/
matching_engine_index_endpoint.py
1521 lines (1342 loc) · 65.7 KB
/
matching_engine_index_endpoint.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# -*- coding: utf-8 -*-
# Copyright 2022 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from dataclasses import dataclass, field
from typing import Dict, List, Optional, Sequence, Tuple
from google.auth import credentials as auth_credentials
from google.cloud.aiplatform import base
from google.cloud.aiplatform import initializer
from google.cloud.aiplatform import matching_engine
from google.cloud.aiplatform import utils
from google.cloud.aiplatform.compat.types import (
machine_resources as gca_machine_resources_compat,
matching_engine_index_endpoint as gca_matching_engine_index_endpoint,
match_service_v1beta1 as gca_match_service_v1beta1,
index_v1beta1 as gca_index_v1beta1,
service_networking as gca_service_networking,
encryption_spec as gca_encryption_spec,
)
from google.cloud.aiplatform.matching_engine._protos import match_service_pb2
from google.cloud.aiplatform.matching_engine._protos import (
match_service_pb2_grpc,
)
from google.protobuf import field_mask_pb2
import grpc
_LOGGER = base.Logger(__name__)
@dataclass
class MatchNeighbor:
"""The id and distance of a nearest neighbor match for a given query embedding.
Args:
id (str):
Required. The id of the neighbor.
distance (float):
Required. The distance to the query embedding.
"""
id: str
distance: float
@dataclass
class Namespace:
"""Namespace specifies the rules for determining the datapoints that are eligible for each matching query, overall query is an AND across namespaces.
Args:
name (str):
Required. The name of this Namespace.
allow_tokens (List(str)):
Optional. The allowed tokens in the namespace.
deny_tokens (List(str)):
Optional. The denied tokens in the namespace. When a token is denied, then matches will be excluded whenever the other datapoint has that token.
For example, if a query specifies [Namespace("color", ["red","blue"], ["purple"])], then that query will match datapoints that are red or blue,
but if those points are also purple, then they will be excluded even if they are red/blue.
"""
name: str
allow_tokens: list = field(default_factory=list)
deny_tokens: list = field(default_factory=list)
@dataclass
class NumericNamespace:
"""NumericNamespace specifies the rules for determining the datapoints that
are eligible for each matching query, overall query is an AND across namespaces.
This uses numeric comparisons.
Args:
name (str):
Required. The name of this numeric namespace.
value_int (int):
Optional. 64 bit integer value for comparison. Must choose one among
`value_int`, `value_float` and `value_double` for intended
precision.
value_float (float):
Optional. 32 bit float value for comparison. Must choose one among
`value_int`, `value_float` and `value_double` for
intended precision.
value_double (float):
Optional. 64b bit float value for comparison. Must choose one among
`value_int`, `value_float` and `value_double` for
intended precision.
operator (str):
Optional. Should be specified for query only, not for a datapoints.
Specify one operator to use for comparison. Datapoints for which
comparisons with query's values are true for the operator and value
combination will be allowlisted. Choose among:
"LESS" for datapoints' values < query's value;
"LESS_EQUAL" for datapoints' values <= query's value;
"EQUAL" for datapoints' values = query's value;
"GREATER_EQUAL" for datapoints' values >= query's value;
"GREATER" for datapoints' values > query's value;
"""
name: str
value_int: Optional[int] = None
value_float: Optional[float] = None
value_double: Optional[float] = None
op: Optional[str] = None
def __post_init__(self):
"""Check NumericNamespace values are of correct types and values are
not all none.
Args:
None.
Raises:
ValueError: Numeric Namespace provided values must be of correct
types and one of value_int, value_float, value_double must exist.
"""
# Check one of
if (
self.value_int is None
and self.value_float is None
and self.value_double is None
):
raise ValueError(
"Must choose one among `value_int`,"
"`value_float` and `value_double` for "
"intended precision."
)
# Check value type
if self.value_int is not None and not isinstance(self.value_int, int):
raise ValueError(
"value_int must be of type int, got" f" { type(self.value_int)}."
