import pytest
+from databricks.sql import connect
+from databricks.sql.client import Connection as DeltaTableConnection
+from databricks.sql.client import Cursor as DeltaTableCursor
+from pydantic import BaseModel, SecretStr
+
+from test.integration.connectors.utils.constants import DESTINATION_TAG, SQL_TAG, env_setup_path
+from test.integration.utils import requires_env
+from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
+from unstructured_ingest.v2.logger import logger
+from unstructured_ingest.v2.processes.connectors.sql.databricks_delta_tables import (
+    CONNECTOR_TYPE,
+    DatabrickDeltaTablesAccessConfig,
+    DatabrickDeltaTablesConnectionConfig,
+    DatabrickDeltaTablesUploader,
+    DatabrickDeltaTablesUploaderConfig,
+    DatabrickDeltaTablesUploadStager,
+)
+
+CATALOG = "utic-dev-tech-fixtures"
+
+
+class EnvData(BaseModel):
+    server_hostname: str
+    http_path: str
+    access_token: SecretStr
+
+
+def get_env_data() -> EnvData:
+    return EnvData(
+        server_hostname=os.environ["DATABRICKS_SERVER_HOSTNAME"],
+        http_path=os.environ["DATABRICKS_HTTP_PATH"],
+        access_token=os.environ["DATABRICKS_ACCESS_TOKEN"],
+    )
+
+
+def get_destination_schema(new_table_name: str) -> str:
+    p = Path(env_setup_path / "sql" / "databricks_delta_tables" / "destination" / "schema.sql")
+    with p.open() as f:
+        data_lines = f.readlines()
+    data_lines[0] = data_lines[0].replace("elements", new_table_name)
+    data = "".join([line.strip() for line in data_lines])
+    return data
+
+
+@contextmanager
+def get_connection() -> DeltaTableConnection:
+    env_data = get_env_data()
+    with connect(
+        server_hostname=env_data.server_hostname,
+        http_path=env_data.http_path,
+        access_token=env_data.access_token.get_secret_value(),
+    ) as connection:
+        yield connection
+
+
+@contextmanager
+def get_cursor() -> DeltaTableCursor:
+    with get_connection() as connection:
+        with connection.cursor() as cursor:
+            cursor.execute(f"USE CATALOG '{CATALOG}'")
+            yield cursor
+
+
+@pytest.fixture
+def destination_table() -> str:
+    random_id = str(uuid4())[:8]
+    table_name = f"elements_{random_id}"
+    destination_schema = get_destination_schema(new_table_name=table_name)
+    with get_cursor() as cursor:
+        logger.info(f"creating table: {table_name}")
+        cursor.execute(f"DROP TABLE IF EXISTS {table_name}")
+        cursor.execute(destination_schema)
+
+    yield table_name
+    with get_cursor() as cursor:
+        logger.info(f"dropping table: {table_name}")
+        cursor.execute(f"DROP TABLE IF EXISTS {table_name}")
+
+
+def validate_destination(expected_num_elements: int, table_name: str, retries=30, interval=1):
+    with get_cursor() as cursor:
+        for i in range(retries):
+            cursor.execute(f"SELECT COUNT(*) FROM {table_name}")
+            count = cursor.fetchone()[0]
+            if count == expected_num_elements:
+                break
+            logger.info(f"retry attempt {i}: expected {expected_num_elements} != count {count}")
+            time.sleep(interval)
+        assert (
+            count == expected_num_elements
+        ), f"dest check failed: got {count}, expected {expected_num_elements}"
+
+
+@pytest.mark.asyncio
+@pytest.mark.skip("Resources take too long to spin up to run in CI")
+@pytest.mark.tags(CONNECTOR_TYPE, DESTINATION_TAG, SQL_TAG)
+@requires_env("DATABRICKS_SERVER_HOSTNAME", "DATABRICKS_HTTP_PATH", "DATABRICKS_ACCESS_TOKEN")
+async def test_databricks_delta_tables_destination(
+    upload_file: Path, temp_dir: Path, destination_table: str
+):
+    env_data = get_env_data()
+    mock_file_data = FileData(
+        identifier="mock file data",
+        connector_type=CONNECTOR_TYPE,
+        source_identifiers=SourceIdentifiers(filename=upload_file.name, fullpath=upload_file.name),
+    )
+    stager = DatabrickDeltaTablesUploadStager()
+    staged_path = stager.run(
+        elements_filepath=upload_file,
+        file_data=mock_file_data,
+        output_dir=temp_dir,
+        output_filename=upload_file.name,
+    )
+
+    assert staged_path.suffix == upload_file.suffix
+
+    uploader = DatabrickDeltaTablesUploader(
+        connection_config=DatabrickDeltaTablesConnectionConfig(
+            access_config=DatabrickDeltaTablesAccessConfig(
+                token=env_data.access_token.get_secret_value()
+            ),
+            http_path=env_data.http_path,
+            server_hostname=env_data.server_hostname,
+        ),
+        upload_config=DatabrickDeltaTablesUploaderConfig(
+            catalog=CATALOG, database="default", table_name=destination_table
+        ),
+    )
+    with staged_path.open("r") as f:
+        staged_data = json.load(f)
+    expected_num_elements = len(staged_data)
+    uploader.precheck()
+    uploader.run(path=staged_path, file_data=mock_file_data)
+    validate_destination(expected_num_elements=expected_num_elements, table_name=destination_table)

test/integration/connectors/test_pinecone.py

@@ -107,11 +107,15 @@ def pinecone_index() -> Generator[str, None, None]:
 
 
 def validate_pinecone_index(
-    index_name: str, expected_num_of_vectors: int, retries=30, interval=1
+    index_name: str,
+    expected_num_of_vectors: int,
+    retries=30,
+    interval=1,
+    namespace: str = "default",
 ) -> None:
     # Because there's a delay for the index to catch up to the recent writes, add in a retry
     pinecone = Pinecone(api_key=get_api_key())
-    index = pinecone.Index(name=index_name)
+    index = pinecone.Index(name=index_name, namespace=namespace)
     vector_count = -1
     for i in range(retries):
         index_stats = index.describe_index_stats()
@@ -133,11 +137,13 @@ def validate_pinecone_index(
 @pytest.mark.asyncio
 @pytest.mark.tags(CONNECTOR_TYPE, DESTINATION_TAG, VECTOR_DB_TAG)
 async def test_pinecone_destination(pinecone_index: str, upload_file: Path, temp_dir: Path):
+
     file_data = FileData(
         source_identifiers=SourceIdentifiers(fullpath=upload_file.name, filename=upload_file.name),
         connector_type=CONNECTOR_TYPE,
         identifier="pinecone_mock_id",
     )
+
     connection_config = PineconeConnectionConfig(
         index_name=pinecone_index,
         access_config=PineconeAccessConfig(api_key=get_api_key()),
@@ -224,6 +230,66 @@ async def test_pinecone_destination_large_index(
     )
 
