unstructured-ingest 0.2.1__py3-none-any.whl → 0.2.2__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/test_confluence.py +113 -0
  2. test/integration/connectors/test_kafka.py +67 -0
  3. test/integration/connectors/test_onedrive.py +112 -0
  4. test/integration/connectors/test_qdrant.py +137 -0
  5. test/integration/connectors/utils/docker.py +2 -1
  6. test/integration/connectors/utils/validation.py +73 -22
  7. unstructured_ingest/__version__.py +1 -1
  8. unstructured_ingest/connector/kafka.py +0 -1
  9. unstructured_ingest/interfaces.py +7 -7
  10. unstructured_ingest/v2/processes/chunker.py +2 -2
  11. unstructured_ingest/v2/processes/connectors/__init__.py +12 -1
  12. unstructured_ingest/v2/processes/connectors/confluence.py +195 -0
  13. unstructured_ingest/v2/processes/connectors/databricks/volumes.py +2 -4
  14. unstructured_ingest/v2/processes/connectors/fsspec/fsspec.py +1 -10
  15. unstructured_ingest/v2/processes/connectors/gitlab.py +267 -0
  16. unstructured_ingest/v2/processes/connectors/kafka/__init__.py +13 -0
  17. unstructured_ingest/v2/processes/connectors/kafka/cloud.py +82 -0
  18. unstructured_ingest/v2/processes/connectors/kafka/kafka.py +196 -0
  19. unstructured_ingest/v2/processes/connectors/kafka/local.py +75 -0
  20. unstructured_ingest/v2/processes/connectors/onedrive.py +163 -2
  21. unstructured_ingest/v2/processes/connectors/qdrant/__init__.py +16 -0
  22. unstructured_ingest/v2/processes/connectors/qdrant/cloud.py +59 -0
  23. unstructured_ingest/v2/processes/connectors/qdrant/local.py +58 -0
  24. unstructured_ingest/v2/processes/connectors/qdrant/qdrant.py +168 -0
  25. unstructured_ingest/v2/processes/connectors/qdrant/server.py +60 -0
  26. unstructured_ingest/v2/processes/connectors/sql/snowflake.py +3 -1
  27. unstructured_ingest/v2/processes/connectors/sql/sql.py +2 -4
  28. unstructured_ingest/v2/processes/partitioner.py +14 -3
  29. unstructured_ingest/v2/unstructured_api.py +24 -10
  30. {unstructured_ingest-0.2.1.dist-info → unstructured_ingest-0.2.2.dist-info}/METADATA +22 -22
  31. {unstructured_ingest-0.2.1.dist-info → unstructured_ingest-0.2.2.dist-info}/RECORD +35 -20
  32. {unstructured_ingest-0.2.1.dist-info → unstructured_ingest-0.2.2.dist-info}/LICENSE.md +0 -0
  33. {unstructured_ingest-0.2.1.dist-info → unstructured_ingest-0.2.2.dist-info}/WHEEL +0 -0
  34. {unstructured_ingest-0.2.1.dist-info → unstructured_ingest-0.2.2.dist-info}/entry_points.txt +0 -0
  35. {unstructured_ingest-0.2.1.dist-info → unstructured_ingest-0.2.2.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,196 @@
1
+ from abc import ABC, abstractmethod
2
+ from contextlib import contextmanager
3
+ from dataclasses import dataclass, field
4
+ from pathlib import Path
5
+ from time import time
6
+ from typing import TYPE_CHECKING, Any, ContextManager, Generator, Optional
7
+
8
+ from pydantic import Secret
9
+
10
+ from unstructured_ingest.error import (
11
+ SourceConnectionError,
12
+ SourceConnectionNetworkError,
13
+ )
14
+ from unstructured_ingest.utils.dep_check import requires_dependencies
15
+ from unstructured_ingest.v2.interfaces import (
16
+ AccessConfig,
17
+ ConnectionConfig,
18
+ Downloader,
19
+ DownloaderConfig,
20
+ FileData,
21
+ FileDataSourceMetadata,
22
+ Indexer,
23
+ IndexerConfig,
24
+ SourceIdentifiers,
25
+ download_responses,
26
+ )
27
+ from unstructured_ingest.v2.logger import logger
28