)
if self.value_float is not None and not isinstance(self.value_float, float):
raise ValueError(
"value_float must be of type float, got " f"{ type(self.value_float)}."
)
if self.value_double is not None and not isinstance(self.value_double, float):
raise ValueError(
"value_double must be of type float, got "
f"{ type(self.value_double)}."
)
# Check operator validity
if (
self.op
not in gca_index_v1beta1.IndexDatapoint.NumericRestriction.Operator._member_names_
):
raise ValueError(
f"Invalid operator '{self.op}'," " must be one of the valid operators."
)
class MatchingEngineIndexEndpoint(base.VertexAiResourceNounWithFutureManager):
"""Matching Engine index endpoint resource for Vertex AI."""
client_class = utils.IndexEndpointClientWithOverride
_resource_noun = "indexEndpoints"
_getter_method = "get_index_endpoint"
_list_method = "list_index_endpoints"
_delete_method = "delete_index_endpoint"
_parse_resource_name_method = "parse_index_endpoint_path"
_format_resource_name_method = "index_endpoint_path"
def __init__(
self,
index_endpoint_name: str,
project: Optional[str] = None,
location: Optional[str] = None,
credentials: Optional[auth_credentials.Credentials] = None,
):
"""Retrieves an existing index endpoint given a name or ID.
Example Usage:
my_index_endpoint = aiplatform.MatchingEngineIndexEndpoint(
index_endpoint_name='projects/123/locations/us-central1/index_endpoint/my_index_id'
)
or
my_index_endpoint = aiplatform.MatchingEngineIndexEndpoint(
index_endpoint_name='my_index_endpoint_id'
)
Args:
index_endpoint_name (str):
Required. A fully-qualified index endpoint resource name or a index ID.
Example: "projects/123/locations/us-central1/index_endpoints/my_index_id"
or "my_index_id" when project and location are initialized or passed.
project (str):
Optional. Project to retrieve index endpoint from. If not set, project
set in aiplatform.init will be used.
location (str):
Optional. Location to retrieve index endpoint from. If not set, location
set in aiplatform.init will be used.
credentials (auth_credentials.Credentials):
Optional. Custom credentials to use to retrieve this IndexEndpoint. Overrides
credentials set in aiplatform.init.
"""
super().__init__(
project=project,
location=location,
credentials=credentials,
resource_name=index_endpoint_name,
)
self._gca_resource = self._get_gca_resource(resource_name=index_endpoint_name)
self._public_match_client = None
if self.public_endpoint_domain_name:
self._public_match_client = self._instantiate_public_match_client()
self._match_grpc_stub_cache = {}
self._private_service_connect_ip_address = None
@classmethod
def create(
cls,
display_name: str,
network: Optional[str] = None,
public_endpoint_enabled: bool = False,
description: Optional[str] = None,
labels: Optional[Dict[str, str]] = None,
project: Optional[str] = None,
location: Optional[str] = None,
credentials: Optional[auth_credentials.Credentials] = None,
request_metadata: Optional[Sequence[Tuple[str, str]]] = (),
sync: bool = True,
enable_private_service_connect: bool = False,
project_allowlist: Optional[Sequence[str]] = None,
encryption_spec_key_name: Optional[str] = None,
) -> "MatchingEngineIndexEndpoint":
"""Creates a MatchingEngineIndexEndpoint resource.
Example Usage:
my_index_endpoint = aiplatform.IndexEndpoint.create(
display_name='my_endpoint',
)
Args:
display_name (str):
Required. The display name of the IndexEndpoint.
The name can be up to 128 characters long and
can be consist of any UTF-8 characters.
network (str):
Optional. The full name of the Google Compute Engine
`network <https://cloud.google.com/compute/docs/networks-and-firewalls#networks>`__
to which the IndexEndpoint should be peered.
Private services access must already be configured for the network.
If left unspecified, the network set with aiplatform.init will be used.
