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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
|
<html><body>
<style>
body, h1, h2, h3, div, span, p, pre, a {
margin: 0;
padding: 0;
border: 0;
font-weight: inherit;
font-style: inherit;
font-size: 100%;
font-family: inherit;
vertical-align: baseline;
}
body {
font-size: 13px;
padding: 1em;
}
h1 {
font-size: 26px;
margin-bottom: 1em;
}
h2 {
font-size: 24px;
margin-bottom: 1em;
}
h3 {
font-size: 20px;
margin-bottom: 1em;
margin-top: 1em;
}
pre, code {
line-height: 1.5;
font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
}
pre {
margin-top: 0.5em;
}
h1, h2, h3, p {
font-family: Arial, sans serif;
}
h1, h2, h3 {
border-bottom: solid #CCC 1px;
}
.toc_element {
margin-top: 0.5em;
}
.firstline {
margin-left: 2 em;
}
.method {
margin-top: 1em;
border: solid 1px #CCC;
padding: 1em;
background: #EEE;
}
.details {
font-weight: bold;
font-size: 14px;
}
</style>
<h1><a href="discoveryengine_v1alpha.html">Discovery Engine API</a> . <a href="discoveryengine_v1alpha.projects.html">projects</a> . <a href="discoveryengine_v1alpha.projects.locations.html">locations</a> . <a href="discoveryengine_v1alpha.projects.locations.dataStores.html">dataStores</a></h1>
<h2>Instance Methods</h2>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.branches.html">branches()</a></code>
</p>
<p class="firstline">Returns the branches Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.completionConfig.html">completionConfig()</a></code>
</p>
<p class="firstline">Returns the completionConfig Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.completionSuggestions.html">completionSuggestions()</a></code>
</p>
<p class="firstline">Returns the completionSuggestions Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.controls.html">controls()</a></code>
</p>
<p class="firstline">Returns the controls Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.conversations.html">conversations()</a></code>
</p>
<p class="firstline">Returns the conversations Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.models.html">models()</a></code>
</p>
<p class="firstline">Returns the models Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.operations.html">operations()</a></code>
</p>
<p class="firstline">Returns the operations Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.schemas.html">schemas()</a></code>
</p>
<p class="firstline">Returns the schemas Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.servingConfigs.html">servingConfigs()</a></code>
</p>
<p class="firstline">Returns the servingConfigs Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.sessions.html">sessions()</a></code>
</p>
<p class="firstline">Returns the sessions Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.siteSearchEngine.html">siteSearchEngine()</a></code>
</p>
<p class="firstline">Returns the siteSearchEngine Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.suggestionDenyListEntries.html">suggestionDenyListEntries()</a></code>
</p>
<p class="firstline">Returns the suggestionDenyListEntries Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.userEvents.html">userEvents()</a></code>
</p>
<p class="firstline">Returns the userEvents Resource.</p>
<p class="toc_element">
<code><a href="discoveryengine_v1alpha.projects.locations.dataStores.widgetConfigs.html">widgetConfigs()</a></code>
</p>
<p class="firstline">Returns the widgetConfigs Resource.</p>
<p class="toc_element">
<code><a href="#close">close()</a></code></p>
<p class="firstline">Close httplib2 connections.</p>
<p class="toc_element">
<code><a href="#completeQuery">completeQuery(dataStore, includeTailSuggestions=None, query=None, queryModel=None, userPseudoId=None, x__xgafv=None)</a></code></p>
<p class="firstline">Completes the specified user input with keyword suggestions.</p>
<p class="toc_element">
<code><a href="#create">create(parent, body=None, cmekConfigName=None, createAdvancedSiteSearch=None, dataStoreId=None, disableCmek=None, skipDefaultSchemaCreation=None, x__xgafv=None)</a></code></p>
<p class="firstline">Creates a DataStore. DataStore is for storing Documents. To serve these documents for Search, or Recommendation use case, an Engine needs to be created separately.</p>
<p class="toc_element">
<code><a href="#delete">delete(name, x__xgafv=None)</a></code></p>
<p class="firstline">Deletes a DataStore.</p>
<p class="toc_element">
<code><a href="#get">get(name, x__xgafv=None)</a></code></p>
<p class="firstline">Gets a DataStore.</p>
<p class="toc_element">
<code><a href="#getDocumentProcessingConfig">getDocumentProcessingConfig(name, x__xgafv=None)</a></code></p>
<p class="firstline">Gets a DocumentProcessingConfig.</p>
<p class="toc_element">
<code><a href="#getSiteSearchEngine">getSiteSearchEngine(name, x__xgafv=None)</a></code></p>
<p class="firstline">Gets the SiteSearchEngine.</p>
<p class="toc_element">
<code><a href="#list">list(parent, filter=None, pageSize=None, pageToken=None, x__xgafv=None)</a></code></p>
<p class="firstline">Lists all the DataStores associated with the project.</p>
<p class="toc_element">
<code><a href="#list_next">list_next()</a></code></p>
<p class="firstline">Retrieves the next page of results.</p>
<p class="toc_element">
<code><a href="#patch">patch(name, body=None, updateMask=None, x__xgafv=None)</a></code></p>
<p class="firstline">Updates a DataStore</p>
<p class="toc_element">
<code><a href="#updateDocumentProcessingConfig">updateDocumentProcessingConfig(name, body=None, updateMask=None, x__xgafv=None)</a></code></p>
<p class="firstline">Updates the DocumentProcessingConfig. DocumentProcessingConfig is a singleon resource of DataStore. It's empty when DataStore is created. The first call to this method will set up DocumentProcessingConfig.</p>
<h3>Method Details</h3>
<div class="method">
<code class="details" id="close">close()</code>
<pre>Close httplib2 connections.</pre>
</div>
<div class="method">
<code class="details" id="completeQuery">completeQuery(dataStore, includeTailSuggestions=None, query=None, queryModel=None, userPseudoId=None, x__xgafv=None)</code>
<pre>Completes the specified user input with keyword suggestions.
