unstructured-ingest 0.7.1__py3-none-any.whl → 1.0.1__py3-none-any.whl

unstructured_ingest/__version__.py

@@ -1 +1 @@
-__version__ = "0.7.1"  # pragma: no cover
+__version__ = "1.0.1"  # 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/logger.py

@@ -1,99 +1,8 @@
-import ast
-import json
 import logging
-import typing as t
 
 logger = logging.getLogger("unstructured_ingest")
 
 
-def default_is_data_sensitive(k: str, v: t.Any) -> bool:
-    sensitive_fields = [
-        "account_name",
-        "client_id",
-    ]
-    sensitive_triggers = ["key", "cred", "token", "password", "oauth", "secret"]
-    return (
-        v
-        and any([s in k.lower() for s in sensitive_triggers])  # noqa: C419
-        or k.lower() in sensitive_fields
-    )
-
-
-def hide_sensitive_fields(
-    data: dict, is_sensitive_fn: t.Callable[[str, t.Any], bool] = default_is_data_sensitive
-) -> dict:
-    """
-    Will recursively look through every k, v pair in this dict and any nested ones and run
-    is_sensitive_fn to dynamically redact the value of the k, v pair. Will also check if
-    any string value can be parsed as valid json and process that dict as well and replace
-    the original string with the json.dumps() version of the redacted dict.
-    """
-    new_data = data.copy()
-    for k, v in new_data.items():
-        if is_sensitive_fn(k, v):
-            new_data[k] = "*******"
-        if isinstance(v, dict):
-            new_data[k] = hide_sensitive_fields(v)
-        if isinstance(v, str):
-            # Need to take into account strings generated via json.dumps() or simply printing a dict
-            try:
-                json_data = json.loads(v)
-                if isinstance(json_data, dict):
-                    updated_data = hide_sensitive_fields(json_data)
-                    new_data[k] = json.dumps(updated_data)
-            except json.JSONDecodeError:
-                pass
-
-    return new_data
-
-
-def redact_jsons(s: str) -> str:
-    """
-    Takes in a generic string and pulls out all valid json content. Leverages
-    hide_sensitive_fields() to redact any sensitive information and replaces the
-    original json with the new redacted format. There can be any number of valid
-    jsons in a generic string and this will work. Having extra '{' without a
-    closing '}' will cause this to break though. i.e '{ text, {"a": 3}'.
-
-    """
-    chars = list(s)
-    if "{" not in chars:
-        return s
-    i = 0
-    jsons = []
-    i = 0
-    while i < len(chars):
-        char = chars[i]
-        if char == "{":
-            stack = [char]
-            current = [char]
-            while len(stack) != 0 and i < len(chars):
-                i += 1
-                char = chars[i]
-                current.append(char)
-                if char == "{":
-                    stack.append(char)
-                if char == "}":
-                    stack.pop(-1)
-            jsons.append("".join(current))
-            continue
-        i += 1
-    for j in jsons:
-        try:
-            formatted_j = json.dumps(json.loads(j))
-        except json.JSONDecodeError:
-            formatted_j = json.dumps(ast.literal_eval(j))
-        hidden_j = json.dumps(hide_sensitive_fields(json.loads(formatted_j)))
-        s = s.replace(j, hidden_j)
-    return s
-
-
-class SensitiveFormatter(logging.Formatter):
-    def format(self, record):
-        s = super().format(record=record)
-        return redact_jsons(s)
-
-
 def remove_root_handlers(logger: logging.Logger) -> None:
     # NOTE(robinson): in some environments such as Google Colab, there is a root handler
     # that doesn't not mask secrets, meaning sensitive info such as api keys appear in logs.
@@ -106,7 +15,7 @@ def remove_root_handlers(logger: logging.Logger) -> None:
 def ingest_log_streaming_init(level: int) -> None:
     handler = logging.StreamHandler()
     handler.name = "ingest_log_handler"
-    formatter = SensitiveFormatter("%(asctime)s %(processName)-10s %(levelname)-8s %(message)s")
+    formatter = logging.Formatter("%(asctime)s %(processName)-10s %(levelname)-8s %(message)s")
     handler.setFormatter(formatter)
 
     # Only want to add the handler once
@@ -122,7 +31,7 @@ def make_default_logger(level: int) -> logging.Logger:
     logger = logging.getLogger("unstructured_ingest")
     handler = logging.StreamHandler()
     handler.name = "ingest_log_handler"
-    formatter = SensitiveFormatter("%(asctime)s %(processName)-10s %(levelname)-8s %(message)s")
+    formatter = logging.Formatter("%(asctime)s %(processName)-10s %(levelname)-8s %(message)s")
     handler.setFormatter(formatter)
     logger.addHandler(handler)
     logger.setLevel(level)

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/assets/databricks_delta_table_schema.sql

@@ -0,0 +1,10 @@
+CREATE TABLE elements (
+    id STRING NOT NULL PRIMARY KEY,
+    record_id STRING NOT NULL,
+    element_id STRING NOT NULL,
+    text STRING,
+    embeddings ARRAY<FLOAT>,
+    type STRING,
+    metadata VARIANT
+);
+

unstructured_ingest/processes/connectors/assets/weaviate_collection_config.json

@@ -0,0 +1,23 @@
+{
+    "properties": [
+        {
+            "dataType": [
+                "text"
+            ],
+            "indexFilterable": true,
+            "indexSearchable": true,
+            "name": "record_id",
+            "tokenization": "word"
+        },
+        {
+            "dataType": [
+                "text"
+            ],
+            "indexFilterable": true,
+            "indexSearchable": true,
+            "name": "text",
+            "tokenization": "word"
+        }
+    ],
+    "vectorizer": "none"
+}

unstructured_ingest/processes/connectors/astradb.py

@@ -43,7 +43,7 @@ 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
 
@@ -465,7 +465,7 @@ class AstraDBUploader(Uploader):
             collection.insert_many(chunk)
 
     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)
 
 

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()