`Format <https://cloud.google.com/compute/docs/reference/rest/v1/networks/insert>`__:
projects/{project}/global/networks/{network}. Where
{project} is a project number, as in '12345', and {network}
is network name.
public_endpoint_enabled (bool):
Optional. If true, the deployed index will be
accessible through public endpoint.
description (str):
Optional. The description of the IndexEndpoint.
labels (Dict[str, str]):
Optional. The labels with user-defined
metadata to organize your IndexEndpoint.
Label keys and values can be no longer than 64
characters (Unicode codepoints), can only
contain lowercase letters, numeric characters,
underscores and dashes. International characters
are allowed.
See https://goo.gl/xmQnxf for more information
on and examples of labels. No more than 64 user
labels can be associated with one
IndexEndpoint (System labels are excluded)."
System reserved label keys are prefixed with
"aiplatform.googleapis.com/" and are immutable.
project (str):
Optional. Project to create IndexEndpoint in. If not set, project
set in aiplatform.init will be used.
location (str):
Optional. Location to create IndexEndpoint in. If not set, location
set in aiplatform.init will be used.
credentials (auth_credentials.Credentials):
Optional. Custom credentials to use to create IndexEndpoints. Overrides
credentials set in aiplatform.init.
request_metadata (Sequence[Tuple[str, str]]):
Optional. Strings which should be sent along with the request as metadata.
sync (bool):
Optional. Whether to execute this creation synchronously. If False, this method
will be executed in concurrent Future and any downstream object will
be immediately returned and synced when the Future has completed.
enable_private_service_connect (bool):
If true, expose the index endpoint via private service connect.
project_allowlist (Sequence[str]):
Optional. List of projects from which the forwarding rule will
target the service attachment.
encryption_spec_key_name (str):
Optional. The Cloud KMS resource identifier of the customer
managed encryption key used to protect the index endpoint.
Has the form:
``projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key``.
The key needs to be in the same region as where the compute
resource is created.
If set, this index endpoint and all sub-resources of this
index endpoint will be secured by this key.
The key needs to be in the same region as where the index
endpoint is created.
Returns:
MatchingEngineIndexEndpoint - IndexEndpoint resource object
Raises:
ValueError: A network must be instantiated when creating a IndexEndpoint.
"""
network = network or initializer.global_config.network
if not (network or public_endpoint_enabled or enable_private_service_connect):
raise ValueError(
"Please provide `network` argument for Private Service Access endpoint,"
"or provide `enable_private_service_connect` for Private Service"
"Connect endpoint, or provide `public_endpoint_enabled` to"
"deploy to a public endpoint"
)
if (
sum(
bool(network_setting)
for network_setting in [
network,
public_endpoint_enabled,
enable_private_service_connect,
]
)
> 1
):
raise ValueError(
"One and only one among network, public_endpoint_enabled and enable_private_service_connect should be set."
)
return cls._create(
display_name=display_name,
network=network,
public_endpoint_enabled=public_endpoint_enabled,
description=description,
labels=labels,
project=project,
location=location,
credentials=credentials,
request_metadata=request_metadata,
sync=sync,
enable_private_service_connect=enable_private_service_connect,
project_allowlist=project_allowlist,
encryption_spec_key_name=encryption_spec_key_name,
)
@classmethod
@base.optional_sync()
def _create(
cls,
display_name: str,
network: Optional[str] = None,
public_endpoint_enabled: bool = False,
description: Optional[str] = None,
labels: Optional[Dict[str, str]] = None,
project: Optional[str] = None,
location: Optional[str] = None,
credentials: Optional[auth_credentials.Credentials] = None,
request_metadata: Optional[Sequence[Tuple[str, str]]] = (),
sync: bool = True,
enable_private_service_connect: bool = False,
project_allowlist: Optional[Sequence[str]] = None,
encryption_spec_key_name: Optional[str] = None,
) -> "MatchingEngineIndexEndpoint":
"""Helper method to ensure network synchronization and to
create a MatchingEngineIndexEndpoint resource.
Args:
display_name (str):
Required. The display name of the IndexEndpoint.
The name can be up to 128 characters long and
can be consist of any UTF-8 characters.
network (str):
Optional. The full name of the Google Compute Engine
`network <https://cloud.google.com/compute/docs/networks-and-firewalls#networks>`__
to which the IndexEndpoint should be peered.
