unstructured-ingest 0.5.16__tar.gz → 0.5.18__tar.gz

{unstructured_ingest-0.5.16/unstructured_ingest.egg-info → unstructured_ingest-0.5.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.5.16
+Version: 0.5.18
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,13 +22,13 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: tqdm
+Requires-Dist: pydantic>=2.7
+Requires-Dist: python-dateutil
+Requires-Dist: click
 Requires-Dist: dataclasses_json
+Requires-Dist: tqdm
 Requires-Dist: opentelemetry-sdk
-Requires-Dist: python-dateutil
 Requires-Dist: pandas
-Requires-Dist: pydantic>=2.7
-Requires-Dist: click
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.30.0; extra == "remote"
 Provides-Extra: csv
@@ -66,16 +66,16 @@ Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
 Requires-Dist: astrapy; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: fsspec; extra == "azure"
+Requires-Dist: adlfs; 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"
+Requires-Dist: boxfs; extra == "box"
 Provides-Extra: chroma
 Requires-Dist: chromadb; extra == "chroma"
 Provides-Extra: clarifai
@@ -98,12 +98,12 @@ Requires-Dist: duckdb; extra == "duckdb"
 Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
-Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: gcsfs; extra == "gcs"
+Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: fsspec; extra == "gcs"
 Provides-Extra: github
-Requires-Dist: pygithub>1.58.0; extra == "github"
 Requires-Dist: requests; extra == "github"
+Requires-Dist: pygithub>1.58.0; extra == "github"
 Provides-Extra: gitlab
 Requires-Dist: python-gitlab; extra == "gitlab"
 Provides-Extra: google-drive
@@ -124,14 +124,14 @@ Requires-Dist: pymilvus; extra == "milvus"
 Provides-Extra: mongodb
 Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: neo4j
-Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: cymple; extra == "neo4j"
+Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Provides-Extra: notion
+Requires-Dist: notion-client; extra == "notion"
 Requires-Dist: backoff; extra == "notion"
-Requires-Dist: httpx; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
-Requires-Dist: notion-client; extra == "notion"
+Requires-Dist: httpx; extra == "notion"
 Provides-Extra: onedrive
 Requires-Dist: bs4; extra == "onedrive"
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
@@ -178,17 +178,17 @@ Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
 Provides-Extra: singlestore
 Requires-Dist: singlestoredb; extra == "singlestore"
 Provides-Extra: vectara
-Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"
 Requires-Dist: aiofiles; extra == "vectara"
+Requires-Dist: httpx; extra == "vectara"
 Provides-Extra: vastdb
-Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: vastdb; extra == "vastdb"
+Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: ibis; 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"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
@@ -204,8 +204,8 @@ Provides-Extra: openai
 Requires-Dist: tiktoken; extra == "openai"
 Requires-Dist: openai; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"
+Requires-Dist: aioboto3; extra == "bedrock"
 Provides-Extra: togetherai
 Requires-Dist: together; extra == "togetherai"
 Dynamic: author

unstructured_ingest-0.5.18/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.5.18"  # pragma: no cover

{unstructured_ingest-0.5.16 → unstructured_ingest-0.5.18}/unstructured_ingest/utils/data_prep.py

@@ -192,6 +192,16 @@ def get_data(path: Union[Path, str]) -> list[dict]:
             logger.warning(f"failed to read {path} as parquet: {e}")
 
 
+def get_json_data(path: Path) -> list[dict]:
+    with path.open() as f:
+        if path.suffix == ".json":
+            return json.load(f)
+        elif path.suffix == ".ndjson":
+            return ndjson.load(f)
+        else:
+            raise ValueError(f"Unsupported file type: {path}")
+
+
 def get_data_df(path: Path) -> pd.DataFrame:
     with path.open() as f:
         if path.suffix == ".json":

{unstructured_ingest-0.5.16 → unstructured_ingest-0.5.18}/unstructured_ingest/v2/processes/connectors/astradb.py

@@ -112,7 +112,6 @@ def get_astra_collection(
     collection_name: str,
     keyspace: str,
 ) -> "AstraDBCollection":
-
     astra_db = get_astra_db(connection_config=connection_config, keyspace=keyspace)
 
     # astradb will return a collection object in all cases (even if it doesn't exist)
@@ -315,6 +314,7 @@ class AstraDBUploadStager(UploadStager):
                     text_as_html, MAX_CONTENT_PARAM_BYTE_SIZE
                 )
             metadata["original_elements"] = format_and_truncate_orig_elements(element_dict)
+            metadata.pop("orig_elements", None)
 
     def conform_dict(self, element_dict: dict, file_data: FileData) -> dict:
         self.truncate_dict_elements(element_dict)

{unstructured_ingest-0.5.16 → unstructured_ingest-0.5.18}/unstructured_ingest/v2/processes/connectors/delta_table.py

@@ -1,4 +1,3 @@
-import json
 import os
 import traceback
 from dataclasses import dataclass, field
@@ -11,7 +10,7 @@ import pandas as pd
 from pydantic import Field, Secret
 
 from unstructured_ingest.error import DestinationConnectionError
-from unstructured_ingest.utils.data_prep import get_data_df
+from unstructured_ingest.utils.data_prep import get_data_df, get_json_data
 from unstructured_ingest.utils.dep_check import requires_dependencies
 from unstructured_ingest.utils.table import convert_to_pandas_dataframe
 from unstructured_ingest.v2.interfaces import (
@@ -86,9 +85,7 @@ class DeltaTableUploadStager(UploadStager):
         output_filename: str,
         **kwargs: Any,
     ) -> Path:
-        with open(elements_filepath) as elements_file:
-            elements_contents = json.load(elements_file)
-
+        elements_contents = get_json_data(elements_filepath)
         output_path = Path(output_dir) / Path(f"{output_filename}.parquet")
 
         df = convert_to_pandas_dataframe(elements_dict=elements_contents)