+ from unstructured_ingest.v2.processes.connector_registry import SourceRegistryEntry
29
+
30
+ if TYPE_CHECKING:
31
+ from confluent_kafka import Consumer
32
+
33
+ CONNECTOR_TYPE = "kafka"
34
+
35
+
36
+ class KafkaAccessConfig(AccessConfig, ABC):
37
+ pass
38
+
39
+
40
+ class KafkaConnectionConfig(ConnectionConfig, ABC):
41
+ access_config: Secret[KafkaAccessConfig]
42
+ timeout: Optional[float] = 1.0
43
+ bootstrap_server: str
44
+ port: int
45
+
46
+ @abstractmethod
47
+ def get_consumer_configuration(self) -> dict:
48
+ pass
49
+
50
+ @contextmanager
51
+ @requires_dependencies(["confluent_kafka"], extras="kafka")
52
+ def get_consumer(self) -> ContextManager["Consumer"]:
53
+ from confluent_kafka import Consumer
54
+
55
+ consumer = Consumer(self.get_consumer_configuration())
56
+ try:
57
+ logger.debug("kafka consumer connected")
58
+ yield consumer
59
+ finally:
60
+ consumer.close()
61
+
62
+
63
+ class KafkaIndexerConfig(IndexerConfig):
64
+ topic: str
65
+ num_messages_to_consume: Optional[int] = 100
66
+
67
+ def update_consumer(self, consumer: "Consumer") -> None:
68
+ consumer.subscribe([self.topic])
69
+
70
+
71
+ @dataclass
72
+ class KafkaIndexer(Indexer):
73
+ connection_config: KafkaConnectionConfig
74
+ index_config: KafkaIndexerConfig
75
+ connector_type: str = CONNECTOR_TYPE
76
+
77
+ @contextmanager
78
+ def get_consumer(self) -> ContextManager["Consumer"]:
79
+ with self.connection_config.get_consumer() as consumer:
80
+ self.index_config.update_consumer(consumer=consumer)
81
+ yield consumer
82
+
83
+ @requires_dependencies(["confluent_kafka"], extras="kafka")
84
+ def generate_messages(self) -> Generator[Any, None, None]:
85
+ from confluent_kafka import KafkaError, KafkaException
86
+
87
+ messages_consumed = 0
88
+ max_empty_polls = 10
89
+ empty_polls = 0
90
+ num_messages_to_consume = self.index_config.num_messages_to_consume
91
+ with self.get_consumer() as consumer:
92
+ while messages_consumed < num_messages_to_consume and empty_polls < max_empty_polls:
93
+ msg = consumer.poll(timeout=self.connection_config.timeout)
94
+ if msg is None:
95
+ logger.debug("No Kafka messages found")
96
+ empty_polls += 1
97
+ continue
98
+ if msg.error():
99
+ if msg.error().code() == KafkaError._PARTITION_EOF:
100
+ logger.info(
101
+ "Reached end of partition for topic %s [%d] at offset %d"
102
+ % (msg.topic(), msg.partition(), msg.offset())
103
+ )
104
+ break
105
+ else:
106
+ raise KafkaException(msg.error())
107
+ try:
108
+ empty_polls = 0
109
+ messages_consumed += 1
110
+ yield msg
111
+ finally:
112
+ consumer.commit(asynchronous=False)
113
+
114
+ def generate_file_data(self, msg) -> FileData:
115
+ msg_content = msg.value().decode("utf8")
116
+ identifier = f"{msg.topic()}_{msg.partition()}_{msg.offset()}"
117
+ additional_metadata = {
118
+ "topic": msg.topic(),
119
+ "partition": msg.partition(),
120
+ "offset": msg.offset(),
121
+ "content": msg_content,
122
+ }
123
+ filename = f"{identifier}.txt"
124
+ return FileData(
125
+ identifier=identifier,
126
+ connector_type=self.connector_type,
127
+ source_identifiers=SourceIdentifiers(
128
+ filename=filename,
129
+ fullpath=filename,
130
+ ),
131
+ metadata=FileDataSourceMetadata(
132
+ date_processed=str(time()),
133
+ ),
134
+ additional_metadata=additional_metadata,
135
+ display_name=filename,
136
+ )
137
+
138
+ def run(self) -> Generator[FileData, None, None]:
139
+ for message in self.generate_messages():
