unstructured-ingest 0.4.0__py3-none-any.whl → 0.4.2__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of unstructured-ingest might be problematic. Click here for more details.

Files changed (35) hide show
  1. test/integration/connectors/sql/test_databricks_delta_tables.py +10 -10
  2. test/integration/connectors/utils/validation/equality.py +2 -1
  3. test/unit/v2/connectors/databricks/__init__.py +0 -0
  4. test/unit/v2/connectors/databricks/test_volumes_table.py +44 -0
  5. test/unit/v2/connectors/sql/test_sql.py +4 -2
  6. unstructured_ingest/__version__.py +1 -1
  7. unstructured_ingest/utils/data_prep.py +11 -3
  8. unstructured_ingest/utils/html.py +109 -0
  9. unstructured_ingest/utils/ndjson.py +52 -0
  10. unstructured_ingest/v2/interfaces/upload_stager.py +3 -13
  11. unstructured_ingest/v2/pipeline/steps/chunk.py +3 -4
  12. unstructured_ingest/v2/pipeline/steps/embed.py +3 -4
  13. unstructured_ingest/v2/pipeline/steps/partition.py +3 -4
  14. unstructured_ingest/v2/processes/connectors/confluence.py +95 -25
  15. unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py +14 -11
  16. unstructured_ingest/v2/processes/connectors/duckdb/base.py +2 -2
  17. unstructured_ingest/v2/processes/connectors/fsspec/azure.py +8 -8
  18. unstructured_ingest/v2/processes/connectors/fsspec/box.py +7 -7
  19. unstructured_ingest/v2/processes/connectors/fsspec/dropbox.py +9 -9
  20. unstructured_ingest/v2/processes/connectors/fsspec/fsspec.py +41 -9
  21. unstructured_ingest/v2/processes/connectors/fsspec/gcs.py +7 -7
  22. unstructured_ingest/v2/processes/connectors/fsspec/s3.py +8 -8
  23. unstructured_ingest/v2/processes/connectors/fsspec/sftp.py +5 -5
  24. unstructured_ingest/v2/processes/connectors/sql/__init__.py +4 -0
  25. unstructured_ingest/v2/processes/connectors/sql/databricks_delta_tables.py +15 -15
  26. unstructured_ingest/v2/processes/connectors/sql/singlestore.py +2 -1
  27. unstructured_ingest/v2/processes/connectors/sql/sql.py +14 -7
  28. unstructured_ingest/v2/processes/connectors/sql/sqlite.py +2 -1
  29. unstructured_ingest/v2/processes/connectors/sql/vastdb.py +270 -0
  30. {unstructured_ingest-0.4.0.dist-info → unstructured_ingest-0.4.2.dist-info}/METADATA +23 -20
  31. {unstructured_ingest-0.4.0.dist-info → unstructured_ingest-0.4.2.dist-info}/RECORD +35 -30
  32. {unstructured_ingest-0.4.0.dist-info → unstructured_ingest-0.4.2.dist-info}/LICENSE.md +0 -0
  33. {unstructured_ingest-0.4.0.dist-info → unstructured_ingest-0.4.2.dist-info}/WHEEL +0 -0
  34. {unstructured_ingest-0.4.0.dist-info → unstructured_ingest-0.4.2.dist-info}/entry_points.txt +0 -0
  35. {unstructured_ingest-0.4.0.dist-info → unstructured_ingest-0.4.2.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,270 @@
1
+ from contextlib import contextmanager
2
+ from dataclasses import dataclass, field
3
+ from typing import TYPE_CHECKING, Any, Optional
4
+
5
+ import numpy as np
6
+ import pandas as pd
7
+ from pydantic import Field, Secret
8
+
9
+ from unstructured_ingest.error import DestinationConnectionError
10
+ from unstructured_ingest.utils.data_prep import split_dataframe
11
+ from unstructured_ingest.utils.dep_check import requires_dependencies
12
+ from unstructured_ingest.v2.constants import RECORD_ID_LABEL
13
+ from unstructured_ingest.v2.interfaces import (
14
+ FileData,
15
+ )
16
+ from unstructured_ingest.v2.logger import logger
17
+ from unstructured_ingest.v2.processes.connector_registry import (
18
+ DestinationRegistryEntry,
19
+ SourceRegistryEntry,
20
+ )
21
+ from unstructured_ingest.v2.processes.connectors.sql.sql import (
22
+ _COLUMNS,
23
+ SQLAccessConfig,
24
+ SqlBatchFileData,
25
+ SQLConnectionConfig,
26
+ SQLDownloader,
27
+ SQLDownloaderConfig,
28
+ SQLIndexer,
29
+ SQLIndexerConfig,
30
+ SQLUploader,
31
+ SQLUploaderConfig,
32
+ SQLUploadStager,
33
+ SQLUploadStagerConfig,
34
+ )
35
+ from unstructured_ingest.v2.utils import get_enhanced_element_id
36
+
37
+ if TYPE_CHECKING:
38
+ from vastdb import connect as VastdbConnect
39
+ from vastdb import transaction as VastdbTransaction
40
+ from vastdb.table import Table as VastdbTable
41
+
42
+ CONNECTOR_TYPE = "vastdb"
43
+
44
+
45
+ class VastdbAccessConfig(SQLAccessConfig):
46
+ endpoint: Optional[str] = Field(default=None, description="DB endpoint")
47
+ access_key_id: Optional[str] = Field(default=None, description="access key id")
48
+ access_key_secret: Optional[str] = Field(default=None, description="access key secret")
49
+
50
+
51
+ class VastdbConnectionConfig(SQLConnectionConfig):
52
