unstructured-ingest 0.7.2__py3-none-any.whl → 1.0.2__py3-none-any.whl

unstructured_ingest/__version__.py

@@ -1 +1 @@
-__version__ = "0.7.2"  # pragma: no cover
+__version__ = "1.0.2"  # pragma: no cover

unstructured_ingest/cli/README.md

@@ -0,0 +1,28 @@
+# Ingest CLI
+This package helps map user input via a cli to the underlying ingest code to run a small ETL pipeline.
+
+## Design Reference
+[cli.py](cli.py) is the main entrypoint to run the cli itself. The key points for this is the interaction between all
+source and destination connectors.
+
+To manually run the cli:
+```shell
+PYTHONPATH=. python unstructured_ingest/v2/main.py --help
+```
+
+The `main.py` file simply wraps the generated Click command created in `cli.py`.
+
+### Source Commands
+All source commands are added as sub commands to the parent ingest Click group. This allows each command to map to
+different connectors with shared and unique parameters.
+
+### Destination Commands
+All destination commands are added as sub commands to each parent source command. This allows each invocation of the source
+sub command to display all possible destination subcommands. The code un [utils.py](./utils.py) helps structure the
+generated text from the Click library to be more intuitive on this approach (i.e. list sub commands as  `Destinations`).
+
+### Configs
+The configs in [configs/](./configs) and connector specific ones in [cmds/](./cmds) help surface all user parameters that
+are needed to marshall the input dictionary from Click into all the respective configs needed to create a full pipeline run.
+Because click returns a flat dictionary of user inputs, the `extract_config` method in `utils.py` helps deserialize this dictionary
+into dataclasses that have nested fields (such as access configs).

unstructured_ingest/embed/mixedbreadai.py

@@ -114,7 +114,6 @@ class MixedbreadAIEmbeddingEncoder(BaseEmbeddingEncoder):
 
 @dataclass
 class AsyncMixedbreadAIEmbeddingEncoder(AsyncBaseEmbeddingEncoder):
-
     config: MixedbreadAIEmbeddingConfig
 
     async def get_exemplary_embedding(self) -> list[float]:

unstructured_ingest/interfaces/upload_stager.py

@@ -8,7 +8,7 @@ from pydantic import BaseModel
 from unstructured_ingest.data_types.file_data import FileData
 from unstructured_ingest.interfaces import BaseProcess
 from unstructured_ingest.utils import ndjson
-from unstructured_ingest.utils.data_prep import get_data, write_data
+from unstructured_ingest.utils.data_prep import get_json_data, write_data
 
 
 class UploadStagerConfig(BaseModel):
@@ -43,7 +43,7 @@ class UploadStager(BaseProcess, ABC):
                     writer.f.flush()
 
     def process_whole(self, input_file: Path, output_file: Path, file_data: FileData) -> None:
-        elements_contents = get_data(path=input_file)
+        elements_contents = get_json_data(path=input_file)
 
         conformed_elements = [
             self.conform_dict(element_dict=element, file_data=file_data)

unstructured_ingest/interfaces/uploader.py

@@ -7,7 +7,7 @@ from pydantic import BaseModel
 
 from unstructured_ingest.data_types.file_data import FileData
 from unstructured_ingest.interfaces import BaseConnector, BaseProcess
-from unstructured_ingest.utils.data_prep import get_data
+from unstructured_ingest.utils.data_prep import get_json_data
 
 
 class UploaderConfig(BaseModel):
@@ -45,11 +45,11 @@ class Uploader(BaseProcess, BaseConnector, ABC):
         return False
 
     def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
-        data = get_data(path=path)
+        data = get_json_data(path=path)
         self.run_data(data=data, file_data=file_data, **kwargs)
 
     async def run_async(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
-        data = get_data(path=path)
+        data = get_json_data(path=path)
         await self.run_data_async(data=data, file_data=file_data, **kwargs)
 
     def run_data(self, data: list[dict], file_data: FileData, **kwargs: Any) -> None:

unstructured_ingest/pipeline/interfaces.py

@@ -119,7 +119,7 @@ class PipelineStep(ABC):
         iterable = iterable or []
         if iterable:
             logger.info(
-                f"calling {self.__class__.__name__} " f"with {len(iterable)} docs",  # type: ignore
+                f"calling {self.__class__.__name__} with {len(iterable)} docs",  # type: ignore
             )
         else:
             logger.info(f"calling {self.__class__.__name__} with no inputs")