Args:
dataStore: string, Required. The parent data store resource name for which the completion is performed, such as `projects/*/locations/global/collections/default_collection/dataStores/default_data_store`. (required)
includeTailSuggestions: boolean, Indicates if tail suggestions should be returned if there are no suggestions that match the full query. Even if set to true, if there are suggestions that match the full query, those are returned and no tail suggestions are returned.
query: string, Required. The typeahead input used to fetch suggestions. Maximum length is 128 characters.
queryModel: string, Specifies the autocomplete data model. This overrides any model specified in the Configuration > Autocomplete section of the Cloud console. Currently supported values: * `document` - Using suggestions generated from user-imported documents. * `search-history` - Using suggestions generated from the past history of SearchService.Search API calls. Do not use it when there is no traffic for Search API. * `user-event` - Using suggestions generated from user-imported search events. * `document-completable` - Using suggestions taken directly from user-imported document fields marked as completable. Default values: * `document` is the default model for regular dataStores. * `search-history` is the default model for site search dataStores.
userPseudoId: string, A unique identifier for tracking visitors. For example, this could be implemented with an HTTP cookie, which should be able to uniquely identify a visitor on a single device. This unique identifier should not change if the visitor logs in or out of the website. This field should NOT have a fixed value such as `unknown_visitor`. This should be the same identifier as UserEvent.user_pseudo_id and SearchRequest.user_pseudo_id. The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an `INVALID_ARGUMENT` error is returned.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response message for CompletionService.CompleteQuery method.
"querySuggestions": [ # Results of the matched query suggestions. The result list is ordered and the first result is a top suggestion.
{ # Suggestions as search queries.
"completableFieldPaths": [ # The unique document field paths that serve as the source of this suggestion if it was generated from completable fields. This field is only populated for the document-completable model.
"A String",
],
"suggestion": "A String", # The suggestion for the query.
},
],
"tailMatchTriggered": True or False, # True if the returned suggestions are all tail suggestions. For tail matching to be triggered, include_tail_suggestions in the request must be true and there must be no suggestions that match the full query.
}</pre>
</div>
<div class="method">
<code class="details" id="create">create(parent, body=None, cmekConfigName=None, createAdvancedSiteSearch=None, dataStoreId=None, disableCmek=None, skipDefaultSchemaCreation=None, x__xgafv=None)</code>
<pre>Creates a DataStore. DataStore is for storing Documents. To serve these documents for Search, or Recommendation use case, an Engine needs to be created separately.
Args:
parent: string, Required. The parent resource name, such as `projects/{project}/locations/{location}/collections/{collection}`. (required)
body: object, The request body.
The object takes the form of:
{ # DataStore captures global settings and configs at the DataStore level.
"aclEnabled": True or False, # Immutable. Whether data in the DataStore has ACL information. If set to `true`, the source data must have ACL. ACL will be ingested when data is ingested by DocumentService.ImportDocuments methods. When ACL is enabled for the DataStore, Document can't be accessed by calling DocumentService.GetDocument or DocumentService.ListDocuments. Currently ACL is only supported in `GENERIC` industry vertical with non-`PUBLIC_WEBSITE` content config.
"advancedSiteSearchConfig": { # Configuration data for advance site search. # Optional. Configuration for advanced site search.
"disableAutomaticRefresh": True or False, # If set true, automatic refresh is disabled for the DataStore.
"disableInitialIndex": True or False, # If set true, initial indexing is disabled for the DataStore.
},
"billingEstimation": { # Estimation of data size per data store. # Output only. Data size estimation for billing.
"structuredDataSize": "A String", # Data size for structured data in terms of bytes.
"structuredDataUpdateTime": "A String", # Last updated timestamp for structured data.
"unstructuredDataSize": "A String", # Data size for unstructured data in terms of bytes.
"unstructuredDataUpdateTime": "A String", # Last updated timestamp for unstructured data.
"websiteDataSize": "A String", # Data size for websites in terms of bytes.
"websiteDataUpdateTime": "A String", # Last updated timestamp for websites.
},
"cmekConfig": { # Configurations used to enable CMEK data encryption with Cloud KMS keys. # Output only. CMEK-related information for the DataStore.
"isDefault": True or False, # Output only. The default CmekConfig for the Customer.
"kmsKey": "A String", # Required. KMS key resource name which will be used to encrypt resources `projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}`.
"kmsKeyVersion": "A String", # Output only. KMS key version resource name which will be used to encrypt resources `/cryptoKeyVersions/{keyVersion}`.
"lastRotationTimestampMicros": "A String", # Output only. The timestamp of the last key rotation.
"name": "A String", # Required. The name of the CmekConfig of the form `projects/{project}/locations/{location}/cmekConfig` or `projects/{project}/locations/{location}/cmekConfigs/{cmek_config}`.
"notebooklmState": "A String", # Output only. Whether the NotebookLM Corpus is ready to be used.
"singleRegionKeys": [ # Optional. Single-regional CMEKs that are required for some VAIS features.
{ # Metadata for single-regional CMEKs.
"kmsKey": "A String", # Required. Single-regional kms key resource name which will be used to encrypt resources `projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}`.
},
],
"state": "A String", # Output only. The states of the CmekConfig.
},
"contentConfig": "A String", # Immutable. The content config of the data store. If this field is unset, the server behavior defaults to ContentConfig.NO_CONTENT.
"createTime": "A String", # Output only. Timestamp the DataStore was created at.
"defaultSchemaId": "A String", # Output only. The id of the default Schema associated to this data store.
"displayName": "A String", # Required. The data store display name. This field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.