 
+@requires_env(API_KEY)
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, DESTINATION_TAG, VECTOR_DB_TAG)
+async def test_pinecone_destination_namespace(
+    pinecone_index: str, upload_file: Path, temp_dir: Path
+):
+    """
+    tests namespace functionality of destination connector.
+    """
+
+    # creates a file data structure.
+    file_data = FileData(
+        source_identifiers=SourceIdentifiers(fullpath=upload_file.name, filename=upload_file.name),
+        connector_type=CONNECTOR_TYPE,
+        identifier="pinecone_mock_id",
+    )
+
+    connection_config = PineconeConnectionConfig(
+        index_name=pinecone_index,
+        access_config=PineconeAccessConfig(api_key=get_api_key()),
+    )
+
+    stager_config = PineconeUploadStagerConfig()
+
+    stager = PineconeUploadStager(upload_stager_config=stager_config)
+    new_upload_file = stager.run(
+        elements_filepath=upload_file,
+        output_dir=temp_dir,
+        output_filename=upload_file.name,
+        file_data=file_data,
+    )
+
+    # here add namespace defintion
+    upload_config = PineconeUploaderConfig()
+    namespace_test_name = "user-1"
+    upload_config.namespace = namespace_test_name
+    uploader = PineconeUploader(connection_config=connection_config, upload_config=upload_config)
+    uploader.precheck()
+
+    uploader.run(path=new_upload_file, file_data=file_data)
+    with new_upload_file.open() as f:
+        staged_content = json.load(f)
+    expected_num_of_vectors = len(staged_content)
+    logger.info("validating first upload")
+    validate_pinecone_index(
+        index_name=pinecone_index,
+        expected_num_of_vectors=expected_num_of_vectors,
+        namespace=namespace_test_name,
+    )
+
+    # Rerun uploader and make sure no duplicates exist
+    uploader.run(path=new_upload_file, file_data=file_data)
+    logger.info("validating second upload")
+    validate_pinecone_index(
+        index_name=pinecone_index,
+        expected_num_of_vectors=expected_num_of_vectors,
+        namespace=namespace_test_name,
+    )
+
+
 @requires_env(API_KEY)
 @pytest.mark.tags(CONNECTOR_TYPE, DESTINATION_TAG, VECTOR_DB_TAG)
 def test_large_metadata(pinecone_index: str, tmp_path: Path, upload_file: Path):

unstructured_ingest/__version__.py

@@ -1 +1 @@
-__version__ = "0.3.14"  # pragma: no cover
+__version__ = "0.3.15"  # pragma: no cover

unstructured_ingest/v2/interfaces/upload_stager.py

@@ -2,7 +2,7 @@ import json
 from abc import ABC
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Any, TypeVar
+from typing import Any, Optional, TypeVar
 
 import ndjson
 from pydantic import BaseModel
@@ -22,10 +22,10 @@ UploadStagerConfigT = TypeVar("UploadStagerConfigT", bound=UploadStagerConfig)
 class UploadStager(BaseProcess, ABC):
     upload_stager_config: UploadStagerConfigT
 
-    def write_output(self, output_path: Path, data: list[dict]) -> None:
+    def write_output(self, output_path: Path, data: list[dict], indent: Optional[int] = 2) -> None:
         if output_path.suffix == ".json":
             with output_path.open("w") as f:
-                json.dump(data, f, indent=2)
+                json.dump(data, f, indent=indent)
         elif output_path.suffix == ".ndjson":
             with output_path.open("w") as f:
                 ndjson.dump(data, f)

unstructured_ingest/v2/processes/connectors/databricks/__init__.py

@@ -25,6 +25,8 @@ from .volumes_native import (
     databricks_native_volumes_destination_entry,
     databricks_native_volumes_source_entry,
 )
+from .volumes_table import CONNECTOR_TYPE as VOLUMES_TABLE_CONNECTOR_TYPE
+from .volumes_table import databricks_volumes_delta_tables_destination_entry
 
 add_source_entry(source_type=VOLUMES_AWS_CONNECTOR_TYPE, entry=databricks_aws_volumes_source_entry)
 add_destination_entry(
@@ -50,3 +52,7 @@ add_source_entry(
 add_destination_entry(
     destination_type=VOLUMES_AZURE_CONNECTOR_TYPE, entry=databricks_azure_volumes_destination_entry
 )
+add_destination_entry(
+    destination_type=VOLUMES_TABLE_CONNECTOR_TYPE,
+    entry=databricks_volumes_delta_tables_destination_entry,
+)

unstructured_ingest/v2/processes/connectors/databricks/volumes.py

@@ -187,6 +187,11 @@ class DatabricksVolumesUploader(Uploader, ABC):
     upload_config: DatabricksVolumesUploaderConfig
     connection_config: DatabricksVolumesConnectionConfig
 
+    def get_output_path(self, file_data: FileData) -> str:
+        return os.path.join(
+            self.upload_config.path, f"{file_data.source_identifiers.filename}.json"
+        )
+
     def precheck(self) -> None:
         try:
             assert self.connection_config.get_client().current_user.me().active
@@ -194,9 +199,7 @@ class DatabricksVolumesUploader(Uploader, ABC):
             raise self.connection_config.wrap_error(e=e)
 
     def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
-        output_path = os.path.join(
-            self.upload_config.path, f"{file_data.source_identifiers.filename}.json"
-        )
+        output_path = self.get_output_path(file_data=file_data)
         with open(path, "rb") as elements_file:
             try:
                 self.connection_config.get_client().files.upload(

unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py

@@ -0,0 +1,106 @@
+import json
+import os
+from contextlib import contextmanager
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any, Generator, Optional
+
+from pydantic import Field
+
+from unstructured_ingest.v2.interfaces import FileData, Uploader, UploaderConfig
+from unstructured_ingest.v2.logger import logger
+from unstructured_ingest.v2.processes.connector_registry import (
+    DestinationRegistryEntry,
+)
+from unstructured_ingest.v2.processes.connectors.databricks.volumes import DatabricksPathMixin
+from unstructured_ingest.v2.processes.connectors.sql.databricks_delta_tables import (
+    DatabrickDeltaTablesConnectionConfig,
+    DatabrickDeltaTablesUploadStager,
+    DatabrickDeltaTablesUploadStagerConfig,
+)
+
+CONNECTOR_TYPE = "databricks_volume_delta_tables"
+
+
+class DatabricksVolumeDeltaTableUploaderConfig(UploaderConfig, DatabricksPathMixin):
+    database: str = Field(description="Database name", default="default")
+    table_name: str = Field(description="Table name")
+
+
+@dataclass
+class DatabricksVolumeDeltaTableStager(DatabrickDeltaTablesUploadStager):
+    def write_output(self, output_path: Path, data: list[dict], indent: Optional[int] = 2) -> None:
+        # To avoid new line issues when migrating from volumes into delta tables, omit indenting
+        # and always write it as a json file
+        with output_path.with_suffix(".json").open("w") as f:
+            json.dump(data, f)
+
+
+@dataclass
+class DatabricksVolumeDeltaTableUploader(Uploader):
+    connection_config: DatabrickDeltaTablesConnectionConfig
+    upload_config: DatabricksVolumeDeltaTableUploaderConfig
+    connector_type: str = CONNECTOR_TYPE
+
+    def precheck(self) -> None:
+        with self.connection_config.get_cursor() as cursor:
+            cursor.execute("SHOW CATALOGS")
+            catalogs = [r[0] for r in cursor.fetchall()]
+            if self.upload_config.catalog not in catalogs:
+                raise ValueError(
+                    "Catalog {} not found in {}".format(
+                        self.upload_config.catalog, ", ".join(catalogs)
+                    )
+                )
+            cursor.execute(f"USE CATALOG '{self.upload_config.catalog}'")
+            cursor.execute("SHOW DATABASES")
+            databases = [r[0] for r in cursor.fetchall()]
+            if self.upload_config.database not in databases:
+                raise ValueError(
+                    "Database {} not found in {}".format(
+                        self.upload_config.database, ", ".join(databases)
+                    )
+                )
+            cursor.execute("SHOW TABLES")
+            table_names = [r[1] for r in cursor.fetchall()]
+            if self.upload_config.table_name not in table_names:
+                raise ValueError(
+                    "Table {} not found in {}".format(
+                        self.upload_config.table_name, ", ".join(table_names)
+                    )
+                )
+
+    def get_output_path(self, file_data: FileData, suffix: str = ".json") -> str:
+        filename = Path(file_data.source_identifiers.filename)
+        adjusted_filename = filename if filename.suffix == suffix else f"{filename}{suffix}"
+        return os.path.join(self.upload_config.path, f"{adjusted_filename}")
+
+    @contextmanager
+    def get_cursor(self, **connect_kwargs) -> Generator[Any, None, None]:
+        with self.connection_config.get_cursor(**connect_kwargs) as cursor:
+            cursor.execute(f"USE CATALOG '{self.upload_config.catalog}'")
+            yield cursor
+
+    def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
+        with self.get_cursor(staging_allowed_local_path=str(path.parent)) as cursor:
+            catalog_path = self.get_output_path(file_data=file_data)
+            logger.debug(f"uploading {path.as_posix()} to {catalog_path}")
+            cursor.execute(f"PUT '{path.as_posix()}' INTO '{catalog_path}' OVERWRITE")
+            logger.debug(
+                f"migrating content from {catalog_path} to table {self.upload_config.table_name}"
+            )
+            with path.open() as f:
+                data = json.load(f)
+                columns = data[0].keys()
+            column_str = ", ".join(columns)
+            sql_statment = f"INSERT INTO `{self.upload_config.table_name}` ({column_str}) SELECT {column_str} FROM json.`{catalog_path}`"  # noqa: E501
+            cursor.execute(sql_statment)
+
+
+databricks_volumes_delta_tables_destination_entry = DestinationRegistryEntry(
+    connection_config=DatabrickDeltaTablesConnectionConfig,
+    uploader=DatabricksVolumeDeltaTableUploader,
+    uploader_config=DatabricksVolumeDeltaTableUploaderConfig,
+    upload_stager=DatabricksVolumeDeltaTableStager,
+    upload_stager_config=DatabrickDeltaTablesUploadStagerConfig,
+)

unstructured_ingest/v2/processes/connectors/pinecone.py

@@ -5,12 +5,10 @@ from typing import TYPE_CHECKING, Any, Optional
 from pydantic import Field, Secret
 
 from unstructured_ingest.error import DestinationConnectionError
-from unstructured_ingest.utils.data_prep import (
-    flatten_dict,
-    generator_batching_wbytes,
-)
+from unstructured_ingest.utils.data_prep import flatten_dict, generator_batching_wbytes
 from unstructured_ingest.utils.dep_check import requires_dependencies
 from unstructured_ingest.v2.constants import RECORD_ID_LABEL
+from unstructured_ingest.v2.errors import UserError
 from unstructured_ingest.v2.interfaces import (
     AccessConfig,
     ConnectionConfig,
@@ -63,6 +61,7 @@ class PineconeConnectionConfig(ConnectionConfig):
         pc = self.get_client()
 
         index = pc.Index(name=self.index_name, **index_kwargs)
+
         logger.debug(f"connected to index: {pc.describe_index(self.index_name)}")
         return index
 
@@ -182,14 +181,18 @@ class PineconeUploader(Uploader):
         delete_kwargs = {
             "filter": {self.upload_config.record_id_key: {"$eq": file_data.identifier}}
         }
+
         if namespace := self.upload_config.namespace:
             delete_kwargs["namespace"] = namespace
+            try:
+                index.delete(**delete_kwargs)
+            except UserError as e:
+                logger.error(f"failed to delete batch of ids: {delete_kwargs} {e}")
 
-        resp = index.delete(**delete_kwargs)
         logger.debug(
             f"deleted any content with metadata "
             f"{self.upload_config.record_id_key}={file_data.identifier} "
-            f"from pinecone index: {resp}"
+            f"from pinecone index: {delete_kwargs}"
         )
 
     def serverless_delete_by_record_id(self, file_data: FileData) -> None:
@@ -203,15 +206,19 @@ class PineconeUploader(Uploader):
         deleted_ids = 0
         if namespace := self.upload_config.namespace:
             list_kwargs["namespace"] = namespace
+
         for ids in index.list(**list_kwargs):
             deleted_ids += len(ids)
             delete_kwargs = {"ids": ids}
+
             if namespace := self.upload_config.namespace:
-                delete_resp = delete_kwargs["namespace"] = namespace
-                # delete_resp should be an empty dict if there were no errors
-                if delete_resp:
-                    logger.error(f"failed to delete batch of ids: {delete_resp}")
-            index.delete(**delete_kwargs)
+                delete_kwargs["namespace"] = namespace
+
+            try:
+                index.delete(**delete_kwargs)
+            except UserError as e:
+                logger.error(f"failed to delete batch of ids: {delete_kwargs} {e}")
+
         logger.info(
             f"deleted {deleted_ids} records with metadata "
             f"{self.upload_config.record_id_key}={file_data.identifier} "