140
+ yield self.generate_file_data(message)
141
+
142
+ async def run_async(self, file_data: FileData, **kwargs: Any) -> download_responses:
143
+ raise NotImplementedError()
144
+
145
+ def precheck(self):
146
+ try:
147
+ with self.get_consumer() as consumer:
148
+ cluster_meta = consumer.list_topics(timeout=self.connection_config.timeout)
149
+ current_topics = [
150
+ topic for topic in cluster_meta.topics if topic != "__consumer_offsets"
151
+ ]
152
+ logger.info(f"successfully checked available topics: {current_topics}")
153
+ except Exception as e:
154
+ logger.error(f"failed to validate connection: {e}", exc_info=True)
155
+ raise SourceConnectionError(f"failed to validate connection: {e}")
156
+
157
+
158
+ class KafkaDownloaderConfig(DownloaderConfig):
159
+ pass
160
+
161
+
162
+ @dataclass
163
+ class KafkaDownloader(Downloader):
164
+ connection_config: KafkaConnectionConfig
165
+ download_config: KafkaDownloaderConfig = field(default_factory=KafkaDownloaderConfig)
166
+ connector_type: str = CONNECTOR_TYPE
167
+ version: Optional[str] = None
168
+ source_url: Optional[str] = None
169
+
170
+ def run(self, file_data: FileData, **kwargs: Any) -> download_responses:
171
+ source_identifiers = file_data.source_identifiers
172
+ if source_identifiers is None:
173
+ raise ValueError("FileData is missing source_identifiers")
174
+
175
+ # Build the download path using source_identifiers
176
+ download_path = Path(self.download_dir) / source_identifiers.relative_path
177
+ download_path.parent.mkdir(parents=True, exist_ok=True)
178
+
179
+ try:
180
+ content = file_data.additional_metadata["content"]
181
+ with open(download_path, "w") as file:
182
+ file.write(content)
183
+ except Exception as e:
184
+ logger.error(f"Failed to download file {file_data.identifier}: {e}")
185
+ raise SourceConnectionNetworkError(f"failed to download file {file_data.identifier}")
186
+
187
+ return self.generate_download_response(file_data=file_data, download_path=download_path)
188
+
189
+
190
+ kafka_source_entry = SourceRegistryEntry(
191
+ connection_config=KafkaConnectionConfig,
192
+ indexer=KafkaIndexer,
193
+ indexer_config=KafkaIndexerConfig,
194
+ downloader=KafkaDownloader,
195
+ downloader_config=KafkaDownloaderConfig,
196
+ )
@@ -0,0 +1,75 @@
1
+ import socket
2
+ from dataclasses import dataclass
3
+ from typing import TYPE_CHECKING
4
+
5
+ from pydantic import Field, Secret
6
+
7
+ from unstructured_ingest.v2.processes.connector_registry import SourceRegistryEntry
8
+ from unstructured_ingest.v2.processes.connectors.kafka.kafka import (
9
+ KafkaAccessConfig,
10
+ KafkaConnectionConfig,
11
+ KafkaDownloader,
12
+ KafkaDownloaderConfig,
13
+ KafkaIndexer,
14
+ KafkaIndexerConfig,
15
+ )
16
+
17
+ if TYPE_CHECKING:
18
+ pass
19
+
20
+ CONNECTOR_TYPE = "kafka-local"
21
+
22
+
23
+ class LocalKafkaAccessConfig(KafkaAccessConfig):
24
+ pass
25
+
26
+
27
+ class LocalKafkaConnectionConfig(KafkaConnectionConfig):
28
+ access_config: Secret[LocalKafkaAccessConfig] = Field(
29
+ default=LocalKafkaAccessConfig(), validate_default=True
30
+ )
31
+
32
+ def get_consumer_configuration(self) -> dict:
33
+ bootstrap = self.bootstrap_server
34
+ port = self.port
35
+
36
+ conf = {
37
+ "bootstrap.servers": f"{bootstrap}:{port}",
38
+ "client.id": socket.gethostname(),
39
+ "group.id": "default_group_id",
40
+ "enable.auto.commit": "false",
41
+ "auto.offset.reset": "earliest",