"documentProcessingConfig": { # A singleton resource of DataStore. If it's empty when DataStore is created and DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED, the default parser will default to digital parser. # Configuration for Document understanding and enrichment.
"chunkingConfig": { # Configuration for chunking config. # Whether chunking mode is enabled.
"layoutBasedChunkingConfig": { # Configuration for the layout based chunking. # Configuration for the layout based chunking.
"chunkSize": 42, # The token size limit for each chunk. Supported values: 100-500 (inclusive). Default value: 500.
"includeAncestorHeadings": True or False, # Whether to include appending different levels of headings to chunks from the middle of the document to prevent context loss. Default value: False.
},
},
"defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
"name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
"parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and layout parsing are supported. * `docx`: Override parsing config for DOCX files, only digital parsing and layout parsing are supported. * `pptx`: Override parsing config for PPTX files, only digital parsing and layout parsing are supported. * `xlsm`: Override parsing config for XLSM files, only digital parsing and layout parsing are supported. * `xlsx`: Override parsing config for XLSX files, only digital parsing and layout parsing are supported.
"a_key": { # Related configurations applied to a specific type of document parser.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
},
},
"healthcareFhirConfig": { # Config to data store for `HEALTHCARE_FHIR` vertical. # Optional. Configuration for `HEALTHCARE_FHIR` vertical.
"enableConfigurableSchema": True or False, # Whether to enable configurable schema for `HEALTHCARE_FHIR` vertical. If set to `true`, the predefined healthcare fhir schema can be extended for more customized searching and filtering.
"enableStaticIndexingForBatchIngestion": True or False, # Whether to enable static indexing for `HEALTHCARE_FHIR` batch ingestion. If set to `true`, the batch ingestion will be processed in a static indexing mode which is slower but more capable of handling larger volume.
},
"identityMappingStore": "A String", # Immutable. The fully qualified resource name of the associated IdentityMappingStore. This field can only be set for acl_enabled DataStores with `THIRD_PARTY` or `GSUITE` IdP. Format: `projects/{project}/locations/{location}/identityMappingStores/{identity_mapping_store}`.
"idpConfig": { # Identity Provider Config. # Output only. Data store level identity provider config.
"externalIdpConfig": { # Third party IDP Config. # External Identity provider config.
"workforcePoolName": "A String", # Workforce pool name. Example: "locations/global/workforcePools/pool_id"
},
"idpType": "A String", # Identity provider type configured.
},
"industryVertical": "A String", # Immutable. The industry vertical that the data store registers.
"isInfobotFaqDataStore": True or False, # Optional. If set, this DataStore is an Infobot FAQ DataStore.
"kmsKeyName": "A String", # Input only. The KMS key to be used to protect this DataStore at creation time. Must be set for requests that need to comply with CMEK Org Policy protections. If this field is set and processed successfully, the DataStore will be protected by the KMS key, as indicated in the cmek_config field.
"languageInfo": { # Language info for DataStore. # Language info for DataStore.
"language": "A String", # Output only. Language part of normalized_language_code. E.g.: `en-US` -> `en`, `zh-Hans-HK` -> `zh`, `en` -> `en`.
"languageCode": "A String", # The language code for the DataStore.
"normalizedLanguageCode": "A String", # Output only. This is the normalized form of language_code. E.g.: language_code of `en-GB`, `en_GB`, `en-UK` or `en-gb` will have normalized_language_code of `en-GB`.
"region": "A String", # Output only. Region part of normalized_language_code, if present. E.g.: `en-US` -> `US`, `zh-Hans-HK` -> `HK`, `en` -> ``.
},
"name": "A String", # Immutable. Identifier. The full resource name of the data store. Format: `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"naturalLanguageQueryUnderstandingConfig": { # Configuration for Natural Language Query Understanding. # Optional. Configuration for Natural Language Query Understanding.
"mode": "A String", # Mode of Natural Language Query Understanding. If this field is unset, the behavior defaults to NaturalLanguageQueryUnderstandingConfig.Mode.DISABLED.
},
"servingConfigDataStore": { # Stores information regarding the serving configurations at DataStore level. # Optional. Stores serving config at DataStore level.
"disabledForServing": True or False, # Optional. If set true, the DataStore will not be available for serving search requests.
},
"solutionTypes": [ # The solutions that the data store enrolls. Available solutions for each industry_vertical: * `MEDIA`: `SOLUTION_TYPE_RECOMMENDATION` and `SOLUTION_TYPE_SEARCH`. * `SITE_SEARCH`: `SOLUTION_TYPE_SEARCH` is automatically enrolled. Other solutions cannot be enrolled.
"A String",
],
"startingSchema": { # Defines the structure and layout of a type of document data. # The start schema to use for this DataStore when provisioning it. If unset, a default vertical specialized schema will be used. This field is only used by CreateDataStore API, and will be ignored if used in other APIs. This field will be omitted from all API responses including CreateDataStore API. To retrieve a schema of a DataStore, use SchemaService.GetSchema API instead. The provided schema will be validated against certain rules on schema. Learn more from [this doc](https://cloud.google.com/generative-ai-app-builder/docs/provide-schema).
"fieldConfigs": [ # Output only. Configurations for fields of the schema.
{ # Configurations for fields of a schema. For example, configuring a field is indexable, or searchable.
"advancedSiteSearchDataSources": [ # If this field is set, only the corresponding source will be indexed for this field. Otherwise, the values from different sources are merged. Assuming a page with `` in meta tag, and `` in page map: if this enum is set to METATAGS, we will only index ``; if this enum is not set, we will merge them and index ``.
"A String",
],
"completableOption": "A String", # If completable_option is COMPLETABLE_ENABLED, field values are directly used and returned as suggestions for Autocomplete in CompletionService.CompleteQuery. If completable_option is unset, the server behavior defaults to COMPLETABLE_DISABLED for fields that support setting completable options, which are just `string` fields. For those fields that do not support setting completable options, the server will skip completable option setting, and setting completable_option for those fields will throw `INVALID_ARGUMENT` error.