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

@@ -5,6 +5,8 @@ from unstructured_ingest.v2.processes.connector_registry import (
     add_source_entry,
 )
 
+from .databricks_delta_tables import CONNECTOR_TYPE as DATABRICKS_DELTA_TABLES_CONNECTOR_TYPE
+from .databricks_delta_tables import databricks_delta_tables_destination_entry
 from .postgres import CONNECTOR_TYPE as POSTGRES_CONNECTOR_TYPE
 from .postgres import postgres_destination_entry, postgres_source_entry
 from .singlestore import CONNECTOR_TYPE as SINGLESTORE_CONNECTOR_TYPE
@@ -25,3 +27,7 @@ add_destination_entry(destination_type=SNOWFLAKE_CONNECTOR_TYPE, entry=snowflake
 add_destination_entry(
     destination_type=SINGLESTORE_CONNECTOR_TYPE, entry=singlestore_destination_entry
 )
+add_destination_entry(
+    destination_type=DATABRICKS_DELTA_TABLES_CONNECTOR_TYPE,
+    entry=databricks_delta_tables_destination_entry,
+)

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

@@ -0,0 +1,213 @@
+import json
+from contextlib import contextmanager
+from dataclasses import dataclass
+from typing import TYPE_CHECKING, Any, Generator, Optional
+
+import numpy as np
+import pandas as pd
+from pydantic import Field, Secret
+
+from unstructured_ingest.utils.data_prep import split_dataframe
+from unstructured_ingest.utils.dep_check import requires_dependencies
+from unstructured_ingest.v2.interfaces import FileData
+from unstructured_ingest.v2.logger import logger
+from unstructured_ingest.v2.processes.connector_registry import (
+    DestinationRegistryEntry,
+)
+from unstructured_ingest.v2.processes.connectors.sql.sql import (
+    SQLAccessConfig,
+    SQLConnectionConfig,
+    SQLUploader,
+    SQLUploaderConfig,
+    SQLUploadStager,
+    SQLUploadStagerConfig,
+)
+
+if TYPE_CHECKING:
+    from databricks.sdk.core import oauth_service_principal
+    from databricks.sql.client import Connection as DeltaTableConnection
+    from databricks.sql.client import Cursor as DeltaTableCursor
+
+CONNECTOR_TYPE = "databricks_delta_tables"
+
+
+class DatabrickDeltaTablesAccessConfig(SQLAccessConfig):
+    token: Optional[str] = Field(default=None, description="Databricks Personal Access Token")
+    client_id: Optional[str] = Field(default=None, description="Client ID of the OAuth app.")
+    client_secret: Optional[str] = Field(
+        default=None, description="Client Secret of the OAuth app."
+    )
+
+
+class DatabrickDeltaTablesConnectionConfig(SQLConnectionConfig):
+    access_config: Secret[DatabrickDeltaTablesAccessConfig]
+    server_hostname: str = Field(description="server hostname connection config value")
+    http_path: str = Field(description="http path connection config value")
+    user_agent: str = "unstructuredio_oss"
+
+    @requires_dependencies(["databricks"], extras="databricks-delta-tables")
+    def get_credentials_provider(self) -> "oauth_service_principal":
+        from databricks.sdk.core import Config, oauth_service_principal
+
+        host = f"https://{self.server_hostname}"
+        access_configs = self.access_config.get_secret_value()
+        if (client_id := access_configs.client_id) and (
+            client_secret := access_configs.client_secret
+        ):
+            return oauth_service_principal(
+                Config(
+                    host=host,
+                    client_id=client_id,
+                    client_secret=client_secret,
+                )
+            )
+        return False
+
+    def model_post_init(self, __context: Any) -> None:
+        access_config = self.access_config.get_secret_value()
+        if access_config.token and access_config.client_secret and access_config.client_id:
+            raise ValueError(
+                "One one for of auth can be provided, either token or client id and secret"
+            )
+        if not access_config.token and not (
+            access_config.client_secret and access_config.client_id
+        ):
+            raise ValueError(
+                "One form of auth must be provided, either token or client id and secret"
+            )
+
+    @contextmanager
+    @requires_dependencies(["databricks"], extras="databricks-delta-tables")
+    def get_connection(self, **connect_kwargs) -> Generator["DeltaTableConnection", None, None]:
+        from databricks.sql import connect
+
+        connect_kwargs = connect_kwargs or {}
+        connect_kwargs["_user_agent_entry"] = self.user_agent
+        connect_kwargs["server_hostname"] = connect_kwargs.get(
+            "server_hostname", self.server_hostname
+        )
+        connect_kwargs["http_path"] = connect_kwargs.get("http_path", self.http_path)
+
+        if credential_provider := self.get_credentials_provider():
+            connect_kwargs["credentials_provider"] = credential_provider
+        else:
+            connect_kwargs["access_token"] = self.access_config.get_secret_value().token
+        with connect(**connect_kwargs) as connection:
+            yield connection
+
+    @contextmanager
+    def get_cursor(self, **connect_kwargs) -> Generator["DeltaTableCursor", None, None]:
+        with self.get_connection(**connect_kwargs) as connection:
+            cursor = connection.cursor()
+            yield cursor
+
+
+class DatabrickDeltaTablesUploadStagerConfig(SQLUploadStagerConfig):
+    pass
+
+
+class DatabrickDeltaTablesUploadStager(SQLUploadStager):
+    upload_stager_config: DatabrickDeltaTablesUploadStagerConfig
+
+
+class DatabrickDeltaTablesUploaderConfig(SQLUploaderConfig):
+    catalog: str = Field(description="Name of the catalog in the Databricks Unity Catalog service")
+    database: str = Field(description="Database name", default="default")
+    table_name: str = Field(description="Table name")
+
+
+@dataclass
+class DatabrickDeltaTablesUploader(SQLUploader):
+    upload_config: DatabrickDeltaTablesUploaderConfig
+    connection_config: DatabrickDeltaTablesConnectionConfig
+    connector_type: str = CONNECTOR_TYPE
+
+    @contextmanager
+    def get_cursor(self) -> Generator[Any, None, None]:
+        with self.connection_config.get_cursor() as cursor:
+            cursor.execute(f"USE CATALOG '{self.upload_config.catalog}'")
+            yield cursor
+
+    def precheck(self) -> None:
+        with self.connection_config.get_cursor() as cursor:
+            cursor.execute("SHOW CATALOGS")
+            catalogs = [r[0] for r in cursor.fetchall()]
+            if self.upload_config.catalog not in catalogs:
+                raise ValueError(
+                    "Catalog {} not found in {}".format(
+                        self.upload_config.catalog, ", ".join(catalogs)
+                    )
+                )
+            cursor.execute(f"USE CATALOG '{self.upload_config.catalog}'")
+            cursor.execute("SHOW DATABASES")
+            databases = [r[0] for r in cursor.fetchall()]
+            if self.upload_config.database not in databases:
+                raise ValueError(
+                    "Database {} not found in {}".format(
+                        self.upload_config.database, ", ".join(databases)
+                    )
+                )
+            cursor.execute("SHOW TABLES")
+            table_names = [r[1] for r in cursor.fetchall()]
+            if self.upload_config.table_name not in table_names:
+                raise ValueError(
+                    "Table {} not found in {}".format(
+                        self.upload_config.table_name, ", ".join(table_names)
+                    )
+                )
+
+    def create_statement(self, columns: list[str], values: tuple[Any, ...]) -> str:
+        values_list = []
+        for v in values:
+            if isinstance(v, dict):
+                values_list.append(json.dumps(v))
+            elif isinstance(v, list):
+                if v and isinstance(v[0], (int, float)):
+                    values_list.append("ARRAY({})".format(", ".join([str(val) for val in v])))
+                else:
+                    values_list.append("ARRAY({})".format(", ".join([f"'{val}'" for val in v])))
+            else:
+                values_list.append(f"'{v}'")
+        statement = "INSERT INTO {table_name} ({columns}) VALUES({values})".format(
+            table_name=self.upload_config.table_name,
+            columns=", ".join(columns),
+            values=", ".join(values_list),
+        )
+        return statement
+
+    def upload_dataframe(self, df: pd.DataFrame, file_data: FileData) -> None:
+        if self.can_delete():
+            self.delete_by_record_id(file_data=file_data)
+        else:
+            logger.warning(
+                f"table doesn't contain expected "
+                f"record id column "
+                f"{self.upload_config.record_id_key}, skipping delete"
+            )
+        df.replace({np.nan: None}, inplace=True)
+        self._fit_to_schema(df=df)
+
+        columns = list(df.columns)
+        logger.info(
+            f"writing a total of {len(df)} elements via"
+            f" document batches to destination"
+            f" table named {self.upload_config.table_name}"
+            # f" with batch size {self.upload_config.batch_size}"
+        )
+        # TODO: currently variable binding not supporting for list types,
+        #  update once that gets resolved in SDK
+        for rows in split_dataframe(df=df, chunk_size=self.upload_config.batch_size):
+            with self.get_cursor() as cursor:
+                values = self.prepare_data(columns, tuple(rows.itertuples(index=False, name=None)))
+                for v in values:
+                    stmt = self.create_statement(columns=columns, values=v)
+                    cursor.execute(stmt)
+
+
+databricks_delta_tables_destination_entry = DestinationRegistryEntry(
+    connection_config=DatabrickDeltaTablesConnectionConfig,
+    uploader=DatabrickDeltaTablesUploader,
+    uploader_config=DatabrickDeltaTablesUploaderConfig,
+    upload_stager=DatabrickDeltaTablesUploadStager,
+    upload_stager_config=DatabrickDeltaTablesUploadStagerConfig,
+)

