forked from watson-developer-cloud/python-sdk
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdiscovery_v1.py
More file actions
6902 lines (6047 loc) · 296 KB
/
discovery_v1.py
File metadata and controls
6902 lines (6047 loc) · 296 KB
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 2018 IBM All Rights Reserved.
#
# 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.
"""
The IBM Watson Discovery Service is a cognitive search and content analytics engine that
you can add to applications to identify patterns, trends and actionable insights to drive
better decision-making. Securely unify structured and unstructured data with pre-enriched
content, and use a simplified query language to eliminate the need for manual filtering of
results.
"""
from __future__ import absolute_import
import json
from .watson_service import datetime_to_string, string_to_datetime
from .watson_service import WatsonService
##############################################################################
# Service
##############################################################################
class DiscoveryV1(WatsonService):
"""The Discovery V1 service."""
default_url = 'https://gateway.watsonplatform.net/discovery/api'
def __init__(self,
version,
url=default_url,
username=None,
password=None,
iam_api_key=None,
iam_access_token=None,
iam_url=None):
"""
Construct a new client for the Discovery service.
:param str version: The API version date to use with the service, in
"YYYY-MM-DD" format. Whenever the API is changed in a backwards
incompatible way, a new minor version of the API is released.
The service uses the API version for the date you specify, or
the most recent version before that date. Note that you should
not programmatically specify the current date at runtime, in
case the API has been updated since your application's release.
Instead, specify a version date that is compatible with your
application, and don't change it until your application is
ready for a later version.
:param str url: The base url to use when contacting the service (e.g.
"https://gateway.watsonplatform.net/discovery/api").
The base url may differ between Bluemix regions.
:param str username: The username used to authenticate with the service.
Username and password credentials are only required to run your
application locally or outside of Bluemix. When running on
Bluemix, the credentials will be automatically loaded from the
`VCAP_SERVICES` environment variable.
:param str password: The password used to authenticate with the service.
Username and password credentials are only required to run your
application locally or outside of Bluemix. When running on
Bluemix, the credentials will be automatically loaded from the
`VCAP_SERVICES` environment variable.
:param str iam_api_key: An API key that can be used to request IAM tokens. If
this API key is provided, the SDK will manage the token and handle the
refreshing.
:param str iam_access_token: An IAM access token is fully managed by the application.
Responsibility falls on the application to refresh the token, either before
it expires or reactively upon receiving a 401 from the service as any requests
made with an expired token will fail.
:param str iam_url: An optional URL for the IAM service API. Defaults to
'https://iam.ng.bluemix.net/identity/token'.
"""
WatsonService.__init__(
self,
vcap_services_name='discovery',
url=url,
username=username,
password=password,
iam_api_key=iam_api_key,
iam_access_token=iam_access_token,
iam_url=iam_url,
use_vcap_services=True)
self.version = version
#########################
# Environments
#########################
def create_environment(self, name, description=None, size=None, **kwargs):
"""
Add an environment.
Creates a new environment. You can create only one environment per service
instance. An attempt to create another environment results in an error.
:param str name: Name that identifies the environment.
:param str description: Description of the environment.
:param int size: **Deprecated**: Size of the environment.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `Environment` response.
:rtype: dict
"""
if name is None:
raise ValueError('name must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
data = {'name': name, 'description': description, 'size': size}
url = '/v1/environments'
response = self.request(
method='POST',
url=url,
headers=headers,
params=params,
json=data,
accept_json=True)
return response
def delete_environment(self, environment_id, **kwargs):
"""
Delete environment.
:param str environment_id: The ID of the environment.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `DeleteEnvironmentResponse` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
url = '/v1/environments/{0}'.format(
*self._encode_path_vars(environment_id))
response = self.request(
method='DELETE',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
def get_environment(self, environment_id, **kwargs):
"""
Get environment info.
:param str environment_id: The ID of the environment.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `Environment` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
url = '/v1/environments/{0}'.format(
*self._encode_path_vars(environment_id))
response = self.request(
method='GET',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
def list_environments(self, name=None, **kwargs):
"""
List environments.
List existing environments for the service instance.
:param str name: Show only the environment with the given name.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `ListEnvironmentsResponse` response.
:rtype: dict
"""
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version, 'name': name}
url = '/v1/environments'
response = self.request(
method='GET',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
def list_fields(self, environment_id, collection_ids, **kwargs):
"""
List fields in specified collections.
Gets a list of the unique fields (and their types) stored in the indexes of the
specified collections.