42
+ "message.max.bytes": 10485760,
43
+ }
44
+ return conf
45
+
46
+
47
+ class LocalKafkaIndexerConfig(KafkaIndexerConfig):
48
+ pass
49
+
50
+
51
+ @dataclass
52
+ class LocalKafkaIndexer(KafkaIndexer):
53
+ connection_config: LocalKafkaConnectionConfig
54
+ index_config: LocalKafkaIndexerConfig
55
+ connector_type: str = CONNECTOR_TYPE
56
+
57
+
58
+ class LocalKafkaDownloaderConfig(KafkaDownloaderConfig):
59
+ pass
60
+
61
+
62
+ @dataclass
63
+ class LocalKafkaDownloader(KafkaDownloader):
64
+ connection_config: LocalKafkaConnectionConfig
65
+ download_config: LocalKafkaDownloaderConfig
66
+ connector_type: str = CONNECTOR_TYPE
67
+
68
+
69
+ kafka_local_source_entry = SourceRegistryEntry(
70
+ connection_config=LocalKafkaConnectionConfig,
71
+ indexer=LocalKafkaIndexer,
72
+ indexer_config=LocalKafkaIndexerConfig,
73
+ downloader=LocalKafkaDownloader,
74
+ downloader_config=LocalKafkaDownloaderConfig,
75
+ )
@@ -9,7 +9,11 @@ from typing import TYPE_CHECKING, Any, Generator, Optional
9
9
  from dateutil import parser
10
10
  from pydantic import Field, Secret
11
11
 
12
- from unstructured_ingest.error import SourceConnectionError, SourceConnectionNetworkError
12
+ from unstructured_ingest.error import (
13
+ DestinationConnectionError,
14
+ SourceConnectionError,
15
+ SourceConnectionNetworkError,
16
+ )
13
17
  from unstructured_ingest.utils.dep_check import requires_dependencies
14
18
  from unstructured_ingest.v2.interfaces import (
15
19
  AccessConfig,
@@ -22,16 +26,20 @@ from unstructured_ingest.v2.interfaces import (
22
26
  Indexer,
23
27
  IndexerConfig,
24
28
  SourceIdentifiers,
29
+ Uploader,
30
+ UploaderConfig,
25
31
  download_responses,
26
32
  )
27
33
  from unstructured_ingest.v2.logger import logger
28
34
  from unstructured_ingest.v2.processes.connector_registry import (
35
+ DestinationRegistryEntry,
29
36
  SourceRegistryEntry,
30
37
  )
31
38
 
32
39
  if TYPE_CHECKING:
33
40
  from office365.graph_client import GraphClient
34
41
  from office365.onedrive.driveitems.driveItem import DriveItem
42
+ from office365.onedrive.drives.drive import Drive
35
43
 
36
44
  CONNECTOR_TYPE = "onedrive"
37
45
  MAX_MB_SIZE = 512_000_000
@@ -55,6 +63,11 @@ class OnedriveConnectionConfig(ConnectionConfig):
55
63
  )
56
64
  access_config: Secret[OnedriveAccessConfig]
57
65
 
66
+ def get_drive(self) -> "Drive":
67
+ client = self.get_client()
68
+ drive = client.users[self.user_pname].drive
69
+ return drive
70
+
58
71
  @requires_dependencies(["msal"], extras="onedrive")
59
72
  def get_token(self):
60
73
  from msal import ConfidentialClientApplication
@@ -100,7 +113,6 @@ class OnedriveIndexer(Indexer):
100
113
  raise SourceConnectionError(
101
114
  "{} ({})".format(error, token_resp.get("error_description"))
102
115
  )
103
- self.connection_config.get_client()
104
116
  except Exception as e:
105
117
  logger.error(f"failed to validate connection: {e}", exc_info=True)
106
118
  raise SourceConnectionError(f"failed to validate connection: {e}")
@@ -224,6 +236,149 @@ class OnedriveDownloader(Downloader):
224
236
  return DownloadResponse(file_data=file_data, path=download_path)
225
237
 
226
238
 
239
+ class OnedriveUploaderConfig(UploaderConfig):
240
+ remote_url: str = Field(
241
+ description="URL of the destination in OneDrive, e.g., 'onedrive://Documents/Folder'"
242
+ )
243
+ prefix: str = "onedrive://"
244
+
245
+ @property
246