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

@@ -129,8 +129,13 @@ class SQLIndexer(Indexer, ABC):
     connection_config: SQLConnectionConfig
     index_config: SQLIndexerConfig
 
-    def _get_doc_ids(self) -> list[str]:
+    @contextmanager
+    def get_cursor(self) -> Generator[Any, None, None]:
         with self.connection_config.get_cursor() as cursor:
+            yield cursor
+
+    def _get_doc_ids(self) -> list[str]:
+        with self.get_cursor() as cursor:
             cursor.execute(
                 f"SELECT {self.index_config.id_column} FROM {self.index_config.table_name}"
             )
@@ -140,7 +145,7 @@ class SQLIndexer(Indexer, ABC):
 
     def precheck(self) -> None:
         try:
-            with self.connection_config.get_cursor() as cursor:
+            with self.get_cursor() as cursor:
                 cursor.execute("SELECT 1;")
         except Exception as e:
             logger.error(f"failed to validate connection: {e}", exc_info=True)
@@ -182,6 +187,11 @@ class SQLDownloader(Downloader, ABC):
     connection_config: SQLConnectionConfig
     download_config: SQLDownloaderConfig
 
+    @contextmanager
+    def get_cursor(self) -> Generator[Any, None, None]:
+        with self.connection_config.get_cursor() as cursor:
+            yield cursor
+
     @abstractmethod
     def query_db(self, file_data: SqlBatchFileData) -> tuple[list[tuple], list[str]]:
         pass
@@ -323,12 +333,17 @@ class SQLUploader(Uploader):
 
     def precheck(self) -> None:
         try:
-            with self.connection_config.get_cursor() as cursor:
+            with self.get_cursor() as cursor:
                 cursor.execute("SELECT 1;")
         except Exception as e:
             logger.error(f"failed to validate connection: {e}", exc_info=True)
             raise DestinationConnectionError(f"failed to validate connection: {e}")
 
+    @contextmanager
+    def get_cursor(self) -> Generator[Any, None, None]:
+        with self.connection_config.get_cursor() as cursor:
+            yield cursor
+
     def prepare_data(
         self, columns: list[str], data: tuple[tuple[Any, ...], ...]
     ) -> list[tuple[Any, ...]]:
@@ -346,7 +361,7 @@ class SQLUploader(Uploader):
             output.append(tuple(parsed))
         return output
 
