unstructured-ingest 0.5.21__py3-none-any.whl → 0.5.23__py3-none-any.whl

unstructured_ingest/__version__.py

@@ -1 +1 @@
-__version__ = "0.5.21"  # pragma: no cover
+__version__ = "0.5.23"  # pragma: no cover

unstructured_ingest/v2/interfaces/__init__.py

@@ -1,6 +1,13 @@
+from unstructured_ingest.v2.types.file_data import (
+    BatchFileData,
+    BatchItem,
+    FileData,
+    FileDataSourceMetadata,
+    SourceIdentifiers,
+)
+
 from .connector import AccessConfig, BaseConnector, ConnectionConfig
 from .downloader import Downloader, DownloaderConfig, DownloadResponse, download_responses
-from .file_data import BatchFileData, BatchItem, FileData, FileDataSourceMetadata, SourceIdentifiers
 from .indexer import Indexer, IndexerConfig
 from .process import BaseProcess
 from .processor import ProcessorConfig

unstructured_ingest/v2/interfaces/file_data.py

@@ -1,116 +1,13 @@
-import json
-from pathlib import Path
-from typing import Any, Optional
-from uuid import NAMESPACE_DNS, uuid5
-
-from pydantic import BaseModel, Field, ValidationError, field_validator, model_validator
-
-from unstructured_ingest.v2.logger import logger
-
-
-class SourceIdentifiers(BaseModel):
-    filename: str
-    fullpath: str
-    rel_path: Optional[str] = None
-
-    @property
-    def filename_stem(self) -> str:
-        return Path(self.filename).stem
-
-    @property
-    def relative_path(self) -> str:
-        return self.rel_path or self.fullpath
-
-
-class FileDataSourceMetadata(BaseModel):
-    url: Optional[str] = None
-    version: Optional[str] = None
-    record_locator: Optional[dict[str, Any]] = None
-    date_created: Optional[str] = None
-    date_modified: Optional[str] = None
-    date_processed: Optional[str] = None
-    permissions_data: Optional[list[dict[str, Any]]] = None
-    filesize_bytes: Optional[int] = None
-
-
-class FileData(BaseModel):
-    identifier: str
-    connector_type: str
-    source_identifiers: SourceIdentifiers
-    metadata: FileDataSourceMetadata = Field(default_factory=lambda: FileDataSourceMetadata())
-    additional_metadata: dict[str, Any] = Field(default_factory=dict)
-    reprocess: bool = False
-    local_download_path: Optional[str] = None
-    display_name: Optional[str] = None
-
-    @classmethod
-    def from_file(cls, path: str) -> "FileData":
-        path = Path(path).resolve()
-        if not path.exists() or not path.is_file():
-            raise ValueError(f"file path not valid: {path}")
-        with open(str(path.resolve()), "rb") as f:
-            file_data_dict = json.load(f)
-        file_data = cls.model_validate(file_data_dict)
-        return file_data
-
-    @classmethod
-    def cast(cls, file_data: "FileData", **kwargs) -> "FileData":
-        file_data_dict = file_data.model_dump()
-        return cls.model_validate(file_data_dict, **kwargs)
-
-    def to_file(self, path: str) -> None:
-        path = Path(path).resolve()
-        path.parent.mkdir(parents=True, exist_ok=True)
-        with open(str(path.resolve()), "w") as f:
-            json.dump(self.model_dump(), f, indent=2)
-
-
-class BatchItem(BaseModel):
-    identifier: str
-    version: Optional[str] = None
-
-
-class BatchFileData(FileData):
-    identifier: str = Field(init=False)
-    batch_items: list[BatchItem]
-    source_identifiers: Optional[SourceIdentifiers] = None
-
-    @field_validator("batch_items")
-    @classmethod
-    def check_batch_items(cls, v: list[BatchItem]) -> list[BatchItem]:
-        if not v:
-            raise ValueError("batch items cannot be empty")
-        all_identifiers = [item.identifier for item in v]
-        if len(all_identifiers) != len(set(all_identifiers)):
-            raise ValueError(f"duplicate identifiers: {all_identifiers}")
-        sorted_batch_items = sorted(v, key=lambda item: item.identifier)
-        return sorted_batch_items
-
-    @model_validator(mode="before")
-    @classmethod
-    def populate_identifier(cls, data: Any) -> Any:
-        if isinstance(data, dict) and "identifier" not in data:
-            batch_items = data["batch_items"]
-            identifier_data = json.dumps(
-                {item.identifier: item.version for item in batch_items}, sort_keys=True
-            )
-            data["identifier"] = str(uuid5(NAMESPACE_DNS, str(identifier_data)))
-        return data
-
-
-def file_data_from_file(path: str) -> FileData:
-    try:
-        return BatchFileData.from_file(path=path)
-    except ValidationError:
-        logger.debug(f"{path} not detected as batch file data")
-
-    return FileData.from_file(path=path)
-
-
-def file_data_from_dict(data: dict) -> FileData:
-    try:
-        return BatchFileData.model_validate(data)
-    except ValidationError:
-        logger.debug(f"{data} not valid for batch file data")
-
-    return FileData.model_validate(data)
+"""
+COMPATABILITY NOTICE:
+This file has moved to the v2/types/ module.
+The following line exists for backward compatibility.
+"""
+
+from unstructured_ingest.v2.types.file_data import *  # noqa - star imports are bad, but this is for maximal backward compatability
+
+#  Eventually this file should go away. Let's start warning users now:
+logger.warning(  # noqa - using logger from the star import
+    "Importing file_data.py through interfaces is deprecated. "
+    "Please use unstructured_ingest.v2.types.file_data instead!"
+)