"dynamicFacetableOption": "A String", # If dynamic_facetable_option is DYNAMIC_FACETABLE_ENABLED, field values are available for dynamic facet. Could only be DYNAMIC_FACETABLE_DISABLED if FieldConfig.indexable_option is INDEXABLE_DISABLED. Otherwise, an `INVALID_ARGUMENT` error will be returned. If dynamic_facetable_option is unset, the server behavior defaults to DYNAMIC_FACETABLE_DISABLED for fields that support setting dynamic facetable options. For those fields that do not support setting dynamic facetable options, such as `object` and `boolean`, the server will skip dynamic facetable option setting, and setting dynamic_facetable_option for those fields will throw `INVALID_ARGUMENT` error.
"fieldPath": "A String", # Required. Field path of the schema field. For example: `title`, `description`, `release_info.release_year`.
"fieldType": "A String", # Output only. Raw type of the field.
"indexableOption": "A String", # If indexable_option is INDEXABLE_ENABLED, field values are indexed so that it can be filtered or faceted in SearchService.Search. If indexable_option is unset, the server behavior defaults to INDEXABLE_DISABLED for fields that support setting indexable options. For those fields that do not support setting indexable options, such as `object` and `boolean` and key properties, the server will skip indexable_option setting, and setting indexable_option for those fields will throw `INVALID_ARGUMENT` error.
"keyPropertyType": "A String", # Output only. Type of the key property that this field is mapped to. Empty string if this is not annotated as mapped to a key property. Example types are `title`, `description`. Full list is defined by `keyPropertyMapping` in the schema field annotation. If the schema field has a `KeyPropertyMapping` annotation, `indexable_option` and `searchable_option` of this field cannot be modified.
"metatagName": "A String", # Optional. The metatag name found in the HTML page. If user defines this field, the value of this metatag name will be used to extract metatag. If the user does not define this field, the FieldConfig.field_path will be used to extract metatag.
"recsFilterableOption": "A String", # If recs_filterable_option is FILTERABLE_ENABLED, field values are filterable by filter expression in RecommendationService.Recommend. If FILTERABLE_ENABLED but the field type is numerical, field values are not filterable by text queries in RecommendationService.Recommend. Only textual fields are supported. If recs_filterable_option is unset, the default setting is FILTERABLE_DISABLED for fields that support setting filterable options. When a field set to [FILTERABLE_DISABLED] is filtered, a warning is generated and an empty result is returned.
"retrievableOption": "A String", # If retrievable_option is RETRIEVABLE_ENABLED, field values are included in the search results. If retrievable_option is unset, the server behavior defaults to RETRIEVABLE_DISABLED for fields that support setting retrievable options. For those fields that do not support setting retrievable options, such as `object` and `boolean`, the server will skip retrievable option setting, and setting retrievable_option for those fields will throw `INVALID_ARGUMENT` error.
"schemaOrgPaths": [ # Field paths for indexing custom attribute from schema.org data. More details of schema.org and its defined types can be found at [schema.org](https://schema.org). It is only used on advanced site search schema. Currently only support full path from root. The full path to a field is constructed by concatenating field names, starting from `_root`, with a period `.` as the delimiter. Examples: * Publish date of the root: _root.datePublished * Publish date of the reviews: _root.review.datePublished
"A String",
],
"searchableOption": "A String", # If searchable_option is SEARCHABLE_ENABLED, field values are searchable by text queries in SearchService.Search. If SEARCHABLE_ENABLED but field type is numerical, field values will not be searchable by text queries in SearchService.Search, as there are no text values associated to numerical fields. If searchable_option is unset, the server behavior defaults to SEARCHABLE_DISABLED for fields that support setting searchable options. Only `string` fields that have no key property mapping support setting searchable_option. For those fields that do not support setting searchable options, the server will skip searchable option setting, and setting searchable_option for those fields will throw `INVALID_ARGUMENT` error.
},
],
"jsonSchema": "A String", # The JSON representation of the schema.
"name": "A String", # Immutable. The full resource name of the schema, in the format of `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/schemas/{schema}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"structSchema": { # The structured representation of the schema.
"a_key": "", # Properties of the object.
},
},
"workspaceConfig": { # Config to store data store type configuration for workspace data # Config to store data store type configuration for workspace data. This must be set when DataStore.content_config is set as DataStore.ContentConfig.GOOGLE_WORKSPACE.
"dasherCustomerId": "A String", # Obfuscated Dasher customer ID.
"superAdminEmailAddress": "A String", # Optional. The super admin email address for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
"superAdminServiceAccount": "A String", # Optional. The super admin service account for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
"type": "A String", # The Google Workspace data source.
},
}
cmekConfigName: string, Resource name of the CmekConfig to use for protecting this DataStore.
createAdvancedSiteSearch: boolean, A boolean flag indicating whether user want to directly create an advanced data store for site search. If the data store is not configured as site search (GENERIC vertical and PUBLIC_WEBSITE content_config), this flag will be ignored.
dataStoreId: string, Required. The ID to use for the DataStore, which will become the final component of the DataStore's resource name. This field must conform to [RFC-1034](https://tools.ietf.org/html/rfc1034) standard with a length limit of 63 characters. Otherwise, an INVALID_ARGUMENT error is returned.
disableCmek: boolean, DataStore without CMEK protections. If a default CmekConfig is set for the project, setting this field will override the default CmekConfig as well.
skipDefaultSchemaCreation: boolean, A boolean flag indicating whether to skip the default schema creation for the data store. Only enable this flag if you are certain that the default schema is incompatible with your use case. If set to true, you must manually create a schema for the data store before any documents can be ingested. This flag cannot be specified if `data_store.starting_schema` is specified.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}</pre>
</div>
<div class="method">
<code class="details" id="delete">delete(name, x__xgafv=None)</code>
<pre>Deletes a DataStore.