unstructured_ingest/pipeline/pipeline.py

@@ -220,7 +220,7 @@ class Pipeline:
 
     def _run(self):
         logger.info(
-            f"running local pipeline: {self} with configs: " f"{self.context.model_dump_json()}"
+            f"running local pipeline: {self} with configs: {self.context.model_dump_json()}"
         )
         if self.context.mp_supported:
             manager = mp.Manager()

unstructured_ingest/processes/chunker.py

@@ -24,6 +24,9 @@ class ChunkerConfig(BaseModel):
         default="https://api.unstructuredapp.io/general/v0/general",
         description="If chunking via api, use the following host.",
     )
+    chunk_api_timeout_ms: Optional[int] = Field(
+        default=None, description="Timeout in milliseconds for all api call during chunking."
+    )
     chunk_by_api: bool = Field(default=False, description="Flag to use api for chunking")
     chunk_api_key: Optional[SecretStr] = Field(
         default=None, description="API Key for chunking endpoint."
@@ -120,6 +123,7 @@ class Chunker(BaseProcess, ABC):
             api_key=self.config.chunk_api_key.get_secret_value(),
             filename=elements_filepath,
             api_parameters=self.config.to_chunking_kwargs(),
+            timeout_ms=self.config.chunk_api_timeout_ms,
         )
 
         elements = assign_and_map_hash_ids(elements=elements)

unstructured_ingest/processes/connectors/airtable.py

@@ -3,7 +3,6 @@ from pathlib import Path
 from typing import TYPE_CHECKING, Any, Generator, Optional
 from uuid import NAMESPACE_DNS, uuid5
 
-import pandas
 from pydantic import BaseModel, Field, Secret, field_validator
 
 from unstructured_ingest.data_types.file_data import FileData, SourceIdentifiers
@@ -213,10 +212,13 @@ class AirtableDownloader(Downloader):
         row_dict.update(table_row["fields"])
         return row_dict
 
+    @requires_dependencies(["pandas"], extras="airtable")
     def run(self, file_data: FileData, **kwargs: Any) -> DownloadResponse:
+        import pandas as pd
+
         table_meta = AirtableTableMeta.model_validate(file_data.additional_metadata)
         table_contents = self.get_table_contents(table_meta=table_meta)
-        df = pandas.DataFrame.from_dict(
+        df = pd.DataFrame.from_dict(
             data=[self._table_row_to_dict(table_row=row) for row in table_contents]
         ).sort_index(axis=1)
         download_path = self.get_download_path(file_data=file_data)

unstructured_ingest/processes/connectors/astradb.py

@@ -1,5 +1,7 @@
+import asyncio
 import csv
 import hashlib
+import os
 import re
 from dataclasses import dataclass, field
 from pathlib import Path
@@ -8,7 +10,6 @@ from typing import TYPE_CHECKING, Any, Generator, Optional
 
 from pydantic import BaseModel, Field, Secret
 
-from unstructured_ingest import __name__ as integration_name
 from unstructured_ingest.__version__ import __version__ as integration_version
 from unstructured_ingest.data_types.file_data import (
     BatchFileData,
@@ -43,7 +44,7 @@ from unstructured_ingest.processes.connector_registry import (
 )
 from unstructured_ingest.processes.connectors.utils import format_and_truncate_orig_elements
 from unstructured_ingest.utils.constants import RECORD_ID_LABEL
-from unstructured_ingest.utils.data_prep import batch_generator, get_data
+from unstructured_ingest.utils.data_prep import batch_generator, get_json_data
 from unstructured_ingest.utils.dep_check import requires_dependencies
 from unstructured_ingest.utils.string_and_date_utils import truncate_string_bytes
 
@@ -83,10 +84,8 @@ class AstraDBConnectionConfig(ConnectionConfig):
 
         # Create a client object to interact with the Astra DB
         # caller_name/version for Astra DB tracking
-        return AstraDBClient(
-            caller_name=integration_name,
-            caller_version=integration_version,
-        )
+        user_agent = os.getenv("UNSTRUCTURED_USER_AGENT", "unstructuredio_oss")
+        return AstraDBClient(callers=[(user_agent, integration_version)])
 
 
 def get_astra_db(
@@ -141,7 +140,7 @@ async def get_async_astra_collection(
     )
 
     # Get async collection from AsyncDatabase
-    async_astra_db_collection = await async_astra_db.get_collection(name=collection_name)
+    async_astra_db_collection = async_astra_db.get_collection(name=collection_name)
     return async_astra_db_collection
 