unstructured_ingest/v2/processes/connectors/elasticsearch/elasticsearch.py

@@ -6,7 +6,7 @@ from pathlib import Path
 from time import time
 from typing import TYPE_CHECKING, Any, Generator, Optional, Union
 
-from pydantic import BaseModel, Field, Secret, SecretStr
+from pydantic import BaseModel, Field, Secret, SecretStr, field_validator
 
 from unstructured_ingest.error import (
     DestinationConnectionError,
@@ -98,6 +98,12 @@ class ElasticsearchConnectionConfig(ConnectionConfig):
     ca_certs: Optional[Path] = None
     access_config: Secret[ElasticsearchAccessConfig]
 
+    @field_validator("hosts", mode="before")
+    def to_list(cls, value):
+        if isinstance(value, str):
+            return [value]
+        return value
+
     def get_client_kwargs(self) -> dict:
         # Update auth related fields to conform to what the SDK expects based on the
         # supported methods:

unstructured_ingest/v2/processes/connectors/elasticsearch/opensearch.py

@@ -2,7 +2,7 @@ from dataclasses import dataclass, field
 from pathlib import Path
 from typing import TYPE_CHECKING, Optional
 
-from pydantic import BaseModel, Field, Secret
+from pydantic import BaseModel, Field, Secret, field_validator
 
 from unstructured_ingest.error import (
     DestinationConnectionError,
@@ -78,6 +78,12 @@ class OpenSearchConnectionConfig(ConnectionConfig):
 
     access_config: Secret[OpenSearchAccessConfig]
 
+    @field_validator("hosts", mode="before")
+    def to_list(cls, value):
+        if isinstance(value, str):
+            return [value]
+        return value
+
     def get_client_kwargs(self) -> dict:
         # Update auth related fields to conform to what the SDK expects based on the
         # supported methods:

unstructured_ingest/v2/types/file_data.py

@@ -0,0 +1,116 @@
+import json
+from pathlib import Path
+from typing import Any, Optional
+from uuid import NAMESPACE_DNS, uuid5
+
+from pydantic import BaseModel, Field, ValidationError, field_validator, model_validator
+
+from unstructured_ingest.v2.logger import logger
+
+
+class SourceIdentifiers(BaseModel):
+    filename: str
+    fullpath: str
+    rel_path: Optional[str] = None
+
+    @property
+    def filename_stem(self) -> str:
+        return Path(self.filename).stem
+
+    @property
+    def relative_path(self) -> str:
+        return self.rel_path or self.fullpath
+
+
+class FileDataSourceMetadata(BaseModel):
+    url: Optional[str] = None
+    version: Optional[str] = None
+    record_locator: Optional[dict[str, Any]] = None
+    date_created: Optional[str] = None
+    date_modified: Optional[str] = None
+    date_processed: Optional[str] = None
+    permissions_data: Optional[list[dict[str, Any]]] = None
+    filesize_bytes: Optional[int] = None
+
+
+class FileData(BaseModel):
+    identifier: str
+    connector_type: str
+    source_identifiers: SourceIdentifiers
+    metadata: FileDataSourceMetadata = Field(default_factory=lambda: FileDataSourceMetadata())
+    additional_metadata: dict[str, Any] = Field(default_factory=dict)
+    reprocess: bool = False
+    local_download_path: Optional[str] = None
+    display_name: Optional[str] = None
+
+    @classmethod
+    def from_file(cls, path: str) -> "FileData":
+        path = Path(path).resolve()
+        if not path.exists() or not path.is_file():
+            raise ValueError(f"file path not valid: {path}")
+        with open(str(path.resolve()), "rb") as f:
+            file_data_dict = json.load(f)
+        file_data = cls.model_validate(file_data_dict)
+        return file_data
+
+    @classmethod
+    def cast(cls, file_data: "FileData", **kwargs) -> "FileData":
+        file_data_dict = file_data.model_dump()
+        return cls.model_validate(file_data_dict, **kwargs)
+
+    def to_file(self, path: str) -> None:
+        path = Path(path).resolve()
+        path.parent.mkdir(parents=True, exist_ok=True)
+        with open(str(path.resolve()), "w") as f:
+            json.dump(self.model_dump(), f, indent=2)
+
+
+class BatchItem(BaseModel):
+    identifier: str
+    version: Optional[str] = None
+
+
+class BatchFileData(FileData):
+    identifier: str = Field(init=False)
+    batch_items: list[BatchItem]
+    source_identifiers: Optional[SourceIdentifiers] = None
+
+    @field_validator("batch_items")
+    @classmethod
+    def check_batch_items(cls, v: list[BatchItem]) -> list[BatchItem]:
+        if not v:
+            raise ValueError("batch items cannot be empty")
+        all_identifiers = [item.identifier for item in v]
+        if len(all_identifiers) != len(set(all_identifiers)):
+            raise ValueError(f"duplicate identifiers: {all_identifiers}")
+        sorted_batch_items = sorted(v, key=lambda item: item.identifier)
+        return sorted_batch_items
+
+    @model_validator(mode="before")
+    @classmethod
+    def populate_identifier(cls, data: Any) -> Any:
+        if isinstance(data, dict) and "identifier" not in data:
+            batch_items = data["batch_items"]
+            identifier_data = json.dumps(
+                {item.identifier: item.version for item in batch_items}, sort_keys=True
+            )
+            data["identifier"] = str(uuid5(NAMESPACE_DNS, str(identifier_data)))
+        return data
+
+
+def file_data_from_file(path: str) -> FileData:
+    try:
+        return BatchFileData.from_file(path=path)
+    except ValidationError:
+        logger.debug(f"{path} not detected as batch file data")
+
+    return FileData.from_file(path=path)
+
+
+def file_data_from_dict(data: dict) -> FileData:
+    try:
+        return BatchFileData.model_validate(data)
+    except ValidationError:
+        logger.debug(f"{data} not valid for batch file data")
+
+    return FileData.model_validate(data)