Args:
name: string, Required. Full resource name of DataStore, such as `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`. If the caller does not have permission to delete the DataStore, regardless of whether or not it exists, a PERMISSION_DENIED error is returned. If the DataStore to delete does not exist, a NOT_FOUND error is returned. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}</pre>
</div>
<div class="method">
<code class="details" id="get">get(name, x__xgafv=None)</code>
<pre>Gets a DataStore.
Args:
name: string, Required. Full resource name of DataStore, such as `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`. If the caller does not have permission to access the DataStore, regardless of whether or not it exists, a PERMISSION_DENIED error is returned. If the requested DataStore does not exist, a NOT_FOUND error is returned. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # DataStore captures global settings and configs at the DataStore level.
"aclEnabled": True or False, # Immutable. Whether data in the DataStore has ACL information. If set to `true`, the source data must have ACL. ACL will be ingested when data is ingested by DocumentService.ImportDocuments methods. When ACL is enabled for the DataStore, Document can't be accessed by calling DocumentService.GetDocument or DocumentService.ListDocuments. Currently ACL is only supported in `GENERIC` industry vertical with non-`PUBLIC_WEBSITE` content config.
"advancedSiteSearchConfig": { # Configuration data for advance site search. # Optional. Configuration for advanced site search.
"disableAutomaticRefresh": True or False, # If set true, automatic refresh is disabled for the DataStore.
"disableInitialIndex": True or False, # If set true, initial indexing is disabled for the DataStore.
},
"billingEstimation": { # Estimation of data size per data store. # Output only. Data size estimation for billing.
"structuredDataSize": "A String", # Data size for structured data in terms of bytes.
"structuredDataUpdateTime": "A String", # Last updated timestamp for structured data.
"unstructuredDataSize": "A String", # Data size for unstructured data in terms of bytes.
"unstructuredDataUpdateTime": "A String", # Last updated timestamp for unstructured data.
"websiteDataSize": "A String", # Data size for websites in terms of bytes.
"websiteDataUpdateTime": "A String", # Last updated timestamp for websites.
},
"cmekConfig": { # Configurations used to enable CMEK data encryption with Cloud KMS keys. # Output only. CMEK-related information for the DataStore.
"isDefault": True or False, # Output only. The default CmekConfig for the Customer.
"kmsKey": "A String", # Required. KMS key resource name which will be used to encrypt resources `projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}`.
"kmsKeyVersion": "A String", # Output only. KMS key version resource name which will be used to encrypt resources `/cryptoKeyVersions/{keyVersion}`.
"lastRotationTimestampMicros": "A String", # Output only. The timestamp of the last key rotation.
"name": "A String", # Required. The name of the CmekConfig of the form `projects/{project}/locations/{location}/cmekConfig` or `projects/{project}/locations/{location}/cmekConfigs/{cmek_config}`.
"notebooklmState": "A String", # Output only. Whether the NotebookLM Corpus is ready to be used.
"singleRegionKeys": [ # Optional. Single-regional CMEKs that are required for some VAIS features.
{ # Metadata for single-regional CMEKs.
"kmsKey": "A String", # Required. Single-regional kms key resource name which will be used to encrypt resources `projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}`.
},
],
"state": "A String", # Output only. The states of the CmekConfig.
},
"contentConfig": "A String", # Immutable. The content config of the data store. If this field is unset, the server behavior defaults to ContentConfig.NO_CONTENT.
"createTime": "A String", # Output only. Timestamp the DataStore was created at.
"defaultSchemaId": "A String", # Output only. The id of the default Schema associated to this data store.
"displayName": "A String", # Required. The data store display name. This field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.
"documentProcessingConfig": { # A singleton resource of DataStore. If it's empty when DataStore is created and DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED, the default parser will default to digital parser. # Configuration for Document understanding and enrichment.
"chunkingConfig": { # Configuration for chunking config. # Whether chunking mode is enabled.
"layoutBasedChunkingConfig": { # Configuration for the layout based chunking. # Configuration for the layout based chunking.
"chunkSize": 42, # The token size limit for each chunk. Supported values: 100-500 (inclusive). Default value: 500.
"includeAncestorHeadings": True or False, # Whether to include appending different levels of headings to chunks from the middle of the document to prevent context loss. Default value: False.
},
},
"defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
"name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
"parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and layout parsing are supported. * `docx`: Override parsing config for DOCX files, only digital parsing and layout parsing are supported. * `pptx`: Override parsing config for PPTX files, only digital parsing and layout parsing are supported. * `xlsm`: Override parsing config for XLSM files, only digital parsing and layout parsing are supported. * `xlsx`: Override parsing config for XLSX files, only digital parsing and layout parsing are supported.
"a_key": { # Related configurations applied to a specific type of document parser.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
},
},
"healthcareFhirConfig": { # Config to data store for `HEALTHCARE_FHIR` vertical. # Optional. Configuration for `HEALTHCARE_FHIR` vertical.
"enableConfigurableSchema": True or False, # Whether to enable configurable schema for `HEALTHCARE_FHIR` vertical. If set to `true`, the predefined healthcare fhir schema can be extended for more customized searching and filtering.
"enableStaticIndexingForBatchIngestion": True or False, # Whether to enable static indexing for `HEALTHCARE_FHIR` batch ingestion. If set to `true`, the batch ingestion will be processed in a static indexing mode which is slower but more capable of handling larger volume.
},
"identityMappingStore": "A String", # Immutable. The fully qualified resource name of the associated IdentityMappingStore. This field can only be set for acl_enabled DataStores with `THIRD_PARTY` or `GSUITE` IdP. Format: `projects/{project}/locations/{location}/identityMappingStores/{identity_mapping_store}`.