Private services access must already be configured for the network.
`Format <https://cloud.google.com/compute/docs/reference/rest/v1/networks/insert>`__:
projects/{project}/global/networks/{network}. Where
{project} is a project number, as in '12345', and {network}
is network name.
public_endpoint_enabled (bool):
Optional. If true, the deployed index will be
accessible through public endpoint.
description (str):
Optional. The description of the IndexEndpoint.
labels (Dict[str, str]):
Optional. The labels with user-defined
metadata to organize your IndexEndpoint.
Label keys and values can be no longer than 64
characters (Unicode codepoints), can only
contain lowercase letters, numeric characters,
underscores and dashes. International characters
are allowed.
See https://goo.gl/xmQnxf for more information
on and examples of labels. No more than 64 user
labels can be associated with one
IndexEndpoint (System labels are excluded)."
System reserved label keys are prefixed with
"aiplatform.googleapis.com/" and are immutable.
project (str):
Optional. Project to create IndexEndpoint in. If not set, project
set in aiplatform.init will be used.
location (str):
Optional. Location to create IndexEndpoint in. If not set, location
set in aiplatform.init will be used.
credentials (auth_credentials.Credentials):
Optional. Custom credentials to use to create IndexEndpoints. Overrides
credentials set in aiplatform.init.
request_metadata (Sequence[Tuple[str, str]]):
Optional. Strings which should be sent along with the request as metadata.
sync (bool):
Optional. Whether to execute this creation synchronously. If False, this method
will be executed in concurrent Future and any downstream object will
be immediately returned and synced when the Future has completed.
encryption_spec_key_name (str):
Immutable. Customer-managed encryption key
spec for an IndexEndpoint. If set, this
IndexEndpoint and all sub-resources of this
IndexEndpoint will be secured by this key.
enable_private_service_connect (bool):
Required. If true, expose the IndexEndpoint
via private service connect.
project_allowlist (MutableSequence[str]):
A list of Projects from which the forwarding
rule will target the service attachment.
Returns:
MatchingEngineIndexEndpoint - IndexEndpoint resource object
"""
# public
if public_endpoint_enabled:
gapic_index_endpoint = gca_matching_engine_index_endpoint.IndexEndpoint(
display_name=display_name,
description=description,
public_endpoint_enabled=public_endpoint_enabled,
)
# PSA
elif network:
gapic_index_endpoint = gca_matching_engine_index_endpoint.IndexEndpoint(
display_name=display_name, description=description, network=network
)
# PSC
else:
gapic_index_endpoint = gca_matching_engine_index_endpoint.IndexEndpoint(
display_name=display_name,
description=description,
private_service_connect_config=gca_service_networking.PrivateServiceConnectConfig(
project_allowlist=project_allowlist,
enable_private_service_connect=enable_private_service_connect,
),
)
if encryption_spec_key_name:
gapic_index_endpoint.encryption_spec = gca_encryption_spec.EncryptionSpec(
kms_key_name=encryption_spec_key_name
)
if labels:
utils.validate_labels(labels)
gapic_index_endpoint.labels = labels
api_client = cls._instantiate_client(location=location, credentials=credentials)
create_lro = api_client.create_index_endpoint(
parent=initializer.global_config.common_location_path(
project=project, location=location
),
index_endpoint=gapic_index_endpoint,
metadata=request_metadata,
)
_LOGGER.log_create_with_lro(cls, create_lro)
created_index = create_lro.result()
_LOGGER.log_create_complete(cls, created_index, "index_endpoint")
index_obj = cls(
index_endpoint_name=created_index.name,
project=project,
location=location,
credentials=credentials,
)
return index_obj
def _instantiate_public_match_client(
self,
) -> utils.MatchClientWithOverride:
"""Helper method to instantiates match client with optional
overrides for this endpoint.
Returns:
match_client (match_service_client.MatchServiceClient):
Initialized match client with optional overrides.