{unstructured_ingest-0.5.21.dist-info → unstructured_ingest-0.5.23.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.5.21
+Version: 0.5.23
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,12 +22,12 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: click
 Requires-Dist: dataclasses_json
-Requires-Dist: pydantic>=2.7
-Requires-Dist: python-dateutil
 Requires-Dist: opentelemetry-sdk
+Requires-Dist: click
 Requires-Dist: tqdm
+Requires-Dist: python-dateutil
+Requires-Dist: pydantic>=2.7
 Requires-Dist: numpy
 Requires-Dist: pandas
 Provides-Extra: remote
@@ -103,8 +103,8 @@ Requires-Dist: astrapy; extra == "astradb"
 Requires-Dist: numpy; extra == "astradb"
 Requires-Dist: pandas; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: fsspec; extra == "azure"
 Requires-Dist: adlfs; extra == "azure"
+Requires-Dist: fsspec; extra == "azure"
 Requires-Dist: numpy; extra == "azure"
 Requires-Dist: pandas; extra == "azure"
 Provides-Extra: azure-ai-search
@@ -117,8 +117,8 @@ Requires-Dist: requests; extra == "biomed"
 Requires-Dist: numpy; extra == "biomed"
 Requires-Dist: pandas; extra == "biomed"
 Provides-Extra: box
-Requires-Dist: fsspec; extra == "box"
 Requires-Dist: boxfs; extra == "box"
+Requires-Dist: fsspec; extra == "box"
 Requires-Dist: numpy; extra == "box"
 Requires-Dist: pandas; extra == "box"
 Provides-Extra: chroma
@@ -148,8 +148,8 @@ Requires-Dist: discord.py; extra == "discord"
 Requires-Dist: numpy; extra == "discord"
 Requires-Dist: pandas; extra == "discord"
 Provides-Extra: dropbox
-Requires-Dist: fsspec; extra == "dropbox"
 Requires-Dist: dropboxdrivefs; extra == "dropbox"
+Requires-Dist: fsspec; extra == "dropbox"
 Requires-Dist: numpy; extra == "dropbox"
 Requires-Dist: pandas; extra == "dropbox"
 Provides-Extra: duckdb
@@ -161,9 +161,9 @@ Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Requires-Dist: numpy; extra == "elasticsearch"
 Requires-Dist: pandas; extra == "elasticsearch"
 Provides-Extra: gcs
-Requires-Dist: bs4; extra == "gcs"
-Requires-Dist: fsspec; extra == "gcs"
 Requires-Dist: gcsfs; extra == "gcs"
+Requires-Dist: fsspec; extra == "gcs"
+Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: numpy; extra == "gcs"
 Requires-Dist: pandas; extra == "gcs"
 Provides-Extra: github
@@ -185,10 +185,10 @@ Requires-Dist: hubspot-api-client; extra == "hubspot"
 Requires-Dist: numpy; extra == "hubspot"
 Requires-Dist: pandas; extra == "hubspot"
 Provides-Extra: ibm-watsonx-s3
-Requires-Dist: pyiceberg; extra == "ibm-watsonx-s3"
 Requires-Dist: pyarrow; extra == "ibm-watsonx-s3"
-Requires-Dist: httpx; extra == "ibm-watsonx-s3"
 Requires-Dist: tenacity; extra == "ibm-watsonx-s3"
+Requires-Dist: pyiceberg; extra == "ibm-watsonx-s3"
+Requires-Dist: httpx; extra == "ibm-watsonx-s3"
 Requires-Dist: numpy; extra == "ibm-watsonx-s3"
 Requires-Dist: pandas; extra == "ibm-watsonx-s3"
 Provides-Extra: jira
@@ -216,22 +216,22 @@ Requires-Dist: pymongo; extra == "mongodb"
 Requires-Dist: numpy; extra == "mongodb"
 Requires-Dist: pandas; extra == "mongodb"
 Provides-Extra: neo4j
-Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: neo4j-rust-ext; extra == "neo4j"
+Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: cymple; extra == "neo4j"
 Requires-Dist: numpy; extra == "neo4j"
 Requires-Dist: pandas; extra == "neo4j"
 Provides-Extra: notion
-Requires-Dist: httpx; extra == "notion"
+Requires-Dist: backoff; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
-Requires-Dist: backoff; extra == "notion"
+Requires-Dist: httpx; extra == "notion"
 Requires-Dist: numpy; extra == "notion"
 Requires-Dist: pandas; extra == "notion"
 Provides-Extra: onedrive
-Requires-Dist: bs4; extra == "onedrive"