+ def root_folder(self) -> str:
247
+ url = (
248
+ self.remote_url.replace(self.prefix, "", 1)
249
+ if self.remote_url.startswith(self.prefix)
250
+ else self.remote_url
251
+ )
252
+ return url.split("/")[0]
253
+
254
+ @property
255
+ def url(self) -> str:
256
+ url = (
257
+ self.remote_url.replace(self.prefix, "", 1)
258
+ if self.remote_url.startswith(self.prefix)
259
+ else self.remote_url
260
+ )
261
+ return url
262
+
263
+
264
+ @dataclass
265
+ class OnedriveUploader(Uploader):
266
+ connection_config: OnedriveConnectionConfig
267
+ upload_config: OnedriveUploaderConfig
268
+ connector_type: str = CONNECTOR_TYPE
269
+
270
+ @requires_dependencies(["office365"], extras="onedrive")
271
+ def precheck(self) -> None:
272
+ from office365.runtime.client_request_exception import ClientRequestException
273
+
274
+ try:
275
+ token_resp: dict = self.connection_config.get_token()
276
+ if error := token_resp.get("error"):
277
+ raise SourceConnectionError(
278
+ "{} ({})".format(error, token_resp.get("error_description"))
279
+ )
280
+ drive = self.connection_config.get_drive()
281
+ root = drive.root
282
+ root_folder = self.upload_config.root_folder
283
+ folder = root.get_by_path(root_folder)
284
+ try:
285
+ folder.get().execute_query()
286
+ except ClientRequestException as e:
287
+ if e.message != "The resource could not be found.":
288
+ raise e
289
+ folder = root.create_folder(root_folder).execute_query()
290
+ logger.info(f"successfully created folder: {folder.name}")
291
+ except Exception as e:
292
+ logger.error(f"failed to validate connection: {e}", exc_info=True)
293
+ raise SourceConnectionError(f"failed to validate connection: {e}")
294
+
295
+ def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
296
+ drive = self.connection_config.get_drive()
297
+
298
+ # Use the remote_url from upload_config as the base destination folder
299
+ base_destination_folder = self.upload_config.url
300
+
301
+ # Use the file's relative path to maintain directory structure, if needed
302
+ if file_data.source_identifiers and file_data.source_identifiers.rel_path:
303
+ # Combine the base destination folder with the file's relative path
304
+ destination_path = Path(base_destination_folder) / Path(
305
+ file_data.source_identifiers.rel_path
306
+ )
307
+ else:
308
+ # If no relative path is provided, upload directly to the base destination folder
309
+ destination_path = Path(base_destination_folder) / path.name
310
+
311
+ destination_folder = destination_path.parent
312
+ file_name = destination_path.name
313
+
314
+ # Convert destination folder to a string suitable for OneDrive API
315
+ destination_folder_str = str(destination_folder).replace("\\", "/")
316
+
317
+ # Resolve the destination folder in OneDrive, creating it if necessary
318
+ try:
319
+ # Attempt to get the folder
320
+ folder = drive.root.get_by_path(destination_folder_str)
321
+ folder.get().execute_query()
322
+ except Exception:
323
+ # Folder doesn't exist, create it recursively
324
+ current_folder = drive.root
325
+ for part in destination_folder.parts:
326
+ # Use filter to find the folder by name
327
+ folders = (
328
+ current_folder.children.filter(f"name eq '{part}' and folder ne null")
329
+ .get()
330
+ .execute_query()
331
+ )
332
+ if folders:
333
+ current_folder = folders[0]
334
+ else:
335
+ # Folder doesn't exist, create it
336
+ current_folder = current_folder.create_folder(part).execute_query()