 
@@ -360,13 +359,22 @@ class AstraDBUploader(Uploader):
     upload_config: AstraDBUploaderConfig
     connector_type: str = CONNECTOR_TYPE
 
+    def is_async(self) -> bool:
+        return True
+
     def init(self, **kwargs: Any) -> None:
         self.create_destination(**kwargs)
 
+    @requires_dependencies(["astrapy"], extras="astradb")
     def precheck(self) -> None:
         try:
             if self.upload_config.collection_name:
-                self.get_collection(collection_name=self.upload_config.collection_name).options()
+                collection = get_astra_collection(
+                    connection_config=self.connection_config,
+                    collection_name=self.upload_config.collection_name,
+                    keyspace=self.upload_config.keyspace,
+                )
+                collection.options()
             else:
                 # check for db connection only if collection name is not provided
                 get_astra_db(
@@ -377,17 +385,7 @@ class AstraDBUploader(Uploader):
             logger.error(f"Failed to validate connection {e}", exc_info=True)
             raise DestinationConnectionError(f"failed to validate connection: {e}")
 
-    @requires_dependencies(["astrapy"], extras="astradb")
-    def get_collection(self, collection_name: Optional[str] = None) -> "AstraDBCollection":
-        return get_astra_collection(
-            connection_config=self.connection_config,
-            collection_name=collection_name or self.upload_config.collection_name,
-            keyspace=self.upload_config.keyspace,
-        )
-
     def _collection_exists(self, collection_name: str):
-        from astrapy.exceptions import CollectionNotFoundException
-
         collection = get_astra_collection(
             connection_config=self.connection_config,
             collection_name=collection_name,
@@ -397,8 +395,10 @@ class AstraDBUploader(Uploader):
         try:
             collection.options()
             return True
-        except CollectionNotFoundException:
-            return False
+        except RuntimeError as e:
+            if "not found" in str(e):
+                return False
+            raise DestinationConnectionError(f"failed to check if astra collection exists : {e}")
         except Exception as e:
             logger.error(f"failed to check if astra collection exists : {e}")
             raise DestinationConnectionError(f"failed to check if astra collection exists : {e}")
@@ -422,6 +422,8 @@ class AstraDBUploader(Uploader):
         self.upload_config.collection_name = collection_name
 
         if not self._collection_exists(collection_name):
+            from astrapy.info import CollectionDefinition
+
             astra_db = get_astra_db(
                 connection_config=self.connection_config, keyspace=self.upload_config.keyspace
             )
@@ -429,44 +431,56 @@ class AstraDBUploader(Uploader):
                 f"creating default astra collection '{collection_name}' with dimension "
                 f"{vector_length} and metric {similarity_metric}"
             )
-            astra_db.create_collection(
-                collection_name,
-                dimension=vector_length,
-                metric=similarity_metric,
+            definition = (
+                CollectionDefinition.builder()
+                .set_vector_dimension(dimension=vector_length)
+                .set_vector_metric(similarity_metric)
+                .build()
             )
+            (astra_db.create_collection(collection_name, definition=definition),)
             return True
         logger.debug(f"collection with name '{collection_name}' already exists, skipping creation")
         return False
 
-    def delete_by_record_id(self, collection: "AstraDBCollection", file_data: FileData):
+    async def delete_by_record_id(self, collection: "AstraDBAsyncCollection", file_data: FileData):
         logger.debug(
             f"deleting records from collection {collection.name} "
             f"with {self.upload_config.record_id_key} "
             f"set to {file_data.identifier}"
         )
         delete_filter = {self.upload_config.record_id_key: {"$eq": file_data.identifier}}
-        delete_resp = collection.delete_many(filter=delete_filter)
+        delete_resp = await collection.delete_many(filter=delete_filter)
         logger.debug(
             f"deleted {delete_resp.deleted_count} records from collection {collection.name}"
         )
 
-    def run_data(self, data: list[dict], file_data: FileData, **kwargs: Any) -> None:
+    async def run_data(self, data: list[dict], file_data: FileData, **kwargs: Any) -> None:
         logger.info(
             f"writing {len(data)} objects to destination "
             f"collection {self.upload_config.collection_name}"
         )
 
         astra_db_batch_size = self.upload_config.batch_size
-        collection = self.get_collection()
+        async_astra_collection = await get_async_astra_collection(
+            connection_config=self.connection_config,
+            collection_name=self.upload_config.collection_name,
+            keyspace=self.upload_config.keyspace,
+        )
 