-Requires-Dist: msal; extra == "onedrive"
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
+Requires-Dist: msal; extra == "onedrive"
+Requires-Dist: bs4; extra == "onedrive"
 Requires-Dist: numpy; extra == "onedrive"
 Requires-Dist: pandas; extra == "onedrive"
 Provides-Extra: opensearch
@@ -239,8 +239,8 @@ Requires-Dist: opensearch-py; extra == "opensearch"
 Requires-Dist: numpy; extra == "opensearch"
 Requires-Dist: pandas; extra == "opensearch"
 Provides-Extra: outlook
-Requires-Dist: msal; extra == "outlook"
 Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
+Requires-Dist: msal; extra == "outlook"
 Requires-Dist: numpy; extra == "outlook"
 Requires-Dist: pandas; extra == "outlook"
 Provides-Extra: pinecone
@@ -264,13 +264,13 @@ Requires-Dist: redis; extra == "redis"
 Requires-Dist: numpy; extra == "redis"
 Requires-Dist: pandas; extra == "redis"
 Provides-Extra: s3
-Requires-Dist: fsspec; extra == "s3"
 Requires-Dist: s3fs; extra == "s3"
+Requires-Dist: fsspec; extra == "s3"
 Requires-Dist: numpy; extra == "s3"
 Requires-Dist: pandas; extra == "s3"
 Provides-Extra: sharepoint
-Requires-Dist: msal; extra == "sharepoint"
 Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
+Requires-Dist: msal; extra == "sharepoint"
 Requires-Dist: numpy; extra == "sharepoint"
 Requires-Dist: pandas; extra == "sharepoint"
 Provides-Extra: salesforce
@@ -287,8 +287,8 @@ Requires-Dist: slack_sdk[optional]; extra == "slack"
 Requires-Dist: numpy; extra == "slack"
 Requires-Dist: pandas; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: snowflake-connector-python; extra == "snowflake"
+Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: numpy; extra == "snowflake"
 Requires-Dist: pandas; extra == "snowflake"
 Provides-Extra: wikipedia
@@ -312,21 +312,21 @@ Requires-Dist: singlestoredb; extra == "singlestore"
 Requires-Dist: numpy; extra == "singlestore"
 Requires-Dist: pandas; extra == "singlestore"
 Provides-Extra: vectara
-Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"
+Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: numpy; extra == "vectara"
 Requires-Dist: pandas; extra == "vectara"
 Provides-Extra: vastdb
-Requires-Dist: ibis; extra == "vastdb"
-Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: vastdb; extra == "vastdb"
+Requires-Dist: pyarrow; extra == "vastdb"
+Requires-Dist: ibis; extra == "vastdb"
 Requires-Dist: numpy; extra == "vastdb"
 Requires-Dist: pandas; extra == "vastdb"
 Provides-Extra: zendesk
 Requires-Dist: bs4; extra == "zendesk"
-Requires-Dist: httpx; extra == "zendesk"
 Requires-Dist: aiofiles; extra == "zendesk"
+Requires-Dist: httpx; extra == "zendesk"
 Requires-Dist: numpy; extra == "zendesk"
 Requires-Dist: pandas; extra == "zendesk"
 Provides-Extra: embed-huggingface
@@ -334,8 +334,8 @@ Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Requires-Dist: numpy; extra == "embed-huggingface"
 Requires-Dist: pandas; 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"
 Requires-Dist: numpy; extra == "embed-octoai"
 Requires-Dist: pandas; extra == "embed-octoai"
 Provides-Extra: embed-vertexai
@@ -351,13 +351,13 @@ Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
 Requires-Dist: numpy; extra == "embed-mixedbreadai"
 Requires-Dist: pandas; extra == "embed-mixedbreadai"
 Provides-Extra: openai
-Requires-Dist: tiktoken; extra == "openai"
 Requires-Dist: openai; extra == "openai"
+Requires-Dist: tiktoken; extra == "openai"
 Requires-Dist: numpy; extra == "openai"
 Requires-Dist: pandas; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"
+Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: numpy; extra == "bedrock"
 Requires-Dist: pandas; extra == "bedrock"
 Provides-Extra: togetherai