{unstructured_ingest-0.5.16 → unstructured_ingest-0.5.18}/unstructured_ingest/v2/processes/connectors/neo4j.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 import asyncio
-import json
 import uuid
 from collections import defaultdict
 from contextlib import asynccontextmanager
@@ -14,7 +13,7 @@ from pydantic import BaseModel, ConfigDict, Field, Secret, field_validator
 
 from unstructured_ingest.error import DestinationConnectionError
 from unstructured_ingest.logger import logger
-from unstructured_ingest.utils.data_prep import batch_generator
+from unstructured_ingest.utils.data_prep import batch_generator, get_json_data
 from unstructured_ingest.utils.dep_check import requires_dependencies
 from unstructured_ingest.v2.interfaces import (
     AccessConfig,
@@ -97,8 +96,7 @@ class Neo4jUploadStager(UploadStager):
         output_filename: str,
         **kwargs: Any,
     ) -> Path:
-        with elements_filepath.open() as file:
-            elements = json.load(file)
+        elements = get_json_data(elements_filepath)
 
         nx_graph = self._create_lexical_graph(
             elements, self._create_document_node(file_data=file_data)
@@ -294,8 +292,7 @@ class Neo4jUploader(Uploader):
         return True
 
     async def run_async(self, path: Path, file_data: FileData, **kwargs) -> None:  # type: ignore
-        with path.open() as file:
-            staged_data = json.load(file)
+        staged_data = get_json_data(path)
 
         graph_data = _GraphData.model_validate(staged_data)
         async with self.connection_config.get_client() as client:

{unstructured_ingest-0.5.16 → unstructured_ingest-0.5.18}/unstructured_ingest/v2/processes/connectors/onedrive.py

@@ -35,6 +35,10 @@ from unstructured_ingest.v2.processes.connector_registry import (
     DestinationRegistryEntry,
     SourceRegistryEntry,
 )
+from unstructured_ingest.v2.processes.utils.blob_storage import (
+    BlobStoreUploadStager,
+    BlobStoreUploadStagerConfig,
+)
 
 if TYPE_CHECKING:
     from office365.graph_client import GraphClient
@@ -428,4 +432,6 @@ onedrive_destination_entry = DestinationRegistryEntry(
     connection_config=OnedriveConnectionConfig,
     uploader=OnedriveUploader,
     uploader_config=OnedriveUploaderConfig,
+    upload_stager_config=BlobStoreUploadStagerConfig,
+    upload_stager=BlobStoreUploadStager,
 )

{unstructured_ingest-0.5.16 → unstructured_ingest-0.5.18/unstructured_ingest.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.5.16
+Version: 0.5.18
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,13 +22,13 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: tqdm
+Requires-Dist: pydantic>=2.7
+Requires-Dist: python-dateutil
+Requires-Dist: click
 Requires-Dist: dataclasses_json
+Requires-Dist: tqdm
 Requires-Dist: opentelemetry-sdk
-Requires-Dist: python-dateutil
 Requires-Dist: pandas
-Requires-Dist: pydantic>=2.7
-Requires-Dist: click
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.30.0; extra == "remote"
 Provides-Extra: csv
@@ -66,16 +66,16 @@ Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
 Requires-Dist: astrapy; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: fsspec; extra == "azure"
+Requires-Dist: adlfs; 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"
+Requires-Dist: boxfs; extra == "box"
 Provides-Extra: chroma
 Requires-Dist: chromadb; extra == "chroma"
 Provides-Extra: clarifai
@@ -98,12 +98,12 @@ Requires-Dist: duckdb; extra == "duckdb"
 Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
-Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: gcsfs; extra == "gcs"
+Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: fsspec; extra == "gcs"
 Provides-Extra: github
-Requires-Dist: pygithub>1.58.0; extra == "github"
 Requires-Dist: requests; extra == "github"
+Requires-Dist: pygithub>1.58.0; extra == "github"
 Provides-Extra: gitlab
 Requires-Dist: python-gitlab; extra == "gitlab"
 Provides-Extra: google-drive
@@ -124,14 +124,14 @@ Requires-Dist: pymilvus; extra == "milvus"
 Provides-Extra: mongodb
 Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: neo4j
-Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: cymple; extra == "neo4j"
+Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Provides-Extra: notion
+Requires-Dist: notion-client; extra == "notion"
 Requires-Dist: backoff; extra == "notion"
-Requires-Dist: httpx; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
-Requires-Dist: notion-client; extra == "notion"
+Requires-Dist: httpx; extra == "notion"
 Provides-Extra: onedrive
 Requires-Dist: bs4; extra == "onedrive"
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
@@ -178,17 +178,17 @@ Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
 Provides-Extra: singlestore
 Requires-Dist: singlestoredb; extra == "singlestore"
 Provides-Extra: vectara
-Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"
 Requires-Dist: aiofiles; extra == "vectara"
+Requires-Dist: httpx; extra == "vectara"
 Provides-Extra: vastdb
-Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: vastdb; extra == "vastdb"
+Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: ibis; 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"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
@@ -204,8 +204,8 @@ Provides-Extra: openai
 Requires-Dist: tiktoken; extra == "openai"
 Requires-Dist: openai; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"
+Requires-Dist: aioboto3; extra == "bedrock"
 Provides-Extra: togetherai
 Requires-Dist: together; extra == "togetherai"
 Dynamic: author

unstructured_ingest-0.5.16/unstructured_ingest/__version__.py

@@ -1 +0,0 @@
-__version__ = "0.5.16"  # pragma: no cover