+ access_config: Secret[VastdbAccessConfig] = Field(
53
+ default=VastdbAccessConfig(), validate_default=True
54
+ )
55
+ vastdb_bucket: str
56
+ vastdb_schema: str
57
+ connector_type: str = Field(default=CONNECTOR_TYPE, init=False)
58
+
59
+ @requires_dependencies(["vastdb"], extras="vastdb")
60
+ @contextmanager
61
+ def get_connection(self) -> "VastdbConnect":
62
+ from vastdb import connect
63
+
64
+ access_config = self.access_config.get_secret_value()
65
+ connection = connect(
66
+ endpoint=access_config.endpoint,
67
+ access=access_config.access_key_id,
68
+ secret=access_config.access_key_secret,
69
+ )
70
+ yield connection
71
+
72
+ @contextmanager
73
+ def get_cursor(self) -> "VastdbTransaction":
74
+ with self.get_connection() as connection:
75
+ with connection.transaction() as transaction:
76
+ yield transaction
77
+
78
+ @contextmanager
79
+ def get_table(self, table_name: str) -> "VastdbTable":
80
+ with self.get_cursor() as cursor:
81
+ bucket = cursor.bucket(self.vastdb_bucket)
82
+ schema = bucket.schema(self.vastdb_schema)
83
+ table = schema.table(table_name)
84
+ yield table
85
+
86
+
87
+ class VastdbIndexerConfig(SQLIndexerConfig):
88
+ pass
89
+
90
+
91
+ @dataclass
92
+ class VastdbIndexer(SQLIndexer):
93
+ connection_config: VastdbConnectionConfig
94
+ index_config: VastdbIndexerConfig
95
+ connector_type: str = CONNECTOR_TYPE
96
+
97
+ def _get_doc_ids(self) -> list[str]:
98
+ with self.connection_config.get_table(self.index_config.table_name) as table:
99
+ reader = table.select(columns=[self.index_config.id_column])
100
+ results = reader.read_all() # Build a PyArrow Table from the RecordBatchReader
101
+ ids = sorted([result[self.index_config.id_column] for result in results.to_pylist()])
102
+ return ids
103
+
104
+ def precheck(self) -> None:
105
+ try:
106
+ with self.connection_config.get_table(self.index_config.table_name) as table:
107
+ table.select()
108
+ except Exception as e:
109
+ logger.error(f"failed to validate connection: {e}", exc_info=True)
110
+ raise DestinationConnectionError(f"failed to validate connection: {e}")
111
+
112
+
113
+ class VastdbDownloaderConfig(SQLDownloaderConfig):
114
+ pass
115
+
116
+
117
+ @dataclass
118
+ class VastdbDownloader(SQLDownloader):
119
+ connection_config: VastdbConnectionConfig
120
+ download_config: VastdbDownloaderConfig
121
+ connector_type: str = CONNECTOR_TYPE
122
+
123
+ @requires_dependencies(["ibis"], extras="vastdb")
124
+ def query_db(self, file_data: SqlBatchFileData) -> tuple[list[tuple], list[str]]:
125
+ from ibis import _ # imports the Ibis deferred expression
126
+
127
+ table_name = file_data.additional_metadata.table_name
128
+ id_column = file_data.additional_metadata.id_column
129
+ ids = tuple([item.identifier for item in file_data.batch_items])
130
+
131
+ with self.connection_config.get_table(table_name) as table:
132
+
133
+ predicate = _[id_column].isin(ids)
134
+
135
+ if self.download_config.fields:
136
+ # Vastdb requires the id column to be included in the fields
137
+ fields = self.download_config.fields + [id_column]
138
+ # dict.fromkeys to remove duplicates and keep order
139
+ reader = table.select(columns=list(dict.fromkeys(fields)), predicate=predicate)
140
+ else:
141
+ reader = table.select(predicate=predicate)
142
+ results = reader.read_all()
143
+ df = results.to_pandas()
144
+ return [tuple(r) for r in df.to_numpy()], results.column_names
145
+
146
+
147
+ class VastdbUploadStagerConfig(SQLUploadStagerConfig):
148
+ rename_columns_map: Optional[dict] = Field(
149
+ default=None,
150
+ description="Map of column names to rename, ex: {'old_name': 'new_name'}",
151
+ )
152
+ additional_columns: Optional[list[str]] = Field(
153
+ default_factory=list, description="Additional columns to include in the upload"
154
+ )
155
+
156
+
157
+ class VastdbUploadStager(SQLUploadStager):
158
+ upload_stager_config: VastdbUploadStagerConfig
159
+
160
+ def conform_dict(self, element_dict: dict, file_data: FileData) -> dict:
161
+ data = element_dict.copy()
162
+ metadata: dict[str, Any] = data.pop("metadata", {})
163
+ data_source = metadata.pop("data_source", {})
164
+ coordinates = metadata.pop("coordinates", {})
165
+
166
+ data.update(metadata)
167
+ data.update(data_source)
168
+ data.update(coordinates)
169
+
170
+ data["id"] = get_enhanced_element_id(element_dict=data, file_data=file_data)
171
+
172
+ # remove extraneous, not supported columns
173
+ # but also allow for additional columns
174
+ approved_columns = set(_COLUMNS).union(self.upload_stager_config.additional_columns)
175