{unstructured_ingest-0.5.21.dist-info → unstructured_ingest-0.5.23.dist-info}/RECORD

@@ -113,7 +113,7 @@ 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=b5BrQJjlBZoPiM_J1cJDbJABGvcwaDFb_Bvwb0AHN10,43
+unstructured_ingest/__version__.py,sha256=zwHqD3LgpFA-cY-rrS_2n5Kv-NY8b8mUJsGrAiSe2kA,43
 unstructured_ingest/error.py,sha256=qDncnJgbf5ils956RcO2CGlAKYDT5OaEM9Clv1JVTNc,1448
 unstructured_ingest/interfaces.py,sha256=7DOnDpGvUNlCoFR7UPRGmOarqH5sFtuUOO5vf8X3oTM,31489
 unstructured_ingest/logger.py,sha256=S5nSqGcABoQyeicgRnBQFjDScCaTvFVivOCvbo-laL0,4479
@@ -398,10 +398,10 @@ unstructured_ingest/v2/cli/base/src.py,sha256=cpQ43qQju4e5s_YSaPxUtA70BaisRkTBdj
 unstructured_ingest/v2/cli/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 unstructured_ingest/v2/cli/utils/click.py,sha256=1_eJgrwS2DFBl1jZPLsj1vgVgR7agFBIEBe4A_n7mH4,7827
 unstructured_ingest/v2/cli/utils/model_conversion.py,sha256=7eEIkk1KU51-ZNiIfI1KRxlwITNW1xl1YxMAG8BcTk0,7604
-unstructured_ingest/v2/interfaces/__init__.py,sha256=Xp7-345QpM6MG7V7G4ZrVERjADAUBiPAY88PKaMRyqY,1005
+unstructured_ingest/v2/interfaces/__init__.py,sha256=Jn5qtWOnmBZzsb2PoQYN3Xj5xHa9thSVc0BEoIN0Pw0,1059
 unstructured_ingest/v2/interfaces/connector.py,sha256=qUFFJ3qgDMenTCZMtVRjq1DIwsVak6pxNjQOH2eVkMw,1623
 unstructured_ingest/v2/interfaces/downloader.py,sha256=Qi_wISgUACZKEPu5p1kUaG3uiCXcr3zWg9z9uRDwoOk,2927
-unstructured_ingest/v2/interfaces/file_data.py,sha256=kowOhvYy0q_-khX3IuR111AfjkdQezEfxjzK6QDH7oA,3836
+unstructured_ingest/v2/interfaces/file_data.py,sha256=DQYzXr8yjlm6VkGuwQLGJ1sia4Gr0d__POAFLrow1PE,525
 unstructured_ingest/v2/interfaces/indexer.py,sha256=i0oftyifXefxfKa4a3sCfSwkzWGSPE6EvC9sg6fwZgk,833
 unstructured_ingest/v2/interfaces/process.py,sha256=S3A_9gkwwGC-iQxvnpj3Er6IJAjAT5npzpSgxuFAzUM,449
 unstructured_ingest/v2/interfaces/processor.py,sha256=VX7JqXlbG1plxMK8THWhWINPbTICaaUEk4XUXhnOixY,3303
@@ -468,8 +468,8 @@ unstructured_ingest/v2/processes/connectors/duckdb/base.py,sha256=o3J81DnSwt3lmA
 unstructured_ingest/v2/processes/connectors/duckdb/duckdb.py,sha256=NIo2CCiPiuTFotNC891Mbelzg01knItryYGUtOM96xg,4393
 unstructured_ingest/v2/processes/connectors/duckdb/motherduck.py,sha256=RW-Cw94Hs3ZsN8Kb4ciSh_N-Qkp0cqkw_xkJbt8CDNU,4656
 unstructured_ingest/v2/processes/connectors/elasticsearch/__init__.py,sha256=Zzc0JNPP-eFqpwWw1Gp-XC8H-s__IgkYKzoagECycZY,829