337
+ folder = current_folder
338
+
339
+ # Check the size of the file
340
+ file_size = path.stat().st_size
341
+
342
+ if file_size < MAX_MB_SIZE:
343
+ # Use simple upload for small files
344
+ with path.open("rb") as local_file:
345
+ content = local_file.read()
346
+ logger.info(f"Uploading {path} to {destination_path} using simple upload")
347
+ try:
348
+ uploaded_file = folder.upload(file_name, content).execute_query()
349
+ if not uploaded_file or uploaded_file.name != file_name:
350
+ raise DestinationConnectionError(f"Upload failed for file '{file_name}'")
351
+ # Log details about the uploaded file
352
+ logger.info(
353
+ f"Uploaded file '{uploaded_file.name}' with ID '{uploaded_file.id}'"
354
+ )
355
+ except Exception as e:
356
+ logger.error(f"Failed to upload file '{file_name}': {e}", exc_info=True)
357
+ raise DestinationConnectionError(
358
+ f"Failed to upload file '{file_name}': {e}"
359
+ ) from e
360
+ else:
361
+ # Use resumable upload for large files
362
+ destination_fullpath = f"{destination_folder_str}/{file_name}"
363
+ destination_drive_item = drive.root.item_with_path(destination_fullpath)
364
+
365
+ logger.info(f"Uploading {path} to {destination_fullpath} using resumable upload")
366
+ try:
367
+ uploaded_file = destination_drive_item.resumable_upload(
368
+ source_path=str(path)
369
+ ).execute_query()
370
+ # Validate the upload
371
+ if not uploaded_file or uploaded_file.name != file_name:
372
+ raise DestinationConnectionError(f"Upload failed for file '{file_name}'")
373
+ # Log details about the uploaded file
374
+ logger.info(f"Uploaded file {uploaded_file.name} with ID {uploaded_file.id}")
375
+ except Exception as e:
376
+ logger.error(f"Failed to upload file '{file_name}' using resumable upload: {e}")
377
+ raise DestinationConnectionError(
378
+ f"Failed to upload file '{file_name}' using resumable upload: {e}"
379
+ ) from e
380
+
381
+
227
382
  onedrive_source_entry = SourceRegistryEntry(
228
383
  connection_config=OnedriveConnectionConfig,
229
384
  indexer_config=OnedriveIndexerConfig,
@@ -231,3 +386,9 @@ onedrive_source_entry = SourceRegistryEntry(
231
386
  downloader_config=OnedriveDownloaderConfig,
232
387
  downloader=OnedriveDownloader,
233
388
  )
389
+
390
+ onedrive_destination_entry = DestinationRegistryEntry(
391
+ connection_config=OnedriveConnectionConfig,
392
+ uploader=OnedriveUploader,
393
+ uploader_config=OnedriveUploaderConfig,
394
+ )
@@ -0,0 +1,16 @@
1
+ from __future__ import annotations
2
+
3
+ from unstructured_ingest.v2.processes.connector_registry import (
4
+ add_destination_entry,
5
+ )
6
+
7
+ from .cloud import CONNECTOR_TYPE as CLOUD_CONNECTOR_TYPE
8
+ from .cloud import qdrant_cloud_destination_entry
9
+ from .local import CONNECTOR_TYPE as LOCAL_CONNECTOR_TYPE
10
+ from .local import qdrant_local_destination_entry
11
+ from .server import CONNECTOR_TYPE as SERVER_CONNECTOR_TYPE
12
+ from .server import qdrant_server_destination_entry
13
+
14
+ add_destination_entry(destination_type=CLOUD_CONNECTOR_TYPE, entry=qdrant_cloud_destination_entry)
15
+ add_destination_entry(destination_type=SERVER_CONNECTOR_TYPE, entry=qdrant_server_destination_entry)
16
+ add_destination_entry(destination_type=LOCAL_CONNECTOR_TYPE, entry=qdrant_local_destination_entry)
@@ -0,0 +1,59 @@
1
+ from dataclasses import dataclass
2
+
3
+ from pydantic import Field, Secret
4
+
5