+ element = {k: v for k, v in data.items() if k in approved_columns}
176
+ element[RECORD_ID_LABEL] = file_data.identifier
177
+ return element
178
+
179
+ def conform_dataframe(self, df: pd.DataFrame) -> pd.DataFrame:
180
+ df = super().conform_dataframe(df=df)
181
+ if self.upload_stager_config.rename_columns_map:
182
+ df.rename(columns=self.upload_stager_config.rename_columns_map, inplace=True)
183
+ return df
184
+
185
+
186
+ class VastdbUploaderConfig(SQLUploaderConfig):
187
+ pass
188
+
189
+
190
+ @dataclass
191
+ class VastdbUploader(SQLUploader):
192
+ upload_config: VastdbUploaderConfig = field(default_factory=VastdbUploaderConfig)
193
+ connection_config: VastdbConnectionConfig
194
+ connector_type: str = CONNECTOR_TYPE
195
+
196
+ def precheck(self) -> None:
197
+ try:
198
+ with self.connection_config.get_table(self.upload_config.table_name) as table:
199
+ table.select()
200
+ except Exception as e:
201
+ logger.error(f"failed to validate connection: {e}", exc_info=True)
202
+ raise DestinationConnectionError(f"failed to validate connection: {e}")
203
+
204
+ @requires_dependencies(["pyarrow"], extras="vastdb")
205
+ def upload_dataframe(self, df: pd.DataFrame, file_data: FileData) -> None:
206
+ import pyarrow as pa
207
+
208
+ if self.can_delete():
209
+ self.delete_by_record_id(file_data=file_data)
210
+ else:
211
+ logger.warning(
212
+ f"table doesn't contain expected "
213
+ f"record id column "
214
+ f"{self.upload_config.record_id_key}, skipping delete"
215
+ )
216
+ df.replace({np.nan: None}, inplace=True)
217
+ df = self._fit_to_schema(df=df)
218
+
219
+ logger.info(
220
+ f"writing a total of {len(df)} elements via"
221
+ f" document batches to destination"
222
+ f" table named {self.upload_config.table_name}"
223
+ f" with batch size {self.upload_config.batch_size}"
224
+ )
225
+
226
+ for rows in split_dataframe(df=df, chunk_size=self.upload_config.batch_size):
227
+
228
+ with self.connection_config.get_table(self.upload_config.table_name) as table:
229
+ pa_table = pa.Table.from_pandas(rows)
230
+ table.insert(pa_table)
231
+
232
+ def get_table_columns(self) -> list[str]:
233
+ if self._columns is None:
234
+ with self.connection_config.get_table(self.upload_config.table_name) as table:
235
+ self._columns = table.columns().names
236
+ return self._columns
237
+
238
+ @requires_dependencies(["ibis"], extras="vastdb")
239
+ def delete_by_record_id(self, file_data: FileData) -> None:
240
+ from ibis import _ # imports the Ibis deferred expression
241
+
242
+ logger.debug(
243
+ f"deleting any content with data "
244
+ f"{self.upload_config.record_id_key}={file_data.identifier} "
245
+ f"from table {self.upload_config.table_name}"
246
+ )
247
+ predicate = _[self.upload_config.record_id_key].isin([file_data.identifier])
248
+ with self.connection_config.get_table(self.upload_config.table_name) as table:
249
+ # Get the internal row id
250
+ rows_to_delete = table.select(
251
+ columns=[], predicate=predicate, internal_row_id=True
252
+ ).read_all()
253
+ table.delete(rows_to_delete)
254
+
255
+
256
+ vastdb_source_entry = SourceRegistryEntry(
257
+ connection_config=VastdbConnectionConfig,
258
+ indexer_config=VastdbIndexerConfig,
259
+ indexer=VastdbIndexer,
260
+ downloader_config=VastdbDownloaderConfig,
261
+ downloader=VastdbDownloader,
262
+ )
263
+
264
+ vastdb_destination_entry = DestinationRegistryEntry(
265
+ connection_config=VastdbConnectionConfig,
266
+ uploader=VastdbUploader,
267
+ uploader_config=VastdbUploaderConfig,
268
+ upload_stager=VastdbUploadStager,
269
+ upload_stager_config=VastdbUploadStagerConfig,
270
+ )
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: unstructured-ingest
3
- Version: 0.4.0
3
+ Version: 0.4.2
4
4
  Summary: A library that prepares raw documents for downstream ML tasks.
5
5
  Home-page: https://github.com/Unstructured-IO/unstructured-ingest
6
6
  Author: Unstructured Technologies
@@ -22,32 +22,31 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
22
22
  Requires-Python: >=3.9.0,<3.14
23
23
  Description-Content-Type: text/markdown
24
24
  License-File: LICENSE.md
25
- Requires-Dist: click
26
25
  Requires-Dist: pydantic>=2.7
26
+ Requires-Dist: click
27
+ Requires-Dist: tqdm
28
+ Requires-Dist: dataclasses-json
27
29
  Requires-Dist: pandas
28
- Requires-Dist: ndjson
29
30
  Requires-Dist: opentelemetry-sdk
30
31
  Requires-Dist: python-dateutil
31
- Requires-Dist: tqdm
32
- Requires-Dist: dataclasses-json
33
32
  Provides-Extra: airtable
34
33
  Requires-Dist: pyairtable; extra == "airtable"
35
34