"""
return initializer.global_config.create_client(
client_class=utils.MatchClientWithOverride,
credentials=self.credentials,
location_override=self.location,
api_path_override=self.public_endpoint_domain_name,
)
def _instantiate_private_match_service_stub(
self,
deployed_index_id: Optional[str] = None,
ip_address: Optional[str] = None,
) -> match_service_pb2_grpc.MatchServiceStub:
"""Helper method to instantiate private match service stub.
Args:
deployed_index_id (str):
Optional. Required for private service access endpoint.
The user specified ID of the DeployedIndex.
ip_address (str):
Optional. Required for private service connect. The ip address
the forwarding rule makes use of.
Returns:
stub (match_service_pb2_grpc.MatchServiceStub):
Initialized match service stub.
Raises:
RuntimeError: No deployed index with id deployed_index_id found
ValueError: Should not set ip address for networks other than
private service connect.
"""
if ip_address:
# Should only set for Private Service Connect
if self.public_endpoint_domain_name:
raise ValueError(
"MatchingEngineIndexEndpoint is set to use ",
"public network. Could not establish connection using "
"provided ip address",
)
elif self.private_service_access_network:
raise ValueError(
"MatchingEngineIndexEndpoint is set to use ",
"private service access network. Could not establish "
"connection using provided ip address",
)
else:
# Private Service Access, find server ip for deployed index
deployed_indexes = [
deployed_index
for deployed_index in self.deployed_indexes
if deployed_index.id == deployed_index_id
]
if not deployed_indexes:
raise RuntimeError(
f"No deployed index with id '{deployed_index_id}' found"
)
# Retrieve server ip from deployed index
ip_address = deployed_indexes[0].private_endpoints.match_grpc_address
if ip_address not in self._match_grpc_stub_cache:
# Set up channel and stub
channel = grpc.insecure_channel("{}:10000".format(ip_address))
self._match_grpc_stub_cache[
ip_address
] = match_service_pb2_grpc.MatchServiceStub(channel)
return self._match_grpc_stub_cache[ip_address]
@property
def public_endpoint_domain_name(self) -> Optional[str]:
"""Public endpoint DNS name."""
self._assert_gca_resource_is_available()
return self._gca_resource.public_endpoint_domain_name
@property
def private_service_access_network(self) -> Optional[str]:
""" "Private service access network."""
self._assert_gca_resource_is_available()
return self._gca_resource.network
@property
def private_service_connect_ip_address(self) -> Optional[str]:
""" "Private service connect ip address."""
return self._private_service_connect_ip_address
@private_service_connect_ip_address.setter
def private_service_connect_ip_address(self, ip_address: str) -> Optional[str]:
""" "Setter for private service connect ip address."""
self._private_service_connect_ip_address = ip_address
def update(
self,
display_name: str,
description: Optional[str] = None,
labels: Optional[Dict[str, str]] = None,
request_metadata: Optional[Sequence[Tuple[str, str]]] = (),
) -> "MatchingEngineIndexEndpoint":
"""Updates an existing index endpoint resource.
Args:
display_name (str):
Required. The display name of the IndexEndpoint.
The name can be up to 128 characters long and
can be consist of any UTF-8 characters.
description (str):
Optional. The description of the IndexEndpoint.
labels (Dict[str, str]):
Optional. The labels with user-defined
metadata to organize your Indexs.
Label keys and values can be no longer than 64
characters (Unicode codepoints), can only
contain lowercase letters, numeric characters,
underscores and dashes. International characters
are allowed.
See https://goo.gl/xmQnxf for more information
on and examples of labels. No more than 64 user
labels can be associated with one IndexEndpoint
(System labels are excluded)."
System reserved label keys are prefixed with
"aiplatform.googleapis.com/" and are immutable.
request_metadata (Sequence[Tuple[str, str]]):
Optional. Strings which should be sent along with the request as metadata.
Returns:
MatchingEngineIndexEndpoint - The updated index endpoint resource object.