:param str environment_id: The ID of the environment.
:param list[str] collection_ids: A comma-separated list of collection IDs to be queried against.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `ListCollectionFieldsResponse` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if collection_ids is None:
raise ValueError('collection_ids must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {
'version': self.version,
'collection_ids': self._convert_list(collection_ids)
}
url = '/v1/environments/{0}/fields'.format(
*self._encode_path_vars(environment_id))
response = self.request(
method='GET',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
def update_environment(self,
environment_id,
name=None,
description=None,
**kwargs):
"""
Update an environment.
Updates an environment. The environment's `name` and `description` parameters can
be changed. You must specify a `name` for the environment.
:param str environment_id: The ID of the environment.
:param str name: Name that identifies the environment.
:param str description: Description of the environment.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `Environment` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
data = {'name': name, 'description': description}
url = '/v1/environments/{0}'.format(
*self._encode_path_vars(environment_id))
response = self.request(
method='PUT',
url=url,
headers=headers,
params=params,
json=data,
accept_json=True)
return response
#########################
# Configurations
#########################
def create_configuration(self,
environment_id,
name,
description=None,
conversions=None,
enrichments=None,
normalizations=None,
**kwargs):
"""
Add configuration.
Creates a new configuration. If the input configuration contains the
`configuration_id`, `created`, or `updated` properties, then they are ignored and
overridden by the system, and an error is not returned so that the overridden
fields do not need to be removed when copying a configuration. The configuration
can contain unrecognized JSON fields. Any such fields are ignored and do not
generate an error. This makes it easier to use newer configuration files with
older versions of the API and the service. It also makes it possible for the
tooling to add additional metadata and information to the configuration.
:param str environment_id: The ID of the environment.
:param str name: The name of the configuration.
:param str description: The description of the configuration, if available.
:param Conversions conversions: The document conversion settings for the configuration.
:param list[Enrichment] enrichments: An array of document enrichment settings for the configuration.
:param list[NormalizationOperation] normalizations: Defines operations that can be used to transform the final output JSON into a normalized form. Operations are executed in the order that they appear in the array.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `Configuration` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if name is None:
raise ValueError('name must be provided')
if conversions is not None:
conversions = self._convert_model(conversions, Conversions)
if enrichments is not None:
enrichments = [
self._convert_model(x, Enrichment) for x in enrichments
]
if normalizations is not None:
normalizations = [
self._convert_model(x, NormalizationOperation)
for x in normalizations
]
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
data = {
'name': name,
'description': description,
'conversions': conversions,
'enrichments': enrichments,
'normalizations': normalizations
}
url = '/v1/environments/{0}/configurations'.format(
*self._encode_path_vars(environment_id))
response = self.request(
method='POST',
url=url,
headers=headers,
params=params,
json=data,
accept_json=True)
return response
def delete_configuration(self, environment_id, configuration_id, **kwargs):
"""
Delete a configuration.
The deletion is performed unconditionally. A configuration deletion request
succeeds even if the configuration is referenced by a collection or document
ingestion. However, documents that have already been submitted for processing
continue to use the deleted configuration. Documents are always processed with a
snapshot of the configuration as it existed at the time the document was
submitted.
:param str environment_id: The ID of the environment.
:param str configuration_id: The ID of the configuration.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `DeleteConfigurationResponse` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if configuration_id is None:
raise ValueError('configuration_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
url = '/v1/environments/{0}/configurations/{1}'.format(
*self._encode_path_vars(environment_id, configuration_id))
response = self.request(
method='DELETE',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
def get_configuration(self, environment_id, configuration_id, **kwargs):
"""
Get configuration details.
:param str environment_id: The ID of the environment.
:param str configuration_id: The ID of the configuration.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `Configuration` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if configuration_id is None:
raise ValueError('configuration_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
url = '/v1/environments/{0}/configurations/{1}'.format(
*self._encode_path_vars(environment_id, configuration_id))
response = self.request(
method='GET',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
def list_configurations(self, environment_id, name=None, **kwargs):
"""
List configurations.
Lists existing configurations for the service instance.
:param str environment_id: The ID of the environment.
:param str name: Find configurations with the given name.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `ListConfigurationsResponse` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version, 'name': name}
url = '/v1/environments/{0}/configurations'.format(
*self._encode_path_vars(environment_id))
response = self.request(
method='GET',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
def update_configuration(self,
environment_id,
configuration_id,
name,
description=None,
conversions=None,
enrichments=None,
normalizations=None,
**kwargs):
"""
Update a configuration.