-        self.delete_by_record_id(collection=collection, file_data=file_data)
+        await self.delete_by_record_id(collection=async_astra_collection, file_data=file_data)
+        await asyncio.gather(
+            *[
+                async_astra_collection.insert_many(chunk)
+                for chunk in batch_generator(data, astra_db_batch_size)
+            ]
+        )
 
-        for chunk in batch_generator(data, astra_db_batch_size):
-            collection.insert_many(chunk)
+    async def run_async(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
+        data = get_json_data(path=path)
+        await self.run_data(data=data, file_data=file_data)
 
-    def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
-        data = get_data(path=path)
-        self.run_data(data=data, file_data=file_data, **kwargs)
+    def run(self, **kwargs: Any) -> Any:
+        raise NotImplementedError("Use astradb run_async instead")
 
 
 astra_db_source_entry = SourceRegistryEntry(

unstructured_ingest/processes/connectors/azure_ai_search.py

@@ -212,7 +212,7 @@ class AzureAISearchUploader(Uploader):
             raise WriteError(
                 ", ".join(
                     [
-                        f"{error.key}: " f"[{error.status_code}] {error.error_message}"
+                        f"{error.key}: [{error.status_code}] {error.error_message}"
                         for error in errors
                     ],
                 ),

unstructured_ingest/processes/connectors/confluence.py

@@ -125,7 +125,6 @@ class ConfluenceIndexer(Indexer):
 
     def precheck(self) -> bool:
         try:
-
             # Attempt to retrieve a list of spaces with limit=1.
             # This should only succeed if all creds are valid
             with self.connection_config.get_client() as client:

unstructured_ingest/processes/connectors/databricks/volumes_aws.py

@@ -28,7 +28,7 @@ CONNECTOR_TYPE = "databricks_volumes_aws"
 class DatabricksAWSVolumesAccessConfig(DatabricksVolumesAccessConfig):
     account_id: Optional[str] = Field(
         default=None,
-        description="The Databricks account ID for the Databricks " "accounts endpoint",
+        description="The Databricks account ID for the Databricks accounts endpoint",
     )
     profile: Optional[str] = None
     token: Optional[str] = Field(

unstructured_ingest/processes/connectors/databricks/volumes_azure.py

@@ -28,7 +28,7 @@ CONNECTOR_TYPE = "databricks_volumes_azure"
 class DatabricksAzureVolumesAccessConfig(DatabricksVolumesAccessConfig):
     account_id: Optional[str] = Field(
         default=None,
-        description="The Databricks account ID for the Databricks " "accounts endpoint.",
+        description="The Databricks account ID for the Databricks accounts endpoint.",
     )
     profile: Optional[str] = None
     azure_workspace_resource_id: Optional[str] = Field(
@@ -47,7 +47,7 @@ class DatabricksAzureVolumesAccessConfig(DatabricksVolumesAccessConfig):
     )
     azure_environment: Optional[str] = Field(
         default=None,
-        description="The Azure environment type for a " "specific set of API endpoints",
+        description="The Azure environment type for a specific set of API endpoints",
         examples=["Public", "UsGov", "China", "Germany"],
     )
 

unstructured_ingest/processes/connectors/databricks/volumes_gcp.py

@@ -28,7 +28,7 @@ CONNECTOR_TYPE = "databricks_volumes_gcp"
 class DatabricksGoogleVolumesAccessConfig(DatabricksVolumesAccessConfig):
     account_id: Optional[str] = Field(
         default=None,
-        description="The Databricks account ID for the Databricks " "accounts endpoint.",
+        description="The Databricks account ID for the Databricks accounts endpoint.",
     )
     profile: Optional[str] = None
     google_credentials: Optional[str] = None

unstructured_ingest/processes/connectors/databricks/volumes_table.py

@@ -166,8 +166,7 @@ class DatabricksVolumeDeltaTableUploader(Uploader):
             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 "
-                f"table {self.upload_config.table_name}"
+                f"migrating content from {catalog_path} to table {self.upload_config.table_name}"
             )
             data = get_json_data(path=path)
             columns = data[0].keys()

unstructured_ingest/processes/connectors/delta_table.py

@@ -181,6 +181,7 @@ class DeltaTableUploader(Uploader):
         df = pd.DataFrame(data=data)
         self.upload_dataframe(df=df, file_data=file_data)
 