"""
self.wait()
update_mask = list()
if labels:
utils.validate_labels(labels)
update_mask.append("labels")
if display_name is not None:
update_mask.append("display_name")
if description is not None:
update_mask.append("description")
update_mask = field_mask_pb2.FieldMask(paths=update_mask)
gapic_index_endpoint = gca_matching_engine_index_endpoint.IndexEndpoint(
name=self.resource_name,
display_name=display_name,
description=description,
labels=labels,
)
self._gca_resource = self.api_client.update_index_endpoint(
index_endpoint=gapic_index_endpoint,
update_mask=update_mask,
metadata=request_metadata,
)
return self
@staticmethod
def _build_deployed_index(
deployed_index_id: str,
index_resource_name: Optional[str] = None,
display_name: Optional[str] = None,
machine_type: Optional[str] = None,
min_replica_count: Optional[int] = None,
max_replica_count: Optional[int] = None,
enable_access_logging: Optional[bool] = None,
reserved_ip_ranges: Optional[Sequence[str]] = None,
deployment_group: Optional[str] = None,
auth_config_audiences: Optional[Sequence[str]] = None,
auth_config_allowed_issuers: Optional[Sequence[str]] = None,
) -> gca_matching_engine_index_endpoint.DeployedIndex:
"""Builds a DeployedIndex.
Args:
deployed_index_id (str):
Required. The user specified ID of the
DeployedIndex. The ID can be up to 128
characters long and must start with a letter and
only contain letters, numbers, and underscores.
The ID must be unique within the project it is
created in.
index_resource_name (str):
Optional. A fully-qualified index endpoint resource name or a index ID.
Example: "projects/123/locations/us-central1/index_endpoints/my_index_id"
display_name (str):
Optional. The display name of the DeployedIndex. If not provided upon
creation, the Index's display_name is used.
machine_type (str):
Optional. The type of machine. Not specifying machine type will
result in model to be deployed with automatic resources.
min_replica_count (int):
Optional. The minimum number of machine replicas this deployed
model will be always deployed on. If traffic against it increases,
it may dynamically be deployed onto more replicas, and as traffic
decreases, some of these extra replicas may be freed.
If this value is not provided, the value of 2 will be used.
max_replica_count (int):
Optional. The maximum number of replicas this deployed model may
be deployed on when the traffic against it increases. If requested
value is too large, the deployment will error, but if deployment
succeeds then the ability to scale the model to that many replicas
is guaranteed (barring service outages). If traffic against the
deployed model increases beyond what its replicas at maximum may
handle, a portion of the traffic will be dropped. If this value
is not provided, the larger value of min_replica_count or 2 will
be used. If value provided is smaller than min_replica_count, it
will automatically be increased to be min_replica_count.
enable_access_logging (bool):
Optional. If true, private endpoint's access
logs are sent to StackDriver Logging.
These logs are like standard server access logs,
containing information like timestamp and
latency for each MatchRequest.
Note that Stackdriver logs may incur a cost,
especially if the deployed index receives a high
queries per second rate (QPS). Estimate your
costs before enabling this option.
deployed_index_auth_config (google.cloud.aiplatform_v1.types.DeployedIndexAuthConfig):
Optional. If set, the authentication is
enabled for the private endpoint.
reserved_ip_ranges (Sequence[str]):
Optional. A list of reserved ip ranges under
the VPC network that can be used for this
DeployedIndex.
If set, we will deploy the index within the
provided ip ranges. Otherwise, the index might
be deployed to any ip ranges under the provided
VPC network.
The value sohuld be the name of the address
(https://cloud.google.com/compute/docs/reference/rest/v1/addresses)
Example: 'vertex-ai-ip-range'.
deployment_group (str):
Optional. The deployment group can be no longer than 64
characters (eg: 'test', 'prod'). If not set, we will use the
'default' deployment group.
Creating ``deployment_groups`` with ``reserved_ip_ranges``
is a recommended practice when the peered network has
multiple peering ranges. This creates your deployments from
predictable IP spaces for easier traffic administration.
Also, one deployment_group (except 'default') can only be
used with the same reserved_ip_ranges which means if the
deployment_group has been used with reserved_ip_ranges: [a,
b, c], using it with [a, b] or [d, e] is disallowed.