Replaces an existing configuration. * Completely replaces the original
configuration. * The `configuration_id`, `updated`, and `created` fields are
accepted in the request, but they are ignored, and an error is not generated. It
is also acceptable for users to submit an updated configuration with none of the
three properties. * Documents are processed with a snapshot of the configuration
as it was at the time the document was submitted to be ingested. This means that
already submitted documents will not see any updates made to the configuration.
:param str environment_id: The ID of the environment.
:param str configuration_id: The ID of the configuration.
:param str name: The name of the configuration.
:param str description: The description of the configuration, if available.
:param Conversions conversions: The document conversion settings for the configuration.
:param list[Enrichment] enrichments: An array of document enrichment settings for the configuration.
:param list[NormalizationOperation] normalizations: Defines operations that can be used to transform the final output JSON into a normalized form. Operations are executed in the order that they appear in the array.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `Configuration` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if configuration_id is None:
raise ValueError('configuration_id must be provided')
if name is None:
raise ValueError('name must be provided')
if conversions is not None:
conversions = self._convert_model(conversions, Conversions)
if enrichments is not None:
enrichments = [
self._convert_model(x, Enrichment) for x in enrichments
]
if normalizations is not None:
normalizations = [
self._convert_model(x, NormalizationOperation)
for x in normalizations
]
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
data = {
'name': name,
'description': description,
'conversions': conversions,
'enrichments': enrichments,
'normalizations': normalizations
}
url = '/v1/environments/{0}/configurations/{1}'.format(
*self._encode_path_vars(environment_id, configuration_id))
response = self.request(
method='PUT',
url=url,
headers=headers,
params=params,
json=data,
accept_json=True)
return response
#########################
# Test your configuration on a document
#########################
def test_configuration_in_environment(self,
environment_id,
configuration=None,
step=None,
configuration_id=None,
file=None,
metadata=None,
file_content_type=None,
filename=None,
**kwargs):
"""
Test configuration.
Runs a sample document through the default or your configuration and returns
diagnostic information designed to help you understand how the document was
processed. The document is not added to the index.
:param str environment_id: The ID of the environment.
:param str configuration: The configuration to use to process the document. If this part is provided, then the provided configuration is used to process the document. If the `configuration_id` is also provided (both are present at the same time), then request is rejected. The maximum supported configuration size is 1 MB. Configuration parts larger than 1 MB are rejected. See the `GET /configurations/{configuration_id}` operation for an example configuration.
:param str step: Specify to only run the input document through the given step instead of running the input document through the entire ingestion workflow. Valid values are `convert`, `enrich`, and `normalize`.
:param str configuration_id: The ID of the configuration to use to process the document. If the `configuration` form part is also provided (both are present at the same time), then request will be rejected.
:param file file: The content of the document to ingest. The maximum supported file size is 50 megabytes. Files larger than 50 megabytes is rejected.
:param str metadata: If you're using the Data Crawler to upload your documents, you can test a document against the type of metadata that the Data Crawler might send. The maximum supported metadata file size is 1 MB. Metadata parts larger than 1 MB are rejected. Example: ``` { \"Creator\": \"Johnny Appleseed\", \"Subject\": \"Apples\" } ```.
:param str file_content_type: The content type of file.
:param str filename: The filename for file.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `TestDocument` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {
'version': self.version,
'step': step,
'configuration_id': configuration_id
}
configuration_tuple = None
if configuration:
configuration_tuple = (None, configuration, 'text/plain')
file_tuple = None
if file:
if not filename and hasattr(file, 'name'):
filename = file.name
if not filename:
raise ValueError('filename must be provided')
mime_type = file_content_type or 'application/octet-stream'
file_tuple = (filename, file, mime_type)
metadata_tuple = None
if metadata:
metadata_tuple = (None, metadata, 'text/plain')
url = '/v1/environments/{0}/preview'.format(
*self._encode_path_vars(environment_id))
response = self.request(
method='POST',
url=url,
headers=headers,
params=params,
files={
'configuration': configuration_tuple,
'file': file_tuple,
'metadata': metadata_tuple
},
accept_json=True)
return response
#########################
# Collections
#########################
def create_collection(self,
environment_id,
name,
description=None,
configuration_id=None,
language=None,
**kwargs):
"""
Create a collection.
:param str environment_id: The ID of the environment.
:param str name: The name of the collection to be created.
:param str description: A description of the collection.
:param str configuration_id: The ID of the configuration in which the collection is to be created.