  Provides-Extra: astradb
36
35
  Requires-Dist: astrapy; extra == "astradb"
37
36
  Provides-Extra: azure
38
- Requires-Dist: fsspec; extra == "azure"
39
37
  Requires-Dist: adlfs; extra == "azure"
38
+ Requires-Dist: fsspec; extra == "azure"
40
39
  Provides-Extra: azure-ai-search
41
40
  Requires-Dist: azure-search-documents; extra == "azure-ai-search"
42
41
  Provides-Extra: bedrock
43
- Requires-Dist: boto3; extra == "bedrock"
44
42
  Requires-Dist: aioboto3; extra == "bedrock"
43
+ Requires-Dist: boto3; extra == "bedrock"
45
44
  Provides-Extra: biomed
46
45
  Requires-Dist: bs4; extra == "biomed"
47
46
  Requires-Dist: requests; extra == "biomed"
48
47
  Provides-Extra: box
49
- Requires-Dist: fsspec; extra == "box"
50
48
  Requires-Dist: boxfs; extra == "box"
49
+ Requires-Dist: fsspec; extra == "box"
51
50
  Provides-Extra: chroma
52
51
  Requires-Dist: chromadb; extra == "chroma"
53
52
  Provides-Extra: clarifai
@@ -64,8 +63,8 @@ Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
64
63
  Provides-Extra: databricks-volumes
65
64
  Requires-Dist: databricks-sdk; extra == "databricks-volumes"
66
65
  Provides-Extra: delta-table
67
- Requires-Dist: boto3; extra == "delta-table"
68
66
  Requires-Dist: deltalake; extra == "delta-table"
67
+ Requires-Dist: boto3; extra == "delta-table"
69
68
  Provides-Extra: discord
70
69
  Requires-Dist: discord.py; extra == "discord"
71
70
  Provides-Extra: doc
@@ -73,8 +72,8 @@ Requires-Dist: unstructured[docx]; extra == "doc"
73
72
  Provides-Extra: docx
74
73
  Requires-Dist: unstructured[docx]; extra == "docx"
75
74
  Provides-Extra: dropbox
76
- Requires-Dist: fsspec; extra == "dropbox"
77
75
  Requires-Dist: dropboxdrivefs; extra == "dropbox"
76
+ Requires-Dist: fsspec; extra == "dropbox"
78
77
  Provides-Extra: duckdb
79
78
  Requires-Dist: duckdb; extra == "duckdb"
80
79
  Provides-Extra: elasticsearch
@@ -84,8 +83,8 @@ Requires-Dist: sentence-transformers; extra == "embed-huggingface"
84
83
  Provides-Extra: embed-mixedbreadai
85
84
  Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
86
85
  Provides-Extra: embed-octoai
87
- Requires-Dist: tiktoken; extra == "embed-octoai"
88
86
  Requires-Dist: openai; extra == "embed-octoai"
87
+ Requires-Dist: tiktoken; extra == "embed-octoai"
89
88
  Provides-Extra: embed-vertexai
90
89
  Requires-Dist: vertexai; extra == "embed-vertexai"
91
90
  Provides-Extra: embed-voyageai
@@ -93,8 +92,8 @@ Requires-Dist: voyageai; extra == "embed-voyageai"
93
92
  Provides-Extra: epub
94
93
  Requires-Dist: unstructured[epub]; extra == "epub"
95
94
  Provides-Extra: gcs
96
- Requires-Dist: fsspec; extra == "gcs"
97
95
  Requires-Dist: bs4; extra == "gcs"
96
+ Requires-Dist: fsspec; extra == "gcs"
98
97
  Requires-Dist: gcsfs; extra == "gcs"
99
98
  Provides-Extra: github
100
99
  Requires-Dist: pygithub>1.58.0; extra == "github"
@@ -104,8 +103,8 @@ Requires-Dist: python-gitlab; extra == "gitlab"
104
103
  Provides-Extra: google-drive
105
104
  Requires-Dist: google-api-python-client; extra == "google-drive"
106
105
  Provides-Extra: hubspot
107
- Requires-Dist: hubspot-api-client; extra == "hubspot"
108
106
  Requires-Dist: urllib3; extra == "hubspot"
107
+ Requires-Dist: hubspot-api-client; extra == "hubspot"
109
108
  Provides-Extra: jira
110
109
  Requires-Dist: atlassian-python-api; extra == "jira"
111
110
  Provides-Extra: kafka
@@ -123,23 +122,23 @@ Requires-Dist: pymongo; extra == "mongodb"
123
122
  Provides-Extra: msg
124
123
  Requires-Dist: unstructured[msg]; extra == "msg"
125
124
  Provides-Extra: neo4j
125
+ Requires-Dist: networkx; extra == "neo4j"
126
126
  Requires-Dist: cymple; extra == "neo4j"
127
127
  Requires-Dist: neo4j; extra == "neo4j"
128
- Requires-Dist: networkx; extra == "neo4j"
129
128
  Provides-Extra: notion
130
- Requires-Dist: notion-client; extra == "notion"
131
129
  Requires-Dist: htmlBuilder; extra == "notion"
132
130
  Requires-Dist: backoff; extra == "notion"
131
+ Requires-Dist: notion-client; extra == "notion"
133
132
  Requires-Dist: httpx; extra == "notion"
134
133
  Provides-Extra: odt
135
134
  Requires-Dist: unstructured[odt]; extra == "odt"
136
135
  Provides-Extra: onedrive
137
- Requires-Dist: bs4; extra == "onedrive"
138
136
  Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
137
+ Requires-Dist: bs4; extra == "onedrive"
139
138
  Requires-Dist: msal; extra == "onedrive"
140
139
  Provides-Extra: openai
141
- Requires-Dist: tiktoken; extra == "openai"
142
140
  Requires-Dist: openai; extra == "openai"
141
+ Requires-Dist: tiktoken; extra == "openai"
143
142