Note: we only support up to 5 deployment groups(not
including 'default').
auth_config_audiences (Sequence[str]):
Optional. The list of JWT
`audiences <https://tools.ietf.org/html/draft-ietf-oauth-json-web-token-32#section-4.1.3>`__.
that are allowed to access. A JWT containing any of these
audiences will be accepted.
auth_config_allowed_issuers (Sequence[str]):
Optional. A list of allowed JWT issuers. Each entry must be a valid
Google service account, in the following format:
``service-account-name@project-id.iam.gserviceaccount.com``
request_metadata (Sequence[Tuple[str, str]]):
Optional. Strings which should be sent along with the request as metadata.
"""
deployed_index = gca_matching_engine_index_endpoint.DeployedIndex(
id=deployed_index_id,
index=index_resource_name,
display_name=display_name,
enable_access_logging=enable_access_logging,
reserved_ip_ranges=reserved_ip_ranges,
deployment_group=deployment_group,
)
if auth_config_audiences and auth_config_allowed_issuers:
deployed_index.deployed_index_auth_config = gca_matching_engine_index_endpoint.DeployedIndexAuthConfig(
auth_provider=gca_matching_engine_index_endpoint.DeployedIndexAuthConfig.AuthProvider(
audiences=auth_config_audiences,
allowed_issuers=auth_config_allowed_issuers,
)
)
if machine_type:
machine_spec = gca_machine_resources_compat.MachineSpec(
machine_type=machine_type
)
deployed_index.dedicated_resources = (
gca_machine_resources_compat.DedicatedResources(
machine_spec=machine_spec,
min_replica_count=min_replica_count,
max_replica_count=max_replica_count,
)
)
else:
deployed_index.automatic_resources = (
gca_machine_resources_compat.AutomaticResources(
min_replica_count=min_replica_count,
max_replica_count=max_replica_count,
)
)
return deployed_index
def deploy_index(
self,
index: matching_engine.MatchingEngineIndex,
deployed_index_id: str,
display_name: Optional[str] = None,
machine_type: Optional[str] = None,
min_replica_count: Optional[int] = None,
max_replica_count: Optional[int] = None,
enable_access_logging: Optional[bool] = None,
reserved_ip_ranges: Optional[Sequence[str]] = None,
deployment_group: Optional[str] = None,
auth_config_audiences: Optional[Sequence[str]] = None,
auth_config_allowed_issuers: Optional[Sequence[str]] = None,
request_metadata: Optional[Sequence[Tuple[str, str]]] = (),
) -> "MatchingEngineIndexEndpoint":
"""Deploys an existing index resource to this endpoint resource.
Args:
index (MatchingEngineIndex):
Required. The Index this is the
deployment of. We may refer to this Index as the
DeployedIndex's "original" Index.
deployed_index_id (str):
Required. The user specified ID of the
DeployedIndex. The ID can be up to 128
characters long and must start with a letter and
only contain letters, numbers, and underscores.
The ID must be unique within the project it is
created in.
display_name (str):
The display name of the DeployedIndex. If not provided upon
creation, the Index's display_name is used.
machine_type (str):
Optional. The type of machine. Not specifying machine type will
result in model to be deployed with automatic resources.
min_replica_count (int):
Optional. The minimum number of machine replicas this deployed
model will be always deployed on. If traffic against it increases,
it may dynamically be deployed onto more replicas, and as traffic
decreases, some of these extra replicas may be freed.
If this value is not provided, the value of 2 will be used.
max_replica_count (int):
Optional. The maximum number of replicas this deployed model may
be deployed on when the traffic against it increases. If requested
value is too large, the deployment will error, but if deployment
succeeds then the ability to scale the model to that many replicas
is guaranteed (barring service outages). If traffic against the
deployed model increases beyond what its replicas at maximum may
handle, a portion of the traffic will be dropped. If this value
is not provided, the larger value of min_replica_count or 2 will
be used. If value provided is smaller than min_replica_count, it
will automatically be increased to be min_replica_count.
enable_access_logging (bool):
Optional. If true, private endpoint's access
logs are sent to StackDriver Logging.