+ from unstructured_ingest.v2.processes.connector_registry import DestinationRegistryEntry
6
+ from unstructured_ingest.v2.processes.connectors.qdrant.qdrant import (
7
+ QdrantAccessConfig,
8
+ QdrantConnectionConfig,
9
+ QdrantUploader,
10
+ QdrantUploaderConfig,
11
+ QdrantUploadStager,
12
+ QdrantUploadStagerConfig,
13
+ )
14
+
15
+ CONNECTOR_TYPE = "qdrant-cloud"
16
+
17
+
18
+ class CloudQdrantAccessConfig(QdrantAccessConfig):
19
+ api_key: str = Field(description="Qdrant API key")
20
+
21
+
22
+ class CloudQdrantConnectionConfig(QdrantConnectionConfig):
23
+ url: str = Field(default=None, description="url of Qdrant Cloud")
24
+ access_config: Secret[CloudQdrantAccessConfig]
25
+
26
+ def get_client_kwargs(self) -> dict:
27
+ return {
28
+ "api_key": self.access_config.get_secret_value().api_key,
29
+ "url": self.url,
30
+ }
31
+
32
+
33
+ class CloudQdrantUploadStagerConfig(QdrantUploadStagerConfig):
34
+ pass
35
+
36
+
37
+ @dataclass
38
+ class CloudQdrantUploadStager(QdrantUploadStager):
39
+ upload_stager_config: CloudQdrantUploadStagerConfig
40
+
41
+
42
+ class CloudQdrantUploaderConfig(QdrantUploaderConfig):
43
+ pass
44
+
45
+
46
+ @dataclass
47
+ class CloudQdrantUploader(QdrantUploader):
48
+ connection_config: CloudQdrantConnectionConfig
49
+ upload_config: CloudQdrantUploaderConfig
50
+ connector_type: str = CONNECTOR_TYPE
51
+
52
+
53
+ qdrant_cloud_destination_entry = DestinationRegistryEntry(
54
+ connection_config=CloudQdrantConnectionConfig,
55
+ uploader=CloudQdrantUploader,
56
+ uploader_config=CloudQdrantUploaderConfig,
57
+ upload_stager=CloudQdrantUploadStager,
58
+ upload_stager_config=CloudQdrantUploadStagerConfig,
59
+ )
@@ -0,0 +1,58 @@
1
+ from dataclasses import dataclass
2
+
3
+ from pydantic import Field, Secret
4
+
5
+ from unstructured_ingest.v2.processes.connector_registry import DestinationRegistryEntry
6
+ from unstructured_ingest.v2.processes.connectors.qdrant.qdrant import (
7
+ QdrantAccessConfig,
8
+ QdrantConnectionConfig,
9
+ QdrantUploader,
10
+ QdrantUploaderConfig,
11
+ QdrantUploadStager,
12
+ QdrantUploadStagerConfig,
13
+ )
14
+
15
+ CONNECTOR_TYPE = "qdrant-local"
16
+
17
+
18
+ class LocalQdrantAccessConfig(QdrantAccessConfig):
19
+ pass
20
+
21
+
22
+ class LocalQdrantConnectionConfig(QdrantConnectionConfig):
23
+ path: str = Field(default=None, description="Persistence path for QdrantLocal.")
24
+ access_config: Secret[LocalQdrantAccessConfig] = Field(
25
+ default_factory=LocalQdrantAccessConfig, validate_default=True
26
+ )
27
+
28
+ def get_client_kwargs(self) -> dict:
29
+ return {"path": self.path}
30
+
31
+
32
+ class LocalQdrantUploadStagerConfig(QdrantUploadStagerConfig):
33
+ pass
34
+
35
+
36
+ @dataclass
37
+ class LocalQdrantUploadStager(QdrantUploadStager):
38
+ upload_stager_config: LocalQdrantUploadStagerConfig
39
+
40
+
41
+ class LocalQdrantUploaderConfig(QdrantUploaderConfig):
42
+ pass
43
+
44
+
45
+ @dataclass
46
+ class LocalQdrantUploader(QdrantUploader):
47
+ connection_config: LocalQdrantConnectionConfig
48
+ upload_config: LocalQdrantUploaderConfig
49
+ connector_type: str = CONNECTOR_TYPE
50
+
51
+
52
+ qdrant_local_destination_entry = DestinationRegistryEntry(
53
+ connection_config=LocalQdrantConnectionConfig,
54
+ uploader=LocalQdrantUploader,
55
+ uploader_config=LocalQdrantUploaderConfig,
56
+ upload_stager=LocalQdrantUploadStager,
57
+ upload_stager_config=LocalQdrantUploadStagerConfig,
58
+ )