  Provides-Extra: opensearch
144
143
  Requires-Dist: opensearch-py; extra == "opensearch"
145
144
  Provides-Extra: org
@@ -175,8 +174,8 @@ Requires-Dist: s3fs; extra == "s3"
175
174
  Provides-Extra: salesforce
176
175
  Requires-Dist: simple-salesforce; extra == "salesforce"
177
176
  Provides-Extra: sftp
178
- Requires-Dist: fsspec; extra == "sftp"
179
177
  Requires-Dist: paramiko; extra == "sftp"
178
+ Requires-Dist: fsspec; extra == "sftp"
180
179
  Provides-Extra: sharepoint
181
180
  Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
182
181
  Requires-Dist: msal; extra == "sharepoint"
@@ -191,10 +190,14 @@ Provides-Extra: togetherai
191
190
  Requires-Dist: together; extra == "togetherai"
192
191
  Provides-Extra: tsv
193
192
  Requires-Dist: unstructured[tsv]; extra == "tsv"
193
+ Provides-Extra: vastdb
194
+ Requires-Dist: ibis; extra == "vastdb"
195
+ Requires-Dist: pyarrow; extra == "vastdb"
196
+ Requires-Dist: vastdb; extra == "vastdb"
194
197
  Provides-Extra: vectara
195
- Requires-Dist: httpx; extra == "vectara"
196
- Requires-Dist: requests; extra == "vectara"
197
198
  Requires-Dist: aiofiles; extra == "vectara"
199
+ Requires-Dist: requests; extra == "vectara"
200
+ Requires-Dist: httpx; extra == "vectara"
198
201
  Provides-Extra: weaviate
199
202
  Requires-Dist: weaviate-client; extra == "weaviate"
200
203
  Provides-Extra: wikipedia
@@ -34,7 +34,7 @@ test/integration/connectors/elasticsearch/conftest.py,sha256=-i4_7MkIxSQENz7nuD2
34
34
  test/integration/connectors/elasticsearch/test_elasticsearch.py,sha256=TsSEPsyaTUoEvFBadinrdM0b5C4FoUtEwCv24OUbpO8,12072
35
35
  test/integration/connectors/elasticsearch/test_opensearch.py,sha256=7b7z0GqoBsBqA3IK35N6axmwEMjzJ1l3Fg2WT2c7uqs,11450
36
36
  test/integration/connectors/sql/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
37
- test/integration/connectors/sql/test_databricks_delta_tables.py,sha256=UjVjw5hVoMSNJoYdoYympYow25gvcDAEHLmUmOJKz7I,5036
37
+ test/integration/connectors/sql/test_databricks_delta_tables.py,sha256=aC8B7peVYR8L2QaR18arqR6ffA197IsVkM2quCOVNSo,5046
38
38
  test/integration/connectors/sql/test_postgres.py,sha256=bGDyzLRpgrXO7nl0U8nF2zSNr6ykUG-w8T4daIqUCG4,6970
39
39
  test/integration/connectors/sql/test_singlestore.py,sha256=XeU2s4Kt_3tGyaDYYKTgYjdOyb8j2dnz4TgSMwFUjWs,6153
40
40
  test/integration/connectors/sql/test_snowflake.py,sha256=LEwsRDoC6-rRiwYsqeo5B9Eo6RYygLLGAUsrtrgI9pM,7494
@@ -45,7 +45,7 @@ test/integration/connectors/utils/docker.py,sha256=4g1STiSbYN5qcmDTXyPxVJgwx97O6
45
45
  test/integration/connectors/utils/docker_compose.py,sha256=GVTB6Cel05c0VQ2n4AwkQQx_cBfz13ZTs1HpbaYipNU,2223
46
46
  test/integration/connectors/utils/validation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
47
47
  test/integration/connectors/utils/validation/destination.py,sha256=ZvMSvqz9in35xaoUJGx9rG8oWCU3FYlfLLQ6sfdI0pw,2649
48
- test/integration/connectors/utils/validation/equality.py,sha256=8riUASLHccqnRZLoEv4rz5_ba54PFEHcxfxuJaJy6X0,2570
48
+ test/integration/connectors/utils/validation/equality.py,sha256=R6d_1c-Si5518WJcBcshF_wBRnywnZ0ORQ-NL0xNmGo,2602
49
49
  test/integration/connectors/utils/validation/source.py,sha256=VALU5ms_JBu_eFkp2WQ7oZtJKozJ8MZSJ7h7ZA3Fz_Q,12296
50
50
  test/integration/connectors/utils/validation/utils.py,sha256=xYYvAbqP6_lZyH09_JjB4w2Sf8aQPvDVT5vZTs05ILs,1428
51
51
  test/integration/connectors/weaviate/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -83,8 +83,10 @@ test/unit/v2/chunkers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3h
83
83
  test/unit/v2/chunkers/test_chunkers.py,sha256=HSr3_lsoMw1nkDhkjO0-NOTEomRdR9oxCrSXvcMFecE,1772
84
84
  test/unit/v2/connectors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
85
85
  test/unit/v2/connectors/test_confluence.py,sha256=bXrn_kRb4IQdqkk4rc-P2gJAtPba7n7pNplQgfbqZDY,1047
86
+ test/unit/v2/connectors/databricks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
87
+ test/unit/v2/connectors/databricks/test_volumes_table.py,sha256=-R_EJHqv1BseGRK9VRAZhF-2EXA64LAlhycoyIu556U,1078
86
88
  test/unit/v2/connectors/sql/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
87
- test/unit/v2/connectors/sql/test_sql.py,sha256=6BfOxNqIvf6OoxGmCSucEqDkUOmaKgA6E1FvwOyB9pc,2412
89
+ test/unit/v2/connectors/sql/test_sql.py,sha256=51-AKUBxw6ThO68bjenLopUUuxM88YZb2rMUV8L6YwY,2464
88
90
  test/unit/v2/embedders/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
89
91
  test/unit/v2/embedders/test_bedrock.py,sha256=sW-Vv-u3Yiw8rHPOfE5x_reywXlnozxO49rIMx6_xjo,1071
90
92
  test/unit/v2/embedders/test_huggingface.py,sha256=mkVPym7TZkRJchwHedujgFXWdL9sVMi1W90jpmZ_vxg,1543