"idpConfig": { # Identity Provider Config. # Output only. Data store level identity provider config.
"externalIdpConfig": { # Third party IDP Config. # External Identity provider config.
"workforcePoolName": "A String", # Workforce pool name. Example: "locations/global/workforcePools/pool_id"
},
"idpType": "A String", # Identity provider type configured.
},
"industryVertical": "A String", # Immutable. The industry vertical that the data store registers.
"isInfobotFaqDataStore": True or False, # Optional. If set, this DataStore is an Infobot FAQ DataStore.
"kmsKeyName": "A String", # Input only. The KMS key to be used to protect this DataStore at creation time. Must be set for requests that need to comply with CMEK Org Policy protections. If this field is set and processed successfully, the DataStore will be protected by the KMS key, as indicated in the cmek_config field.
"languageInfo": { # Language info for DataStore. # Language info for DataStore.
"language": "A String", # Output only. Language part of normalized_language_code. E.g.: `en-US` -> `en`, `zh-Hans-HK` -> `zh`, `en` -> `en`.
"languageCode": "A String", # The language code for the DataStore.
"normalizedLanguageCode": "A String", # Output only. This is the normalized form of language_code. E.g.: language_code of `en-GB`, `en_GB`, `en-UK` or `en-gb` will have normalized_language_code of `en-GB`.
"region": "A String", # Output only. Region part of normalized_language_code, if present. E.g.: `en-US` -> `US`, `zh-Hans-HK` -> `HK`, `en` -> ``.
},
"name": "A String", # Immutable. Identifier. The full resource name of the data store. Format: `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"naturalLanguageQueryUnderstandingConfig": { # Configuration for Natural Language Query Understanding. # Optional. Configuration for Natural Language Query Understanding.
"mode": "A String", # Mode of Natural Language Query Understanding. If this field is unset, the behavior defaults to NaturalLanguageQueryUnderstandingConfig.Mode.DISABLED.
},
"servingConfigDataStore": { # Stores information regarding the serving configurations at DataStore level. # Optional. Stores serving config at DataStore level.
"disabledForServing": True or False, # Optional. If set true, the DataStore will not be available for serving search requests.
},
"solutionTypes": [ # The solutions that the data store enrolls. Available solutions for each industry_vertical: * `MEDIA`: `SOLUTION_TYPE_RECOMMENDATION` and `SOLUTION_TYPE_SEARCH`. * `SITE_SEARCH`: `SOLUTION_TYPE_SEARCH` is automatically enrolled. Other solutions cannot be enrolled.
"A String",
],
"startingSchema": { # Defines the structure and layout of a type of document data. # The start schema to use for this DataStore when provisioning it. If unset, a default vertical specialized schema will be used. This field is only used by CreateDataStore API, and will be ignored if used in other APIs. This field will be omitted from all API responses including CreateDataStore API. To retrieve a schema of a DataStore, use SchemaService.GetSchema API instead. The provided schema will be validated against certain rules on schema. Learn more from [this doc](https://cloud.google.com/generative-ai-app-builder/docs/provide-schema).
"fieldConfigs": [ # Output only. Configurations for fields of the schema.
{ # Configurations for fields of a schema. For example, configuring a field is indexable, or searchable.
"advancedSiteSearchDataSources": [ # If this field is set, only the corresponding source will be indexed for this field. Otherwise, the values from different sources are merged. Assuming a page with `` in meta tag, and `` in page map: if this enum is set to METATAGS, we will only index ``; if this enum is not set, we will merge them and index ``.
"A String",
],
"completableOption": "A String", # If completable_option is COMPLETABLE_ENABLED, field values are directly used and returned as suggestions for Autocomplete in CompletionService.CompleteQuery. If completable_option is unset, the server behavior defaults to COMPLETABLE_DISABLED for fields that support setting completable options, which are just `string` fields. For those fields that do not support setting completable options, the server will skip completable option setting, and setting completable_option for those fields will throw `INVALID_ARGUMENT` error.
"dynamicFacetableOption": "A String", # If dynamic_facetable_option is DYNAMIC_FACETABLE_ENABLED, field values are available for dynamic facet. Could only be DYNAMIC_FACETABLE_DISABLED if FieldConfig.indexable_option is INDEXABLE_DISABLED. Otherwise, an `INVALID_ARGUMENT` error will be returned. If dynamic_facetable_option is unset, the server behavior defaults to DYNAMIC_FACETABLE_DISABLED for fields that support setting dynamic facetable options. For those fields that do not support setting dynamic facetable options, such as `object` and `boolean`, the server will skip dynamic facetable option setting, and setting dynamic_facetable_option for those fields will throw `INVALID_ARGUMENT` error.
"fieldPath": "A String", # Required. Field path of the schema field. For example: `title`, `description`, `release_info.release_year`.
"fieldType": "A String", # Output only. Raw type of the field.
"indexableOption": "A String", # If indexable_option is INDEXABLE_ENABLED, field values are indexed so that it can be filtered or faceted in SearchService.Search. If indexable_option is unset, the server behavior defaults to INDEXABLE_DISABLED for fields that support setting indexable options. For those fields that do not support setting indexable options, such as `object` and `boolean` and key properties, the server will skip indexable_option setting, and setting indexable_option for those fields will throw `INVALID_ARGUMENT` error.
"keyPropertyType": "A String", # Output only. Type of the key property that this field is mapped to. Empty string if this is not annotated as mapped to a key property. Example types are `title`, `description`. Full list is defined by `keyPropertyMapping` in the schema field annotation. If the schema field has a `KeyPropertyMapping` annotation, `indexable_option` and `searchable_option` of this field cannot be modified.