:param str language: The language of the documents stored in the collection, in the form of an ISO 639-1 language code.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `Collection` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if name is None:
raise ValueError('name must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
data = {
'name': name,
'description': description,
'configuration_id': configuration_id,
'language': language
}
url = '/v1/environments/{0}/collections'.format(
*self._encode_path_vars(environment_id))
response = self.request(
method='POST',
url=url,
headers=headers,
params=params,
json=data,
accept_json=True)
return response
def delete_collection(self, environment_id, collection_id, **kwargs):
"""
Delete a collection.
:param str environment_id: The ID of the environment.
:param str collection_id: The ID of the collection.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `DeleteCollectionResponse` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if collection_id is None:
raise ValueError('collection_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
url = '/v1/environments/{0}/collections/{1}'.format(
*self._encode_path_vars(environment_id, collection_id))
response = self.request(
method='DELETE',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
def get_collection(self, environment_id, collection_id, **kwargs):
"""
Get collection details.
:param str environment_id: The ID of the environment.
:param str collection_id: The ID of the collection.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `Collection` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if collection_id is None:
raise ValueError('collection_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
url = '/v1/environments/{0}/collections/{1}'.format(
*self._encode_path_vars(environment_id, collection_id))
response = self.request(
method='GET',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
def list_collection_fields(self, environment_id, collection_id, **kwargs):
"""
List unique fields.
Gets a list of the unique fields (and their types) stored in the index.
:param str environment_id: The ID of the environment.
:param str collection_id: The ID of the collection.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `ListCollectionFieldsResponse` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if collection_id is None:
raise ValueError('collection_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
url = '/v1/environments/{0}/collections/{1}/fields'.format(
*self._encode_path_vars(environment_id, collection_id))
response = self.request(
method='GET',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
def list_collections(self, environment_id, name=None, **kwargs):
"""
List collections.
Lists existing collections for the service instance.
:param str environment_id: The ID of the environment.
:param str name: Find collections with the given name.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `ListCollectionsResponse` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version, 'name': name}
url = '/v1/environments/{0}/collections'.format(
*self._encode_path_vars(environment_id))
response = self.request(
method='GET',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
def update_collection(self,
environment_id,
collection_id,
name,
description=None,
configuration_id=None,
**kwargs):
"""
Update a collection.
:param str environment_id: The ID of the environment.
:param str collection_id: The ID of the collection.
:param str name: The name of the collection.
:param str description: A description of the collection.
:param str configuration_id: The ID of the configuration in which the collection is to be updated.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `Collection` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if collection_id is None:
raise ValueError('collection_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
data = {
'name': name,
'description': description,
'configuration_id': configuration_id
}
url = '/v1/environments/{0}/collections/{1}'.format(
*self._encode_path_vars(environment_id, collection_id))
response = self.request(
method='PUT',
url=url,
headers=headers,
params=params,
json=data,
accept_json=True)
return response
#########################
# Expansions
#########################
def create_expansions(self, environment_id, collection_id, expansions,
**kwargs):
"""
Set the expansion list.
Create or replace the Expansion list for this collection. The maximum number of
expanded terms per collection is `500`. The current expansion list is replaced
with the uploaded content.
:param str environment_id: The ID of the environment.
:param str collection_id: The ID of the collection.
:param list[Expansion] expansions: An array of query expansion definitions. Each object in the `expansions` array represents a term or set of terms that will be expanded into other terms. Each expansion object can be configured so that all terms are expanded to all other terms in the object - bi-directional, or a set list of terms can be expanded into a second list of terms - uni-directional. To create a bi-directional expansion specify an `expanded_terms` array. When found in a query, all items in the `expanded_terms` array are then expanded to the other items in the same array. To create a uni-directional expansion, specify both an array of `input_terms` and an array of `expanded_terms`. When items in the `input_terms` array are present in a query, they are expanded using the items listed in the `expanded_terms` array.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `Expansions` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if collection_id is None:
raise ValueError('collection_id must be provided')
if expansions is None:
raise ValueError('expansions must be provided')
expansions = [self._convert_model(x, Expansion) for x in expansions]
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
data = {'expansions': expansions}
url = '/v1/environments/{0}/collections/{1}/expansions'.format(
*self._encode_path_vars(environment_id, collection_id))
response = self.request(
method='POST',
url=url,
headers=headers,
params=params,
json=data,
accept_json=True)
return response
def delete_expansions(self, environment_id, collection_id, **kwargs):
"""
Delete the expansions list.