-    def _fit_to_schema(self, df: pd.DataFrame, columns: list[str]) -> pd.DataFrame:
+    def _fit_to_schema(self, df: pd.DataFrame) -> pd.DataFrame:
         columns = set(df.columns)
         schema_fields = set(columns)
         columns_to_drop = columns - schema_fields
@@ -367,6 +382,7 @@ class SQLUploader(Uploader):
 
         for column in missing_columns:
             df[column] = pd.Series()
+        return df
 
     def upload_dataframe(self, df: pd.DataFrame, file_data: FileData) -> None:
         if self.can_delete():
@@ -378,7 +394,7 @@ class SQLUploader(Uploader):
                 f"{self.upload_config.record_id_key}, skipping delete"
             )
         df.replace({np.nan: None}, inplace=True)
-        self._fit_to_schema(df=df, columns=self.get_table_columns())
+        self._fit_to_schema(df=df)
 
         columns = list(df.columns)
         stmt = "INSERT INTO {table_name} ({columns}) VALUES({values})".format(
@@ -393,7 +409,7 @@ class SQLUploader(Uploader):
             f" with batch size {self.upload_config.batch_size}"
         )
         for rows in split_dataframe(df=df, chunk_size=self.upload_config.batch_size):
-            with self.connection_config.get_cursor() as cursor:
+            with self.get_cursor() as cursor:
                 values = self.prepare_data(columns, tuple(rows.itertuples(index=False, name=None)))
                 # For debugging purposes:
                 # for val in values:
@@ -406,7 +422,7 @@ class SQLUploader(Uploader):
                 cursor.executemany(stmt, values)
 
     def get_table_columns(self) -> list[str]:
-        with self.connection_config.get_cursor() as cursor:
+        with self.get_cursor() as cursor:
             cursor.execute(f"SELECT * from {self.upload_config.table_name}")
             return [desc[0] for desc in cursor.description]
 
@@ -420,10 +436,11 @@ class SQLUploader(Uploader):
             f"from table {self.upload_config.table_name}"
         )
         stmt = f"DELETE FROM {self.upload_config.table_name} WHERE {self.upload_config.record_id_key} = {self.values_delimiter}"  # noqa: E501
-        with self.connection_config.get_cursor() as cursor:
+        with self.get_cursor() as cursor:
             cursor.execute(stmt, [file_data.identifier])
             rowcount = cursor.rowcount
-            logger.info(f"deleted {rowcount} rows from table {self.upload_config.table_name}")
+            if rowcount > 0:
+                logger.info(f"deleted {rowcount} rows from table {self.upload_config.table_name}")
 
     def run_data(self, data: list[dict], file_data: FileData, **kwargs: Any) -> None:
         df = pd.DataFrame(data)

{unstructured_ingest-0.3.14.dist-info → unstructured_ingest-0.3.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unstructured-ingest
-Version: 0.3.14
+Version: 0.3.15
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,14 +22,14 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: python-dateutil
+Requires-Dist: ndjson
+Requires-Dist: pydantic>=2.7
 Requires-Dist: pandas
-Requires-Dist: tqdm
 Requires-Dist: dataclasses-json
-Requires-Dist: opentelemetry-sdk
+Requires-Dist: tqdm
 Requires-Dist: click
-Requires-Dist: ndjson
-Requires-Dist: pydantic>=2.7
+Requires-Dist: python-dateutil
+Requires-Dist: opentelemetry-sdk
 Provides-Extra: airtable
 Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
@@ -40,11 +40,11 @@ Requires-Dist: fsspec; extra == "azure"
 Provides-Extra: azure-ai-search
 Requires-Dist: azure-search-documents; extra == "azure-ai-search"
 Provides-Extra: bedrock
-Requires-Dist: boto3; extra == "bedrock"
 Requires-Dist: aioboto3; extra == "bedrock"
+Requires-Dist: boto3; extra == "bedrock"
 Provides-Extra: biomed
-Requires-Dist: requests; extra == "biomed"
 Requires-Dist: bs4; extra == "biomed"
+Requires-Dist: requests; extra == "biomed"
 Provides-Extra: box
 Requires-Dist: boxfs; extra == "box"
 Requires-Dist: fsspec; extra == "box"
@@ -59,6 +59,8 @@ Provides-Extra: couchbase
 Requires-Dist: couchbase; extra == "couchbase"
 Provides-Extra: csv
 Requires-Dist: unstructured[tsv]; extra == "csv"
+Provides-Extra: databricks-delta-tables
+Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
 Provides-Extra: databricks-volumes
 Requires-Dist: databricks-sdk; extra == "databricks-volumes"
 Provides-Extra: delta-table
@@ -71,8 +73,8 @@ Requires-Dist: unstructured[docx]; extra == "doc"
 Provides-Extra: docx
 Requires-Dist: unstructured[docx]; extra == "docx"
 Provides-Extra: dropbox
-Requires-Dist: fsspec; extra == "dropbox"
 Requires-Dist: dropboxdrivefs; extra == "dropbox"
+Requires-Dist: fsspec; extra == "dropbox"
 Provides-Extra: duckdb
 Requires-Dist: duckdb; extra == "duckdb"
 Provides-Extra: elasticsearch
@@ -82,8 +84,8 @@ Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-mixedbreadai
 Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
 Provides-Extra: embed-octoai
-Requires-Dist: openai; extra == "embed-octoai"
 Requires-Dist: tiktoken; extra == "embed-octoai"
+Requires-Dist: openai; extra == "embed-octoai"
 Provides-Extra: embed-vertexai
 Requires-Dist: vertexai; extra == "embed-vertexai"
 Provides-Extra: embed-voyageai
@@ -92,8 +94,8 @@ Provides-Extra: epub
 Requires-Dist: unstructured[epub]; extra == "epub"
 Provides-Extra: gcs
 Requires-Dist: bs4; extra == "gcs"
-Requires-Dist: fsspec; extra == "gcs"
 Requires-Dist: gcsfs; extra == "gcs"
+Requires-Dist: fsspec; extra == "gcs"
 Provides-Extra: github
 Requires-Dist: pygithub>1.58.0; extra == "github"
 Requires-Dist: requests; extra == "github"
@@ -122,22 +124,22 @@ Provides-Extra: msg
 Requires-Dist: unstructured[msg]; extra == "msg"
 Provides-Extra: neo4j
 Requires-Dist: cymple; extra == "neo4j"
-Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: neo4j; extra == "neo4j"
+Requires-Dist: networkx; extra == "neo4j"
 Provides-Extra: notion
+Requires-Dist: httpx; extra == "notion"
+Requires-Dist: htmlBuilder; extra == "notion"
 Requires-Dist: backoff; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
-Requires-Dist: htmlBuilder; extra == "notion"
-Requires-Dist: httpx; extra == "notion"
 Provides-Extra: odt
 Requires-Dist: unstructured[odt]; extra == "odt"
 Provides-Extra: onedrive
-Requires-Dist: bs4; extra == "onedrive"
 Requires-Dist: Office365-REST-Python-Client; 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"
+Requires-Dist: openai; extra == "openai"
 Provides-Extra: opensearch
 Requires-Dist: opensearch-py; extra == "opensearch"
 Provides-Extra: org
@@ -168,8 +170,8 @@ 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
@@ -183,16 +185,16 @@ 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: vectara
-Requires-Dist: requests; extra == "vectara"
-Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: httpx; extra == "vectara"
+Requires-Dist: aiofiles; extra == "vectara"
+Requires-Dist: requests; extra == "vectara"
 Provides-Extra: weaviate
 Requires-Dist: weaviate-client; extra == "weaviate"
 Provides-Extra: wikipedia