@@ -99,7 +101,7 @@ test/unit/v2/partitioners/test_partitioner.py,sha256=iIYg7IpftV3LusoO4H8tr1IHY1U
99
101
  test/unit/v2/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
100
102
  test/unit/v2/utils/data_generator.py,sha256=UoYVNjG4S4wlaA9gceQ82HIpF9_6I1UTHD1_GrQBHp0,973
101
103
  unstructured_ingest/__init__.py,sha256=U4S_2y3zgLZVfMenHRaJFBW8yqh2mUBuI291LGQVOJ8,35
102
- unstructured_ingest/__version__.py,sha256=uG7rkjX1YTBF6-J_mvj3gBQn-ZgW3qMoKBfjt0oZDS8,42
104
+ unstructured_ingest/__version__.py,sha256=Y85nIpRVpjjjl2MW3ZwhLs55JjhABkZJeXfKDAbsRxM,42
103
105
  unstructured_ingest/error.py,sha256=qDncnJgbf5ils956RcO2CGlAKYDT5OaEM9Clv1JVTNc,1448
104
106
  unstructured_ingest/interfaces.py,sha256=OYVUP0bzBJpT-Lz92BDyz_hLBvyfxkuSwWHhUdnUayA,31493
105
107
  unstructured_ingest/logger.py,sha256=S5nSqGcABoQyeicgRnBQFjDScCaTvFVivOCvbo-laL0,4479
@@ -358,9 +360,11 @@ unstructured_ingest/runner/writers/fsspec/s3.py,sha256=kHJq2O3864QBd_tL2SKb0mdyw
358
360
  unstructured_ingest/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
359
361
  unstructured_ingest/utils/chunking.py,sha256=9b3sXMA6L8RW5xAkKQbwdtVudGLAcj_sgT6Grh5tyYM,1870
360
362
  unstructured_ingest/utils/compression.py,sha256=NNiY-2S2Gf3at7zC1PYxMijaEza9vVSzRn5mdFf6mHo,4434
361
- unstructured_ingest/utils/data_prep.py,sha256=FB0LXNvxXQWQSXyn4VecRzcFavIG6kh49yQ-PGsc76k,6837
363
+ unstructured_ingest/utils/data_prep.py,sha256=X3d8Kos1zqX-HQAicF_8TB0BrstRtHrbMzu_1s7mj7M,7191
362
364
  unstructured_ingest/utils/dep_check.py,sha256=SXXcUna2H0RtxA6j1S2NGkvQa9JP2DujWhmyBa7776Y,2400
363
365
  unstructured_ingest/utils/google_filetype.py,sha256=YVspEkiiBrRUSGVeVbsavvLvTmizdy2e6TsjigXTSRU,468
366
+ unstructured_ingest/utils/html.py,sha256=gORKKCkva71JBbOilYtAn_MLLCqV8VKmSjSbpwEOlno,4257
367
+ unstructured_ingest/utils/ndjson.py,sha256=nz8VUOPEgAFdhaDOpuveknvCU4x82fVwqE01qAbElH0,1201
364
368
  unstructured_ingest/utils/string_and_date_utils.py,sha256=kijtPlGAbH376vVjFSo5H_ZhW-FEcMC2sCNsSNwDOjo,1729
365
369
  unstructured_ingest/utils/table.py,sha256=aWjcowDVSClNpEAdR6PY3H7khKu4T6T3QqQE6GjmQ_M,3469
366
370
  unstructured_ingest/v2/__init__.py,sha256=U4S_2y3zgLZVfMenHRaJFBW8yqh2mUBuI291LGQVOJ8,35
@@ -389,19 +393,19 @@ unstructured_ingest/v2/interfaces/file_data.py,sha256=7MyRlj5dijQsCR6W18wQ8fEgJi
389
393
  unstructured_ingest/v2/interfaces/indexer.py,sha256=gsa1MLhFa82BzD2h4Yb7ons0VxRwKINZOrzvHAahwVU,846
390
394
  unstructured_ingest/v2/interfaces/process.py,sha256=BgglTu5K93FnDDopZKKr_rkK2LTZOguR6kcQjKHjF40,392
391
395
  unstructured_ingest/v2/interfaces/processor.py,sha256=VX7JqXlbG1plxMK8THWhWINPbTICaaUEk4XUXhnOixY,3303
392
- unstructured_ingest/v2/interfaces/upload_stager.py,sha256=nbMuo_U6Gqn9bDJrAJTCjrZXKMw_G28OZOuNsT23i0k,3608
396
+ unstructured_ingest/v2/interfaces/upload_stager.py,sha256=9EV9863ODDv0Y5liDT3xh2yiVuFiaVVyCcnwCy6nfkM,3172
393
397
  unstructured_ingest/v2/interfaces/uploader.py,sha256=T2oHbN-d4Px1w1oATKKYZA10aUssqytEpiaqBM92r0Q,1600
394
398
  unstructured_ingest/v2/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
395
399
  unstructured_ingest/v2/pipeline/interfaces.py,sha256=-Y6gPnl-SbNxIx5-dQCmiYSPKUMjivrRlBLIKIUWVeM,8658
396
400
  unstructured_ingest/v2/pipeline/otel.py,sha256=K3pQvWVgWzyOWMKCBUofsH7wTZPJ0Ysw5sLjMBLW41I,1088
397
401
  unstructured_ingest/v2/pipeline/pipeline.py,sha256=7Yg8_xwlSX6lA-oPGlTcn6KXZ9kc51zsoJxME5TiUlw,15956
398
402
  unstructured_ingest/v2/pipeline/steps/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
399
- unstructured_ingest/v2/pipeline/steps/chunk.py,sha256=wmGYmydm3CfoaRd0vXzou-o9h7-3pc2OOeVbzH6QZAI,3212
403
+ unstructured_ingest/v2/pipeline/steps/chunk.py,sha256=LK2ldM24TE4ukX_Z6Z81LpF53orMaRkddM3uhLtT5EQ,3221
400
404
  unstructured_ingest/v2/pipeline/steps/download.py,sha256=nZ4B0d9p-6TgWqrBoKUQPlr8m6dz1RGNr_3OjUhRpWg,8259
401
- unstructured_ingest/v2/pipeline/steps/embed.py,sha256=gafBvg-9CECHxxR0ptm00IwtJyLw1bTXL0yMDz13j0I,3190
405
+ unstructured_ingest/v2/pipeline/steps/embed.py,sha256=iL6X0G5AvKnlfI-3XRWudlb0-6rD_PqyzA3MFmmcn6M,3199
402
406
  unstructured_ingest/v2/pipeline/steps/filter.py,sha256=pju7knTSbB2ll1jC9DPePRDnHlOlvEcU1-sjk6xYGGc,1211
403
407
  unstructured_ingest/v2/pipeline/steps/index.py,sha256=uIiGZeI9pFxkwS91IldXE37UUwAopsinfUgGNL7WJaw,3555
404
- unstructured_ingest/v2/pipeline/steps/partition.py,sha256=5Rr1-J6iGnmFgd02P9v3ExYCqq7QlT0mWZaheuDG6Zk,3273
408
+ unstructured_ingest/v2/pipeline/steps/partition.py,sha256=IJQWaOTcyFlH2bz8WbmynE5Zkd5D8ELOKTnSCnt9Wcc,3282
405
409