+    @requires_dependencies(["pandas"], extras="delta-table")
     def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
         df = get_data_df(path)
         self.upload_dataframe(df=df, file_data=file_data)

unstructured_ingest/processes/connectors/duckdb/base.py

@@ -4,7 +4,7 @@ from typing import Any
 
 from unstructured_ingest.data_types.file_data import FileData
 from unstructured_ingest.interfaces import UploadStager
-from unstructured_ingest.utils.data_prep import get_data, get_enhanced_element_id, write_data
+from unstructured_ingest.utils.data_prep import get_enhanced_element_id, get_json_data, write_data
 from unstructured_ingest.utils.dep_check import requires_dependencies
 
 _COLUMNS = (
@@ -81,7 +81,7 @@ class BaseDuckDBUploadStager(UploadStager):
     ) -> Path:
         import pandas as pd
 
-        elements_contents = get_data(path=elements_filepath)
+        elements_contents = get_json_data(path=elements_filepath)
         output_filename_suffix = Path(elements_filepath).suffix
         output_filename = f"{Path(output_filename).stem}{output_filename_suffix}"
         output_path = self.get_output_path(output_filename=output_filename, output_dir=output_dir)

unstructured_ingest/processes/connectors/duckdb/duckdb.py

@@ -67,9 +67,8 @@ class DuckDBConnectionConfig(ConnectionConfig):
 
     @contextmanager
     def get_cursor(self) -> Generator["DuckDBConnection", None, None]:
-        with self.get_client() as client:
-            with client.cursor() as cursor:
-                yield cursor
+        with self.get_client() as client, client.cursor() as cursor:
+            yield cursor
 
 
 class DuckDBUploadStagerConfig(UploadStagerConfig):
@@ -116,6 +115,7 @@ class DuckDBUploader(Uploader):
         df = pd.DataFrame(data=data)
         self.upload_dataframe(df=df)
 
+    @requires_dependencies(["pandas"], extras="duckdb")
     def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
         df = get_data_df(path)
         self.upload_dataframe(df=df)

unstructured_ingest/processes/connectors/duckdb/motherduck.py

@@ -66,9 +66,8 @@ class MotherDuckConnectionConfig(ConnectionConfig):
 
     @contextmanager
     def get_cursor(self) -> Generator["MotherDuckConnection", None, None]:
-        with self.get_client() as client:
-            with client.cursor() as cursor:
-                yield cursor
+        with self.get_client() as client, client.cursor() as cursor:
+            yield cursor
 
 
 class MotherDuckUploadStagerConfig(UploadStagerConfig):
@@ -116,6 +115,7 @@ class MotherDuckUploader(Uploader):
         df = pd.DataFrame(data=data)
         self.upload_dataframe(df=df)
 
+    @requires_dependencies(["pandas"], extras="duckdb")
     def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
         df = get_data_df(path)
         self.upload_dataframe(df=df)

unstructured_ingest/processes/connectors/fsspec/s3.py

@@ -134,9 +134,11 @@ class S3Indexer(FsspecIndexer):
 
         version = file_info.get("ETag").rstrip('"').lstrip('"') if "ETag" in file_info else None
         metadata: dict[str, str] = {}
-        with contextlib.suppress(AttributeError):
-            with self.connection_config.get_client(protocol=self.index_config.protocol) as client:
-                metadata = client.metadata(path=path)
+        with (
+            contextlib.suppress(AttributeError),
+            self.connection_config.get_client(protocol=self.index_config.protocol) as client,
+        ):
+            metadata = client.metadata(path=path)
         record_locator = {
             "protocol": self.index_config.protocol,
             "remote_file_path": self.index_config.remote_url,

unstructured_ingest/processes/connectors/gitlab.py

@@ -230,8 +230,7 @@ class GitLabDownloader(Downloader):
         download_path = self.get_download_path(file_data=file_data)
         if download_path is None:
             logger.error(
-                "Generated download path is None, source_identifiers might be missing"
-                "from FileData."
+                "Generated download path is None, source_identifiers might be missingfrom FileData."
             )
             raise ValueError("Generated invalid download path.")
 

