unstructured-ingest 0.3.14__tar.gz → 0.3.15__tar.gz

{unstructured_ingest-0.3.14/unstructured_ingest.egg-info → unstructured_ingest-0.3.15}/PKG-INFO

@@ -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: opentelemetry-sdk
-Requires-Dist: tqdm
 Requires-Dist: pandas
-Requires-Dist: python-dateutil
-Requires-Dist: pydantic>=2.7
+Requires-Dist: tqdm
+Requires-Dist: click
 Requires-Dist: ndjson
 Requires-Dist: dataclasses_json
-Requires-Dist: click
+Requires-Dist: pydantic>=2.7
+Requires-Dist: opentelemetry-sdk
+Requires-Dist: python-dateutil
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.26.1; extra == "remote"
 Provides-Extra: csv
@@ -67,13 +67,13 @@ Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
 Requires-Dist: astrapy; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: fsspec; extra == "azure"
 Requires-Dist: adlfs; extra == "azure"
+Requires-Dist: fsspec; extra == "azure"
 Provides-Extra: azure-ai-search
 Requires-Dist: azure-search-documents; extra == "azure-ai-search"
 Provides-Extra: biomed
-Requires-Dist: bs4; 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"
@@ -82,8 +82,8 @@ Requires-Dist: chromadb; extra == "chroma"
 Provides-Extra: clarifai
 Requires-Dist: clarifai; extra == "clarifai"
 Provides-Extra: confluence
-Requires-Dist: atlassian-python-api; extra == "confluence"
 Requires-Dist: requests; extra == "confluence"
+Requires-Dist: atlassian-python-api; extra == "confluence"
 Provides-Extra: couchbase
 Requires-Dist: couchbase; extra == "couchbase"
 Provides-Extra: delta-table
@@ -92,8 +92,8 @@ Requires-Dist: deltalake; extra == "delta-table"
 Provides-Extra: discord
 Requires-Dist: discord.py; extra == "discord"
 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
@@ -110,8 +110,8 @@ Requires-Dist: python-gitlab; extra == "gitlab"
 Provides-Extra: google-drive
 Requires-Dist: google-api-python-client; extra == "google-drive"
 Provides-Extra: hubspot
-Requires-Dist: hubspot-api-client; extra == "hubspot"
 Requires-Dist: urllib3; extra == "hubspot"
+Requires-Dist: hubspot-api-client; extra == "hubspot"
 Provides-Extra: jira
 Requires-Dist: atlassian-python-api; extra == "jira"
 Provides-Extra: kafka
@@ -130,18 +130,18 @@ Requires-Dist: neo4j; extra == "neo4j"
 Requires-Dist: cymple; extra == "neo4j"
 Provides-Extra: notion
 Requires-Dist: notion-client; extra == "notion"
-Requires-Dist: backoff; extra == "notion"
 Requires-Dist: httpx; extra == "notion"
+Requires-Dist: backoff; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
 Provides-Extra: onedrive
-Requires-Dist: bs4; extra == "onedrive"
-Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Requires-Dist: msal; extra == "onedrive"
+Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
+Requires-Dist: bs4; extra == "onedrive"
 Provides-Extra: opensearch
 Requires-Dist: opensearch-py; extra == "opensearch"
 Provides-Extra: outlook
-Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
 Requires-Dist: msal; extra == "outlook"
+Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
 Provides-Extra: pinecone
 Requires-Dist: pinecone-client>=3.7.1; extra == "pinecone"
 Provides-Extra: postgres
@@ -156,13 +156,13 @@ Provides-Extra: s3
 Requires-Dist: s3fs; extra == "s3"
 Requires-Dist: fsspec; extra == "s3"
 Provides-Extra: sharepoint
-Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
 Requires-Dist: msal; extra == "sharepoint"
+Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
 Provides-Extra: salesforce
 Requires-Dist: simple-salesforce; extra == "salesforce"
 Provides-Extra: sftp
-Requires-Dist: fsspec; extra == "sftp"
 Requires-Dist: paramiko; extra == "sftp"
+Requires-Dist: fsspec; extra == "sftp"
 Provides-Extra: slack
 Requires-Dist: slack_sdk[optional]; extra == "slack"
 Provides-Extra: snowflake
@@ -174,17 +174,19 @@ Provides-Extra: weaviate
 Requires-Dist: weaviate-client; extra == "weaviate"
 Provides-Extra: databricks-volumes
 Requires-Dist: databricks-sdk; extra == "databricks-volumes"
+Provides-Extra: databricks-delta-tables
+Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
 Provides-Extra: singlestore
 Requires-Dist: singlestoredb; extra == "singlestore"
 Provides-Extra: vectara
 Requires-Dist: requests; extra == "vectara"
-Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: httpx; extra == "vectara"
+Requires-Dist: aiofiles; extra == "vectara"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
-Requires-Dist: tiktoken; extra == "embed-octoai"
 Requires-Dist: openai; extra == "embed-octoai"
+Requires-Dist: tiktoken; extra == "embed-octoai"
 Provides-Extra: embed-vertexai
 Requires-Dist: vertexai; extra == "embed-vertexai"
 Provides-Extra: embed-voyageai
@@ -192,11 +194,11 @@ Requires-Dist: voyageai; extra == "embed-voyageai"
 Provides-Extra: embed-mixedbreadai
 Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
 Provides-Extra: openai
-Requires-Dist: tiktoken; extra == "openai"
 Requires-Dist: openai; extra == "openai"
+Requires-Dist: tiktoken; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: boto3; extra == "bedrock"
 Requires-Dist: aioboto3; extra == "bedrock"
+Requires-Dist: boto3; extra == "bedrock"
 Provides-Extra: togetherai
 Requires-Dist: together; extra == "togetherai"
 

{unstructured_ingest-0.3.14 → unstructured_ingest-0.3.15}/pyproject.toml

@@ -18,7 +18,7 @@ exclude= [
     "venv",
     ".python_packages",
     "build",
-    "migrations"
+    "migrations",
 ]
 
 [tool.ruff.lint]

{unstructured_ingest-0.3.14 → unstructured_ingest-0.3.15}/setup.py

@@ -127,6 +127,9 @@ connectors_reqs = {
     "wikipedia": load_requirements("requirements/connectors/wikipedia.in"),
     "weaviate": load_requirements("requirements/connectors/weaviate.in"),
     "databricks-volumes": load_requirements("requirements/connectors/databricks-volumes.in"),
+    "databricks-delta-tables": load_requirements(
+        "requirements/connectors/databricks-delta-tables.in"
+    ),
     "singlestore": load_requirements("requirements/connectors/singlestore.in"),
     "vectara": load_requirements("requirements/connectors/vectara.in"),
 }

unstructured_ingest-0.3.15/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)

{unstructured_ingest-0.3.14 → unstructured_ingest-0.3.15}/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-0.3.15/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.3.15"  # pragma: no cover

{unstructured_ingest-0.3.14 → unstructured_ingest-0.3.15}/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-0.3.14 → unstructured_ingest-0.3.15}/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-0.3.14 → unstructured_ingest-0.3.15}/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-0.3.15/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-0.3.14 → unstructured_ingest-0.3.15}/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-0.3.14 → unstructured_ingest-0.3.15}/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,
+)