{unstructured_ingest-0.3.14.dist-info → unstructured_ingest-0.3.15.dist-info}/RECORD

@@ -16,7 +16,7 @@ test/integration/connectors/test_mongodb.py,sha256=0A6DvF-iTCSZzOefisd_i20j9li8u
 test/integration/connectors/test_neo4j.py,sha256=r4TRYtTXeeOdcRcfa_gvslhSKvoIWrwN1FRJ5XRoH4k,8456
 test/integration/connectors/test_notion.py,sha256=ueXyVqYWzP4LuZYe6PauptkXNG6qkoV3srltFOSSKTA,5403
 test/integration/connectors/test_onedrive.py,sha256=TcMaa5BIp8J6engS4UZ2t19WQP0NNz2rkpBB47m7A3Y,3835
-test/integration/connectors/test_pinecone.py,sha256=nzHwftPt-dPX4H5OrAJ6bs9qqOSOcfJL9jVEcWSPAqo,10325
+test/integration/connectors/test_pinecone.py,sha256=acKEu1vnAk0Ht3FhCnGtOEKaj_YlgCzZB7wRU17ehQ0,12407
 test/integration/connectors/test_qdrant.py,sha256=Yme3ZZ5zIbaZ-yYLUqN2oy0hsrcAfvlleRLYWMSYeSE,8049
 test/integration/connectors/test_redis.py,sha256=1aKwOb-K4zCxZwHmgW_WzGJwqLntbWTbpGQ-rtUwN9o,4360
 test/integration/connectors/test_s3.py,sha256=E1dypeag_E3OIfpQWIz3jb7ctRHRD63UtyTrzyvJzpc,7473
@@ -34,6 +34,7 @@ test/integration/connectors/elasticsearch/conftest.py,sha256=-i4_7MkIxSQENz7nuD2
 test/integration/connectors/elasticsearch/test_elasticsearch.py,sha256=TsSEPsyaTUoEvFBadinrdM0b5C4FoUtEwCv24OUbpO8,12072
 test/integration/connectors/elasticsearch/test_opensearch.py,sha256=7b7z0GqoBsBqA3IK35N6axmwEMjzJ1l3Fg2WT2c7uqs,11450
 test/integration/connectors/sql/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+test/integration/connectors/sql/test_databricks_delta_tables.py,sha256=UjVjw5hVoMSNJoYdoYympYow25gvcDAEHLmUmOJKz7I,5036
 test/integration/connectors/sql/test_postgres.py,sha256=bGDyzLRpgrXO7nl0U8nF2zSNr6ykUG-w8T4daIqUCG4,6970
 test/integration/connectors/sql/test_singlestore.py,sha256=XeU2s4Kt_3tGyaDYYKTgYjdOyb8j2dnz4TgSMwFUjWs,6153
 test/integration/connectors/sql/test_snowflake.py,sha256=LEwsRDoC6-rRiwYsqeo5B9Eo6RYygLLGAUsrtrgI9pM,7494
@@ -96,7 +97,7 @@ 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=F6lwOpOsFNj6MPWAGEZBkXIqf1jekdFZ5wZw3drsib8,43
+unstructured_ingest/__version__.py,sha256=31lJzr6gfqqAcVEa6C2kjStzBSJPXWUyP7eRpa8Y7gI,43
 unstructured_ingest/error.py,sha256=qDncnJgbf5ils956RcO2CGlAKYDT5OaEM9Clv1JVTNc,1448
 unstructured_ingest/interfaces.py,sha256=OYVUP0bzBJpT-Lz92BDyz_hLBvyfxkuSwWHhUdnUayA,31493
 unstructured_ingest/logger.py,sha256=S5nSqGcABoQyeicgRnBQFjDScCaTvFVivOCvbo-laL0,4479
@@ -386,7 +387,7 @@ unstructured_ingest/v2/interfaces/file_data.py,sha256=7MyRlj5dijQsCR6W18wQ8fEgJi
 unstructured_ingest/v2/interfaces/indexer.py,sha256=gsa1MLhFa82BzD2h4Yb7ons0VxRwKINZOrzvHAahwVU,846
 unstructured_ingest/v2/interfaces/process.py,sha256=BgglTu5K93FnDDopZKKr_rkK2LTZOguR6kcQjKHjF40,392
 unstructured_ingest/v2/interfaces/processor.py,sha256=VX7JqXlbG1plxMK8THWhWINPbTICaaUEk4XUXhnOixY,3303
-unstructured_ingest/v2/interfaces/upload_stager.py,sha256=HSSq_htv009-5yA8QqIi6rRnkfI1fnDkX5JRom8rNDY,3566
+unstructured_ingest/v2/interfaces/upload_stager.py,sha256=nbMuo_U6Gqn9bDJrAJTCjrZXKMw_G28OZOuNsT23i0k,3608
 unstructured_ingest/v2/interfaces/uploader.py,sha256=T2oHbN-d4Px1w1oATKKYZA10aUssqytEpiaqBM92r0Q,1600
 unstructured_ingest/v2/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 unstructured_ingest/v2/pipeline/interfaces.py,sha256=-Y6gPnl-SbNxIx5-dQCmiYSPKUMjivrRlBLIKIUWVeM,8658
@@ -427,19 +428,20 @@ 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=d6gC40YmfqBNXxizAt4MO4OOu5BoCZ7SAe1AbNwTP0E,18322
 unstructured_ingest/v2/processes/connectors/outlook.py,sha256=KgNGM8hImRhy6_SpswRP2VwRD4VOrqqJoySgxf2oduI,9290
-unstructured_ingest/v2/processes/connectors/pinecone.py,sha256=cohF7gBj0opSGKXlENSdGfTtyIKMHd1pwu4ydeb7JAY,10605
+unstructured_ingest/v2/processes/connectors/pinecone.py,sha256=bQDCch7OGiQgpWO3n3ncLuQ4XCWqDc7ZWEB-Qrqkss8,10730
 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=Ndn2Wm7RupfjAtlLxxQwJueeE0V8aGMbNVPuFq9nqdQ,19730
 unstructured_ingest/v2/processes/connectors/slack.py,sha256=Z73VmQ3oUY09KoLEi5OBdQeDt4ONEY_02SglWQc6HXE,9252
 unstructured_ingest/v2/processes/connectors/utils.py,sha256=8kd0g7lo9NqnpaIkjeO-Ut6erhwUNH_gS9koevpe3WE,878
 unstructured_ingest/v2/processes/connectors/vectara.py,sha256=BlI_4nkpNR99aYxDd9eusm5LQsVB9EI0r-5Kc1D7pgQ,12255