unstructured_ingest/processes/connectors/google_drive.py

@@ -334,7 +334,6 @@ class GoogleDriveIndexer(Indexer):
         recursive: bool = False,
         previous_path: Optional[str] = None,
     ) -> list[dict]:
-
         fields_input = "nextPageToken, files({})".format(",".join(self.fields))
         q = f"'{object_id}' in parents"
         # Filter by extension but still include any directories
@@ -394,7 +393,6 @@ class GoogleDriveIndexer(Indexer):
         if not self.is_dir(root_info):
             data = [self.map_file_data(root_info)]
         else:
-
             file_contents = self.get_paginated_results(
                 files_client=files_client,
                 object_id=object_id,

unstructured_ingest/processes/connectors/ibm_watsonx/ibm_watsonx_s3.py

@@ -5,7 +5,6 @@ from dataclasses import dataclass, field
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Generator, Optional, Tuple
 
-import pandas as pd
 from pydantic import Field, Secret
 
 from unstructured_ingest.data_types.file_data import FileData
@@ -29,6 +28,7 @@ from unstructured_ingest.utils.data_prep import get_data_df
 from unstructured_ingest.utils.dep_check import requires_dependencies
 
 if TYPE_CHECKING:
+    from pandas import DataFrame
     from pyarrow import Table as ArrowTable
     from pyiceberg.catalog.rest import RestCatalog
     from pyiceberg.table import Table, Transaction
@@ -96,14 +96,12 @@ class IbmWatsonxConnectionConfig(ConnectionConfig):
             return UserAuthError(e)
         if 400 <= response_code < 500:
             logger.error(
-                f"Request to {url} failed"
-                f"in IBM watsonx.data connector, status code {response_code}"
+                f"Request to {url} failedin IBM watsonx.data connector, status code {response_code}"
             )
             return UserError(e)
         if response_code > 500:
             logger.error(
-                f"Request to {url} failed"
-                f"in IBM watsonx.data connector, status code {response_code}"
+                f"Request to {url} failedin IBM watsonx.data connector, status code {response_code}"
             )
             return ProviderError(e)
         logger.error(f"Unhandled exception from IBM watsonx.data connector: {e}", exc_info=True)
@@ -217,7 +215,7 @@ class IbmWatsonxUploader(SQLUploader):
         return self.upload_config.record_id_key in self.get_table_columns()
 
     @requires_dependencies(["pyarrow"], extras="ibm-watsonx-s3")
-    def _df_to_arrow_table(self, df: pd.DataFrame) -> "ArrowTable":
+    def _df_to_arrow_table(self, df: "DataFrame") -> "ArrowTable":
         import pyarrow as pa
 
         # Iceberg will automatically fill missing columns with nulls
@@ -277,16 +275,20 @@ class IbmWatsonxUploader(SQLUploader):
         except Exception as e:
             raise ProviderError(f"Failed to upload data to table: {e}")
 
-    def upload_dataframe(self, df: pd.DataFrame, file_data: FileData) -> None:
+    def upload_dataframe(self, df: "DataFrame", file_data: FileData) -> None:
         data_table = self._df_to_arrow_table(df)
 
         with self.get_table() as table:
             self.upload_data_table(table, data_table, file_data)
 
+    @requires_dependencies(["pandas"], extras="ibm-watsonx-s3")
     def run_data(self, data: list[dict], file_data: FileData, **kwargs: Any) -> None:
+        import pandas as pd
+
         df = pd.DataFrame(data)
         self.upload_dataframe(df=df, file_data=file_data)
 
+    @requires_dependencies(["pandas"], extras="ibm-watsonx-s3")
     def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
         df = get_data_df(path=path)
         self.upload_dataframe(df=df, file_data=file_data)

unstructured_ingest/processes/connectors/kdbai.py

@@ -141,6 +141,7 @@ class KdbaiUploader(Uploader):
         df = pd.DataFrame(data=data)
         self.process_dataframe(df=df)
 
+    @requires_dependencies(["pandas"], extras="kdbai")
     def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
         data = get_data_df(path=path)
         self.process_dataframe(df=data)

unstructured_ingest/processes/connectors/outlook.py

@@ -199,8 +199,7 @@ class OutlookDownloader(Downloader):
         download_path = self.get_download_path(file_data)
         if download_path is None:
             logger.error(
-                "Generated download path is None, source_identifiers might be missing"
-                "from FileData."
+                "Generated download path is None, source_identifiers might be missingfrom FileData."
             )
             raise ValueError("Generated invalid download path.")
 

unstructured_ingest/processes/connectors/pinecone.py

@@ -227,7 +227,6 @@ class PineconeUploader(VectorDBUploader):
         self.connection_config.index_name = index_name
 
         if not self.index_exists(index_name):
-
             logger.info(f"creating pinecone index {index_name}")
 
             pc = self.connection_config.get_client()