Remove the expansion information for this collection. The expansion list must be
deleted to disable query expansion for a collection.
:param str environment_id: The ID of the environment.
:param str collection_id: The ID of the collection.
:param dict headers: A `dict` containing the request headers
:rtype: None
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if collection_id is None:
raise ValueError('collection_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
url = '/v1/environments/{0}/collections/{1}/expansions'.format(
*self._encode_path_vars(environment_id, collection_id))
self.request(
method='DELETE',
url=url,
headers=headers,
params=params,
accept_json=True)
return None
def list_expansions(self, environment_id, collection_id, **kwargs):
"""
List current expansions.
Returns the current expansion list for the specified collection. If an expansion
list is not specified, an object with empty expansion arrays is returned.
:param str environment_id: The ID of the environment.
:param str collection_id: The ID of the collection.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `Expansions` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if collection_id is None:
raise ValueError('collection_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
url = '/v1/environments/{0}/collections/{1}/expansions'.format(
*self._encode_path_vars(environment_id, collection_id))
response = self.request(
method='GET',
url=url,
headers=headers,
params=params,
accept_json=True)
return response
#########################
# Documents
#########################
def add_document(self,
environment_id,
collection_id,
file=None,
metadata=None,
file_content_type=None,
filename=None,
**kwargs):
"""
Add a document.
Add a document to a collection with optional metadata. * The `version` query
parameter is still required. * Returns immediately after the system has
accepted the document for processing. * The user must provide document content,
metadata, or both. If the request is missing both document content and metadata,
it is rejected. * The user can set the `Content-Type` parameter on the `file`
part to indicate the media type of the document. If the `Content-Type` parameter
is missing or is one of the generic media types (for example,
`application/octet-stream`), then the service attempts to automatically detect the
document's media type. * The following field names are reserved and will be
filtered out if present after normalization: `id`, `score`, `highlight`, and any
field with the prefix of: `_`, `+`, or `-` * Fields with empty name values
after normalization are filtered out before indexing. * Fields containing the
following characters after normalization are filtered out before indexing: `#` and
`,`.
:param str environment_id: The ID of the environment.
:param str collection_id: The ID of the collection.
:param file file: The content of the document to ingest. The maximum supported file size is 50 megabytes. Files larger than 50 megabytes is rejected.
:param str metadata: If you're using the Data Crawler to upload your documents, you can test a document against the type of metadata that the Data Crawler might send. The maximum supported metadata file size is 1 MB. Metadata parts larger than 1 MB are rejected. Example: ``` { \"Creator\": \"Johnny Appleseed\", \"Subject\": \"Apples\" } ```.
:param str file_content_type: The content type of file.
:param str filename: The filename for file.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `DocumentAccepted` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if collection_id is None:
raise ValueError('collection_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
file_tuple = None
if file:
if not filename and hasattr(file, 'name'):
filename = file.name
if not filename:
raise ValueError('filename must be provided')
mime_type = file_content_type or 'application/octet-stream'
file_tuple = (filename, file, mime_type)
metadata_tuple = None
if metadata:
metadata_tuple = (None, metadata, 'text/plain')
url = '/v1/environments/{0}/collections/{1}/documents'.format(
*self._encode_path_vars(environment_id, collection_id))
response = self.request(
method='POST',
url=url,
headers=headers,
params=params,
files={'file': file_tuple,
'metadata': metadata_tuple},
accept_json=True)
return response
def delete_document(self, environment_id, collection_id, document_id,
**kwargs):
"""
Delete a document.
If the given document ID is invalid, or if the document is not found, then the a
success response is returned (HTTP status code `200`) with the status set to
'deleted'.
:param str environment_id: The ID of the environment.
:param str collection_id: The ID of the collection.
:param str document_id: The ID of the document.
:param dict headers: A `dict` containing the request headers
:return: A `dict` containing the `DeleteDocumentResponse` response.
:rtype: dict
"""
if environment_id is None:
raise ValueError('environment_id must be provided')
if collection_id is None:
raise ValueError('collection_id must be provided')
if document_id is None:
raise ValueError('document_id must be provided')
headers = {}
if 'headers' in kwargs:
headers.update(kwargs.get('headers'))
params = {'version': self.version}
url = '/v1/environments/{0}/collections/{1}/documents/{2}'.format(
*self._encode_path_vars(environment_id, collection_id, document_id))
response = self.request(
method='DELETE',
url=url,
headers=headers,
params=params,
accept_json=True)
return response