-unstructured_ingest/v2/processes/connectors/databricks/__init__.py,sha256=jO71UTC7bLA_N12CrLWJzh_yZML5gfT7VohxzCpUGWg,1848
-unstructured_ingest/v2/processes/connectors/databricks/volumes.py,sha256=MDnTUjFlqOP4rmQA5wkgT2DhwjhFhUwPpUPGSzqCOOE,7577
+unstructured_ingest/v2/processes/connectors/databricks/__init__.py,sha256=Oh8SwTWi66gO8BsNF6vRMoQVuegyBPPCpVozkOHEf3A,2136
+unstructured_ingest/v2/processes/connectors/databricks/volumes.py,sha256=Yj4fIxgGo9Qh1x_6-INdbrPGHCuZElu-QKNfSVtW7F4,7694
 unstructured_ingest/v2/processes/connectors/databricks/volumes_aws.py,sha256=TA2e_1SIr4VaEI62873eyReCNfgmQ51_2Pko2I04pPM,2747
 unstructured_ingest/v2/processes/connectors/databricks/volumes_azure.py,sha256=cb-EUW0T-linZMkbU6AcKEGWnFHQvhpO5Abtps4P2X0,3532
 unstructured_ingest/v2/processes/connectors/databricks/volumes_gcp.py,sha256=tR8NubkyHw49IpW_42g6w1Koxlm56EPiPf1lB-eoRSI,2783
 unstructured_ingest/v2/processes/connectors/databricks/volumes_native.py,sha256=dJLD1fueXf8_0AfC4cg0G7siJZVefz68iuEx2Kq7rMs,2890
+unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py,sha256=muj7G2JFO_WwAPub14k0VqDmN3c56t9MA60rM48wal8,4750
 unstructured_ingest/v2/processes/connectors/duckdb/__init__.py,sha256=5sVvJCWhU-YkjHIwk4W6BZCanFYK5W4xTpWtQ8xzeB4,561
 unstructured_ingest/v2/processes/connectors/duckdb/base.py,sha256=XTV9Pox3_xVmI8YVQWC9Bn6PugbPM49kp4Scv1OXFys,2649
 unstructured_ingest/v2/processes/connectors/duckdb/duckdb.py,sha256=oUHHaLpO2pWW2Lu4Mc-XFjrA0ze97205WQ_xP95ua4M,4296
@@ -538,20 +540,21 @@ unstructured_ingest/v2/processes/connectors/qdrant/cloud.py,sha256=accJ4sNWBVWV-
 unstructured_ingest/v2/processes/connectors/qdrant/local.py,sha256=cGEyv3Oy6y4BQ4DU8yhJWMpL82QYwBVdPTxxNuV127U,1588
 unstructured_ingest/v2/processes/connectors/qdrant/qdrant.py,sha256=BHI7HYSdbS05j2vrjyDvLzVG1WfsM8osKeq-lttlybQ,5437
 unstructured_ingest/v2/processes/connectors/qdrant/server.py,sha256=odvCZWZp8DmRxLXMR7tHhW-c7UQbix1_zpFdfXfCvKI,1613
-unstructured_ingest/v2/processes/connectors/sql/__init__.py,sha256=E16CXRBw8fZKTuXIECns5wif_I07oncBHskVxHC4p7w,1448
+unstructured_ingest/v2/processes/connectors/sql/__init__.py,sha256=mxcrncrjeP-C2jqQoTOOpGjV3Bmyfg4efT5lq_c-V1E,1760
+unstructured_ingest/v2/processes/connectors/sql/databricks_delta_tables.py,sha256=s_W6wSvyIXZ9mdAxvgSXFeFSze9E7pwIvc38p1hVDLM,8839
 unstructured_ingest/v2/processes/connectors/sql/postgres.py,sha256=BATfX1PQGT2kl8jAbdNKXTojYKJxh3pJV9-h3OBnHGo,5124
 unstructured_ingest/v2/processes/connectors/sql/singlestore.py,sha256=-2E9dsdNhjAiuzeSBytBbAhljOhvQ8kN8wvlUESvLo8,5465
 unstructured_ingest/v2/processes/connectors/sql/snowflake.py,sha256=8qCm1XiJmVxy8TSeoxwmQrE2W1x8S8At2ctrS_lJ8-I,7780
-unstructured_ingest/v2/processes/connectors/sql/sql.py,sha256=FtI5DSMd1QUgoYLn8NAVoETc4qwCbFEwSulqziXyODY,15292
+unstructured_ingest/v2/processes/connectors/sql/sql.py,sha256=ZGpeBfiOEzVaSiQxwqJkMC00Eu6TQhsrZKHnOHM0Xug,15667
 unstructured_ingest/v2/processes/connectors/sql/sqlite.py,sha256=Q5RAqn5Ccw-pbeKZLkiMn5IVw6EemCMukXzLlS7pDhc,5162
 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=X1yv1H_orDQ-J965EMXhR2XaURqe8vovSi9n1fk85B4,10499
-unstructured_ingest-0.3.14.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
-unstructured_ingest-0.3.14.dist-info/METADATA,sha256=PiIp0oqW-sia84q3v0SXUGy-Oh0fzUZCmZqBogsg7qA,7813
-unstructured_ingest-0.3.14.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-unstructured_ingest-0.3.14.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
-unstructured_ingest-0.3.14.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
-unstructured_ingest-0.3.14.dist-info/RECORD,,
+unstructured_ingest-0.3.15.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
+unstructured_ingest-0.3.15.dist-info/METADATA,sha256=rZFAbiv0HZ-VUWVk4MP2vANZuzsxJLhK2_QWZ5zTjRA,7929
+unstructured_ingest-0.3.15.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+unstructured_ingest-0.3.15.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
+unstructured_ingest-0.3.15.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
+unstructured_ingest-0.3.15.dist-info/RECORD,,