  unstructured_ingest/v2/pipeline/steps/stage.py,sha256=VR8SLUJdVva61aieVKyxUHzupTCQbQeaMA0CKu4Fx7o,2347
406
410
  unstructured_ingest/v2/pipeline/steps/uncompress.py,sha256=p2nPFGbcpivPAZO5jDogTfn0iaL5bCFsgBNMejxVbzE,1768
407
411
  unstructured_ingest/v2/pipeline/steps/upload.py,sha256=We4OAtStuZwWKKBCOPhfeAz_vjQt5hgsy_jRCxPzxo4,2010
@@ -417,7 +421,7 @@ unstructured_ingest/v2/processes/connectors/airtable.py,sha256=eeZJe-bBNxt5Sa-XE
417
421
  unstructured_ingest/v2/processes/connectors/astradb.py,sha256=xhUMoUdnrfAY1isZGqsV4lZUsnZNpbvgLyQWQbR4hVo,14814
418
422
  unstructured_ingest/v2/processes/connectors/azure_ai_search.py,sha256=ngPDpU0oZ6m5sxIlB6u5ebQpqCS_SJ-_amCC1KQ03EQ,11529
419
423
  unstructured_ingest/v2/processes/connectors/chroma.py,sha256=VHCnM56qNXuHzovJihrNfJnZbWLJShOe8j12PJFrbL0,7219
420
- unstructured_ingest/v2/processes/connectors/confluence.py,sha256=dE2kEQJT2QamFLsdCHpac_D5G4zTN7RIFRIEvt6XBPc,8238
424
+ unstructured_ingest/v2/processes/connectors/confluence.py,sha256=OdoMK5ZD2HOncquj9c_Xct7bFa6kSGW3qZwfiN1LqtQ,11399
421
425
  unstructured_ingest/v2/processes/connectors/couchbase.py,sha256=i7vuNKsUkN93JRVmg4--MO0ZgbjvhIqt46oYqk9zFSQ,12250
422
426
  unstructured_ingest/v2/processes/connectors/delta_table.py,sha256=SotSXZQ85_6TO906YvFi3yTml8jE9A_zV6nBJ4oTx8A,7075
423
427
  unstructured_ingest/v2/processes/connectors/discord.py,sha256=-e4-cBK4TnHkknK1qIb86AIVMy81lBgC288_iLpTzM8,5246
@@ -443,22 +447,22 @@ unstructured_ingest/v2/processes/connectors/databricks/volumes_aws.py,sha256=TA2
443
447
  unstructured_ingest/v2/processes/connectors/databricks/volumes_azure.py,sha256=cb-EUW0T-linZMkbU6AcKEGWnFHQvhpO5Abtps4P2X0,3532
444
448
  unstructured_ingest/v2/processes/connectors/databricks/volumes_gcp.py,sha256=tR8NubkyHw49IpW_42g6w1Koxlm56EPiPf1lB-eoRSI,2783
445
449
  unstructured_ingest/v2/processes/connectors/databricks/volumes_native.py,sha256=dJLD1fueXf8_0AfC4cg0G7siJZVefz68iuEx2Kq7rMs,2890
446
- unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py,sha256=muj7G2JFO_WwAPub14k0VqDmN3c56t9MA60rM48wal8,4750
450
+ unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py,sha256=2KNLwDZJDhsMAUGCzktEIn4Lvb0nxLWabBOPJbgyoEE,5010
447
451
  unstructured_ingest/v2/processes/connectors/duckdb/__init__.py,sha256=5sVvJCWhU-YkjHIwk4W6BZCanFYK5W4xTpWtQ8xzeB4,561
448
- unstructured_ingest/v2/processes/connectors/duckdb/base.py,sha256=XTV9Pox3_xVmI8YVQWC9Bn6PugbPM49kp4Scv1OXFys,2649
452
+ unstructured_ingest/v2/processes/connectors/duckdb/base.py,sha256=0YBdOpTX5mbRLhP00lRHSMpl2-LfuRpqB1XPMJMxn04,2647
449
453
  unstructured_ingest/v2/processes/connectors/duckdb/duckdb.py,sha256=oUHHaLpO2pWW2Lu4Mc-XFjrA0ze97205WQ_xP95ua4M,4296
450
454
  unstructured_ingest/v2/processes/connectors/duckdb/motherduck.py,sha256=mU5x6SnbFgRsVicNGh4y4gtR6ek7eQFinI0dQQmzMds,4481
451
455
  unstructured_ingest/v2/processes/connectors/elasticsearch/__init__.py,sha256=Zzc0JNPP-eFqpwWw1Gp-XC8H-s__IgkYKzoagECycZY,829
452
456
  unstructured_ingest/v2/processes/connectors/elasticsearch/elasticsearch.py,sha256=MEKU64OsiQmbLPb3ken-WWCIV6-pnFbs_6kjJweG-SY,18813
453
457
  unstructured_ingest/v2/processes/connectors/elasticsearch/opensearch.py,sha256=qRz8Fyr2RSZIPZGkhPeme6AZxM0aX-c_xOa1ZtSr2Kg,6781
454
458
  unstructured_ingest/v2/processes/connectors/fsspec/__init__.py,sha256=TtdeImM7Ypl_n6sl7I1JqX6bGSG0t_FqvCqE3Cy24og,1846
455
- unstructured_ingest/v2/processes/connectors/fsspec/azure.py,sha256=c_ivsh8zWcz2YzKCPyLkyflg7a7nCtMRZejJF8F3g_o,6933
456
- unstructured_ingest/v2/processes/connectors/fsspec/box.py,sha256=hJ8Xli89DAgvIHI2CG8uqYvgFlmQn-AoFDRipOFprDc,5658
457
- unstructured_ingest/v2/processes/connectors/fsspec/dropbox.py,sha256=IoSm1DfWPqJveXUBPR_pZCILQ404KKksR9Fv8kuxfZA,5707
458
- unstructured_ingest/v2/processes/connectors/fsspec/fsspec.py,sha256=rvI0_a5vFB7jU3aThnHxG-AnCxQkV6Jz-TiSpxEjb-s,12764
459
- unstructured_ingest/v2/processes/connectors/fsspec/gcs.py,sha256=xiAewsD5wbkdXDZhwUNTFTORhJV2eLlO4mqqLSf7v0I,6954
460
- unstructured_ingest/v2/processes/connectors/fsspec/s3.py,sha256=8mg25go9bZypbBDb-VSkMOJvh6bEKcRHv_qKrXkqDZg,6400
461
- unstructured_ingest/v2/processes/connectors/fsspec/sftp.py,sha256=JsxXKXNI20mdgwR_A6Rnf4u8fsFwLe3AkJmIe_3NEKY,6150
459
+ unstructured_ingest/v2/processes/connectors/fsspec/azure.py,sha256=fwbHYoRrN0ZRuLdLb5X-Z7nr11rMSY8VhWMhfR3ljQo,6933
460
+ unstructured_ingest/v2/processes/connectors/fsspec/box.py,sha256=VXxEfgJbW8DCOrqLW7mQkSeWqH-HczidTNIE28SgERY,5658
461
+ unstructured_ingest/v2/processes/connectors/fsspec/dropbox.py,sha256=GflyMNCKxYRj6hgO1btyrZ4hx3lXOwbWjHViRw1LIWw,5707
462