"metatagName": "A String", # Optional. The metatag name found in the HTML page. If user defines this field, the value of this metatag name will be used to extract metatag. If the user does not define this field, the FieldConfig.field_path will be used to extract metatag.
"recsFilterableOption": "A String", # If recs_filterable_option is FILTERABLE_ENABLED, field values are filterable by filter expression in RecommendationService.Recommend. If FILTERABLE_ENABLED but the field type is numerical, field values are not filterable by text queries in RecommendationService.Recommend. Only textual fields are supported. If recs_filterable_option is unset, the default setting is FILTERABLE_DISABLED for fields that support setting filterable options. When a field set to [FILTERABLE_DISABLED] is filtered, a warning is generated and an empty result is returned.
"retrievableOption": "A String", # If retrievable_option is RETRIEVABLE_ENABLED, field values are included in the search results. If retrievable_option is unset, the server behavior defaults to RETRIEVABLE_DISABLED for fields that support setting retrievable options. For those fields that do not support setting retrievable options, such as `object` and `boolean`, the server will skip retrievable option setting, and setting retrievable_option for those fields will throw `INVALID_ARGUMENT` error.
"schemaOrgPaths": [ # Field paths for indexing custom attribute from schema.org data. More details of schema.org and its defined types can be found at [schema.org](https://schema.org). It is only used on advanced site search schema. Currently only support full path from root. The full path to a field is constructed by concatenating field names, starting from `_root`, with a period `.` as the delimiter. Examples: * Publish date of the root: _root.datePublished * Publish date of the reviews: _root.review.datePublished
"A String",
],
"searchableOption": "A String", # If searchable_option is SEARCHABLE_ENABLED, field values are searchable by text queries in SearchService.Search. If SEARCHABLE_ENABLED but field type is numerical, field values will not be searchable by text queries in SearchService.Search, as there are no text values associated to numerical fields. If searchable_option is unset, the server behavior defaults to SEARCHABLE_DISABLED for fields that support setting searchable options. Only `string` fields that have no key property mapping support setting searchable_option. For those fields that do not support setting searchable options, the server will skip searchable option setting, and setting searchable_option for those fields will throw `INVALID_ARGUMENT` error.
},
],
"jsonSchema": "A String", # The JSON representation of the schema.
"name": "A String", # Immutable. The full resource name of the schema, in the format of `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/schemas/{schema}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"structSchema": { # The structured representation of the schema.
"a_key": "", # Properties of the object.
},
},
"workspaceConfig": { # Config to store data store type configuration for workspace data # Config to store data store type configuration for workspace data. This must be set when DataStore.content_config is set as DataStore.ContentConfig.GOOGLE_WORKSPACE.
"dasherCustomerId": "A String", # Obfuscated Dasher customer ID.
"superAdminEmailAddress": "A String", # Optional. The super admin email address for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
"superAdminServiceAccount": "A String", # Optional. The super admin service account for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
"type": "A String", # The Google Workspace data source.
},
}</pre>
</div>
<div class="method">
<code class="details" id="getDocumentProcessingConfig">getDocumentProcessingConfig(name, x__xgafv=None)</code>
<pre>Gets a DocumentProcessingConfig.
Args:
name: string, Required. Full DocumentProcessingConfig resource name. Format: `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}/documentProcessingConfig` (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # A singleton resource of DataStore. If it's empty when DataStore is created and DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED, the default parser will default to digital parser.
"chunkingConfig": { # Configuration for chunking config. # Whether chunking mode is enabled.
"layoutBasedChunkingConfig": { # Configuration for the layout based chunking. # Configuration for the layout based chunking.
"chunkSize": 42, # The token size limit for each chunk. Supported values: 100-500 (inclusive). Default value: 500.
"includeAncestorHeadings": True or False, # Whether to include appending different levels of headings to chunks from the middle of the document to prevent context loss. Default value: False.
},
},
"defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
"name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
"parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and layout parsing are supported. * `docx`: Override parsing config for DOCX files, only digital parsing and layout parsing are supported. * `pptx`: Override parsing config for PPTX files, only digital parsing and layout parsing are supported. * `xlsm`: Override parsing config for XLSM files, only digital parsing and layout parsing are supported. * `xlsx`: Override parsing config for XLSX files, only digital parsing and layout parsing are supported.
"a_key": { # Related configurations applied to a specific type of document parser.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
},
}</pre>
</div>
<div class="method">
<code class="details" id="getSiteSearchEngine">getSiteSearchEngine(name, x__xgafv=None)</code>
<pre>Gets the SiteSearchEngine.
Args:
name: string, Required. Resource name of SiteSearchEngine, such as `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/siteSearchEngine`. If the caller does not have permission to access the [SiteSearchEngine], regardless of whether or not it exists, a PERMISSION_DENIED error is returned. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # SiteSearchEngine captures DataStore level site search persisting configurations. It is a singleton value per data store.
"name": "A String", # The fully qualified resource name of the site search engine. Format: `projects/*/locations/*/dataStores/*/siteSearchEngine`
}</pre>
</div>
<div class="method">
<code class="details" id="list">list(parent, filter=None, pageSize=None, pageToken=None, x__xgafv=None)</code>
<pre>Lists all the DataStores associated with the project.
Args:
parent: string, Required. The parent branch resource name, such as `projects/{project}/locations/{location}/collections/{collection_id}`. If the caller does not have permission to list DataStores under this location, regardless of whether or not this data store exists, a PERMISSION_DENIED error is returned. (required)
filter: string, Filter by solution type . For example: `filter = 'solution_type:SOLUTION_TYPE_SEARCH'`
pageSize: integer, Maximum number of DataStores to return. If unspecified, defaults to 10. The maximum allowed value is 50. Values above 50 will be coerced to 50. If this field is negative, an INVALID_ARGUMENT is returned.
pageToken: string, A page token ListDataStoresResponse.next_page_token, received from a previous DataStoreService.ListDataStores call. Provide this to retrieve the subsequent page. When paginating, all other parameters provided to DataStoreService.ListDataStores must match the call that provided the page token. Otherwise, an INVALID_ARGUMENT error is returned.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response message for DataStoreService.ListDataStores method.