-unstructured_ingest/v2/processes/connectors/elasticsearch/elasticsearch.py,sha256=MEKU64OsiQmbLPb3ken-WWCIV6-pnFbs_6kjJweG-SY,18813
-unstructured_ingest/v2/processes/connectors/elasticsearch/opensearch.py,sha256=qRz8Fyr2RSZIPZGkhPeme6AZxM0aX-c_xOa1ZtSr2Kg,6781
+unstructured_ingest/v2/processes/connectors/elasticsearch/elasticsearch.py,sha256=KmlQCA7LXppxhL9e27LBBqNT999nUcc39qe2IkZsUJ8,18988
+unstructured_ingest/v2/processes/connectors/elasticsearch/opensearch.py,sha256=tzOV0eNMyVHMXE5nedp6u0yyWC0Gn_blklg2ZdoOa4c,6956
 unstructured_ingest/v2/processes/connectors/fsspec/__init__.py,sha256=TtdeImM7Ypl_n6sl7I1JqX6bGSG0t_FqvCqE3Cy24og,1846
 unstructured_ingest/v2/processes/connectors/fsspec/azure.py,sha256=kw0UfGI2fx3oQ8jVpzF45pH8Qg_QP_que5C_VXgnktc,7156
 unstructured_ingest/v2/processes/connectors/fsspec/box.py,sha256=aJCtCHRBAauLwdWEQe704Cm4UHv-ukTXV2bT3SBENVk,5881
@@ -581,9 +581,11 @@ unstructured_ingest/v2/processes/connectors/zendesk/client.py,sha256=DDAYQB7catK
 unstructured_ingest/v2/processes/connectors/zendesk/zendesk.py,sha256=R8SXYkRhVUoWEHdGCt2CzcTxxuFundw_0GlGZ34YmbM,8987
 unstructured_ingest/v2/processes/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 unstructured_ingest/v2/processes/utils/blob_storage.py,sha256=EWvK4HRYubr9i1UyMhv5cU9u0UzVkCDC_BIm4Uxab7Y,964
-unstructured_ingest-0.5.21.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
-unstructured_ingest-0.5.21.dist-info/METADATA,sha256=c1bUHvgG6X9QOiAD669sVHAFkGfI2tBTRBM-eRJBLiU,14999
-unstructured_ingest-0.5.21.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-unstructured_ingest-0.5.21.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
-unstructured_ingest-0.5.21.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
-unstructured_ingest-0.5.21.dist-info/RECORD,,
+unstructured_ingest/v2/types/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+unstructured_ingest/v2/types/file_data.py,sha256=kowOhvYy0q_-khX3IuR111AfjkdQezEfxjzK6QDH7oA,3836
+unstructured_ingest-0.5.23.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
+unstructured_ingest-0.5.23.dist-info/METADATA,sha256=yEHUhxSR1EF-2IoXViunb9iiNlEy9p0LgMTngzwtjLM,14999
+unstructured_ingest-0.5.23.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+unstructured_ingest-0.5.23.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
+unstructured_ingest-0.5.23.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
+unstructured_ingest-0.5.23.dist-info/RECORD,,