+ unstructured_ingest/v2/processes/connectors/fsspec/fsspec.py,sha256=0Z--cPh17W_j4jQkSe2BeeD_j0Tt147Z01gqqF58Z9A,14421
463
+ unstructured_ingest/v2/processes/connectors/fsspec/gcs.py,sha256=uOfm2tLc0r5U3CNkfauuwhGOhP7RJpjyBpHWMDXCk7c,6954
464
+ unstructured_ingest/v2/processes/connectors/fsspec/s3.py,sha256=LcfIU-QgW5oVMF4jMUVm7HSgVcSrQamY6mgXdQuiSjc,6400
465
+ unstructured_ingest/v2/processes/connectors/fsspec/sftp.py,sha256=3cVwVH3fT_JEYzIbl48-NDXdbo7XWX4C4_eqTvgWIro,6150
462
466
  unstructured_ingest/v2/processes/connectors/fsspec/utils.py,sha256=jec_Qfe2hbfahBuY-u8FnvHuv933AI5HwPFjOL3kEEY,456
463
467
  unstructured_ingest/v2/processes/connectors/kafka/__init__.py,sha256=mQJ9Ex-QCfhz-BB5YWTfbPf7xGLd1i7FpjRr0ukbhNw,754
464
468
  unstructured_ingest/v2/processes/connectors/kafka/cloud.py,sha256=GdAeQ8Uz-6v1C5byBHtjfevVfbzW3obScBFFLRTb0ps,3441
@@ -542,21 +546,22 @@ unstructured_ingest/v2/processes/connectors/qdrant/cloud.py,sha256=accJ4sNWBVWV-
542
546
  unstructured_ingest/v2/processes/connectors/qdrant/local.py,sha256=cGEyv3Oy6y4BQ4DU8yhJWMpL82QYwBVdPTxxNuV127U,1588
543
547
  unstructured_ingest/v2/processes/connectors/qdrant/qdrant.py,sha256=BHI7HYSdbS05j2vrjyDvLzVG1WfsM8osKeq-lttlybQ,5437
544
548
  unstructured_ingest/v2/processes/connectors/qdrant/server.py,sha256=odvCZWZp8DmRxLXMR7tHhW-c7UQbix1_zpFdfXfCvKI,1613
545
- unstructured_ingest/v2/processes/connectors/sql/__init__.py,sha256=mxcrncrjeP-C2jqQoTOOpGjV3Bmyfg4efT5lq_c-V1E,1760
546
- unstructured_ingest/v2/processes/connectors/sql/databricks_delta_tables.py,sha256=s_W6wSvyIXZ9mdAxvgSXFeFSze9E7pwIvc38p1hVDLM,8839
549
+ unstructured_ingest/v2/processes/connectors/sql/__init__.py,sha256=NSEZwJDHh_9kFc31LnG14iRtYF3meK2UfUlQfYnwYEQ,2059
550
+ unstructured_ingest/v2/processes/connectors/sql/databricks_delta_tables.py,sha256=SRNplobVKd8fSeauYbLzBNlMb3HRHhinFS281B8aYtY,8854
547
551
  unstructured_ingest/v2/processes/connectors/sql/postgres.py,sha256=BATfX1PQGT2kl8jAbdNKXTojYKJxh3pJV9-h3OBnHGo,5124
548
- unstructured_ingest/v2/processes/connectors/sql/singlestore.py,sha256=-2E9dsdNhjAiuzeSBytBbAhljOhvQ8kN8wvlUESvLo8,5465
552
+ unstructured_ingest/v2/processes/connectors/sql/singlestore.py,sha256=OPBDQ2c_5KjWHEFfqXxf3pQ2tWC-N4MtslMulMgP1Wc,5503
549
553
  unstructured_ingest/v2/processes/connectors/sql/snowflake.py,sha256=QE-WBqrPVjCgcxR5EdVD9iTHBjgDSSSQgWYvq5N61qU,7746
550
- unstructured_ingest/v2/processes/connectors/sql/sql.py,sha256=MZPj-o4OdIrcMPmzMk851w21i9Ms0fm7dTiqegp773k,15813
551
- unstructured_ingest/v2/processes/connectors/sql/sqlite.py,sha256=Q5RAqn5Ccw-pbeKZLkiMn5IVw6EemCMukXzLlS7pDhc,5162
554
+ unstructured_ingest/v2/processes/connectors/sql/sql.py,sha256=O2XBu_E2WqNia9OUTdhTWkYo0xhoMMm6ZuanTz-0V9s,16192
555
+ unstructured_ingest/v2/processes/connectors/sql/sqlite.py,sha256=PRjN_S7UQv0k4ZpSyclW1AJrsrugyxbR-GoOrHvBpks,5200
556
+ unstructured_ingest/v2/processes/connectors/sql/vastdb.py,sha256=4DckpVAXpmMTcoKrWiJbnFQQlcrwMA-GMaDsAYchTUs,9992
552
557
  unstructured_ingest/v2/processes/connectors/weaviate/__init__.py,sha256=NMiwnVWan69KnzVELvaqX34tMhCytIa-C8EDsXVKsEo,856
553
558
  unstructured_ingest/v2/processes/connectors/weaviate/cloud.py,sha256=bXtfEYLquR-BszZ5S_lQ4JbETNs9Vozgpfm8x9egAmE,6251
554
559
  unstructured_ingest/v2/processes/connectors/weaviate/embedded.py,sha256=S8Zg8StuZT-k7tCg1D5YShO1-vJYYk9-M1bE1fIqx64,3014
555
560
  unstructured_ingest/v2/processes/connectors/weaviate/local.py,sha256=LuTBKPseVewsz8VqxRPRLfGEm3BeI9nBZxpy7ZU5tOA,2201
556
561
  unstructured_ingest/v2/processes/connectors/weaviate/weaviate.py,sha256=X1yv1H_orDQ-J965EMXhR2XaURqe8vovSi9n1fk85B4,10499
557
- unstructured_ingest-0.4.0.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
558
- unstructured_ingest-0.4.0.dist-info/METADATA,sha256=YCJmfdIJGlE9lfszi5ybee8wf0rTrB58YmBakeuZ8ac,7928
559
- unstructured_ingest-0.4.0.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
560
- unstructured_ingest-0.4.0.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
561
- unstructured_ingest-0.4.0.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
562
- unstructured_ingest-0.4.0.dist-info/RECORD,,
562
+ unstructured_ingest-0.4.2.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
563
+ unstructured_ingest-0.4.2.dist-info/METADATA,sha256=-3ILUK1wZ1fDgJcT22FO9ZhM_NKKHNBCLvgWBgzvVOY,8051
564
+ unstructured_ingest-0.4.2.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
565
+ unstructured_ingest-0.4.2.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
566
+ unstructured_ingest-0.4.2.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
567
+ unstructured_ingest-0.4.2.dist-info/RECORD,,