These logs are like standard server access logs,
containing information like timestamp and
latency for each MatchRequest.
Note that Stackdriver logs may incur a cost,
especially if the deployed index receives a high
queries per second rate (QPS). Estimate your
costs before enabling this option.
reserved_ip_ranges (Sequence[str]):
Optional. A list of reserved ip ranges under
the VPC network that can be used for this
DeployedIndex.
If set, we will deploy the index within the
provided ip ranges. Otherwise, the index might
be deployed to any ip ranges under the provided
VPC network.
The value sohuld be the name of the address
(https://cloud.google.com/compute/docs/reference/rest/v1/addresses)
Example: 'vertex-ai-ip-range'.
deployment_group (str):
Optional. The deployment group can be no longer than 64
characters (eg: 'test', 'prod'). If not set, we will use the
'default' deployment group.
Creating ``deployment_groups`` with ``reserved_ip_ranges``
is a recommended practice when the peered network has
multiple peering ranges. This creates your deployments from
predictable IP spaces for easier traffic administration.
Also, one deployment_group (except 'default') can only be
used with the same reserved_ip_ranges which means if the
deployment_group has been used with reserved_ip_ranges: [a,
b, c], using it with [a, b] or [d, e] is disallowed.
Note: we only support up to 5 deployment groups(not
including 'default').
auth_config_audiences (Sequence[str]):
The list of JWT
`audiences <https://tools.ietf.org/html/draft-ietf-oauth-json-web-token-32#section-4.1.3>`__.
that are allowed to access. A JWT containing any of these
audiences will be accepted.
auth_config_audiences and auth_config_allowed_issuers must be passed together.
auth_config_allowed_issuers (Sequence[str]):
A list of allowed JWT issuers. Each entry must be a valid
Google service account, in the following format:
``service-account-name@project-id.iam.gserviceaccount.com``
auth_config_audiences and auth_config_allowed_issuers must be passed together.
request_metadata (Sequence[Tuple[str, str]]):
Optional. Strings which should be sent along with the request as metadata.
Returns:
MatchingEngineIndexEndpoint - IndexEndpoint resource object
"""
self.wait()
_LOGGER.log_action_start_against_resource(
"Deploying index",
"index_endpoint",
self,
)
deployed_index = self._build_deployed_index(
deployed_index_id=deployed_index_id,
index_resource_name=index.resource_name,
display_name=display_name,
machine_type=machine_type,
min_replica_count=min_replica_count,
max_replica_count=max_replica_count,
enable_access_logging=enable_access_logging,
reserved_ip_ranges=reserved_ip_ranges,
deployment_group=deployment_group,
auth_config_audiences=auth_config_audiences,
auth_config_allowed_issuers=auth_config_allowed_issuers,
)
deploy_lro = self.api_client.deploy_index(
index_endpoint=self.resource_name,
deployed_index=deployed_index,
metadata=request_metadata,
)
_LOGGER.log_action_started_against_resource_with_lro(
"Deploy index", "index_endpoint", self.__class__, deploy_lro
)
deploy_lro.result(timeout=None)
_LOGGER.log_action_completed_against_resource(
"index_endpoint", "Deployed index", self
)
# update local resource
self._sync_gca_resource()
return self
def undeploy_index(
self,
deployed_index_id: str,
request_metadata: Optional[Sequence[Tuple[str, str]]] = (),
) -> "MatchingEngineIndexEndpoint":
"""Undeploy a deployed index endpoint resource.
Args:
deployed_index_id (str):
Required. The ID of the DeployedIndex
to be undeployed from the IndexEndpoint.
request_metadata (Sequence[Tuple[str, str]]):
Optional. Strings which should be sent along with the request as metadata.
Returns:
MatchingEngineIndexEndpoint - IndexEndpoint resource object
"""
self.wait()
_LOGGER.log_action_start_against_resource(
"Undeploying index",
"index_endpoint",
self,
)
undeploy_lro = self.api_client.undeploy_index(
index_endpoint=self.resource_name,
deployed_index_id=deployed_index_id,