"dataStores": [ # All the customer's DataStores.
{ # DataStore captures global settings and configs at the DataStore level.
"aclEnabled": True or False, # Immutable. Whether data in the DataStore has ACL information. If set to `true`, the source data must have ACL. ACL will be ingested when data is ingested by DocumentService.ImportDocuments methods. When ACL is enabled for the DataStore, Document can't be accessed by calling DocumentService.GetDocument or DocumentService.ListDocuments. Currently ACL is only supported in `GENERIC` industry vertical with non-`PUBLIC_WEBSITE` content config.
"advancedSiteSearchConfig": { # Configuration data for advance site search. # Optional. Configuration for advanced site search.
"disableAutomaticRefresh": True or False, # If set true, automatic refresh is disabled for the DataStore.
"disableInitialIndex": True or False, # If set true, initial indexing is disabled for the DataStore.
},
"billingEstimation": { # Estimation of data size per data store. # Output only. Data size estimation for billing.
"structuredDataSize": "A String", # Data size for structured data in terms of bytes.
"structuredDataUpdateTime": "A String", # Last updated timestamp for structured data.
"unstructuredDataSize": "A String", # Data size for unstructured data in terms of bytes.
"unstructuredDataUpdateTime": "A String", # Last updated timestamp for unstructured data.
"websiteDataSize": "A String", # Data size for websites in terms of bytes.
"websiteDataUpdateTime": "A String", # Last updated timestamp for websites.
},
"cmekConfig": { # Configurations used to enable CMEK data encryption with Cloud KMS keys. # Output only. CMEK-related information for the DataStore.
"isDefault": True or False, # Output only. The default CmekConfig for the Customer.
"kmsKey": "A String", # Required. KMS key resource name which will be used to encrypt resources `projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}`.
"kmsKeyVersion": "A String", # Output only. KMS key version resource name which will be used to encrypt resources `/cryptoKeyVersions/{keyVersion}`.
"lastRotationTimestampMicros": "A String", # Output only. The timestamp of the last key rotation.
"name": "A String", # Required. The name of the CmekConfig of the form `projects/{project}/locations/{location}/cmekConfig` or `projects/{project}/locations/{location}/cmekConfigs/{cmek_config}`.
"notebooklmState": "A String", # Output only. Whether the NotebookLM Corpus is ready to be used.
"singleRegionKeys": [ # Optional. Single-regional CMEKs that are required for some VAIS features.
{ # Metadata for single-regional CMEKs.
"kmsKey": "A String", # Required. Single-regional kms key resource name which will be used to encrypt resources `projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}`.
},
],
"state": "A String", # Output only. The states of the CmekConfig.
},
"contentConfig": "A String", # Immutable. The content config of the data store. If this field is unset, the server behavior defaults to ContentConfig.NO_CONTENT.
"createTime": "A String", # Output only. Timestamp the DataStore was created at.
"defaultSchemaId": "A String", # Output only. The id of the default Schema associated to this data store.
"displayName": "A String", # Required. The data store display name. This field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.
"documentProcessingConfig": { # A singleton resource of DataStore. If it's empty when DataStore is created and DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED, the default parser will default to digital parser. # Configuration for Document understanding and enrichment.
"chunkingConfig": { # Configuration for chunking config. # Whether chunking mode is enabled.
"layoutBasedChunkingConfig": { # Configuration for the layout based chunking. # Configuration for the layout based chunking.
"chunkSize": 42, # The token size limit for each chunk. Supported values: 100-500 (inclusive). Default value: 500.
"includeAncestorHeadings": True or False, # Whether to include appending different levels of headings to chunks from the middle of the document to prevent context loss. Default value: False.
},
},
"defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
"name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
"parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and layout parsing are supported. * `docx`: Override parsing config for DOCX files, only digital parsing and layout parsing are supported. * `pptx`: Override parsing config for PPTX files, only digital parsing and layout parsing are supported. * `xlsm`: Override parsing config for XLSM files, only digital parsing and layout parsing are supported. * `xlsx`: Override parsing config for XLSX files, only digital parsing and layout parsing are supported.
"a_key": { # Related configurations applied to a specific type of document parser.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
},
},
"healthcareFhirConfig": { # Config to data store for `HEALTHCARE_FHIR` vertical. # Optional. Configuration for `HEALTHCARE_FHIR` vertical.
"enableConfigurableSchema": True or False, # Whether to enable configurable schema for `HEALTHCARE_FHIR` vertical. If set to `true`, the predefined healthcare fhir schema can be extended for more customized searching and filtering.
"enableStaticIndexingForBatchIngestion": True or False, # Whether to enable static indexing for `HEALTHCARE_FHIR` batch ingestion. If set to `true`, the batch ingestion will be processed in a static indexing mode which is slower but more capable of handling larger volume.
},
"identityMappingStore": "A String", # Immutable. The fully qualified resource name of the associated IdentityMappingStore. This field can only be set for acl_enabled DataStores with `THIRD_PARTY` or `GSUITE` IdP. Format: `projects/{project}/locations/{location}/identityMappingStores/{identity_mapping_store}`.
"idpConfig": { # Identity Provider Config. # Output only. Data store level identity provider config.
"externalIdpConfig": { # Third party IDP Config. # External Identity provider config.
"workforcePoolName": "A String", # Workforce pool name. Example: "locations/global/workforcePools/pool_id"
},
"idpType": "A String", # Identity provider type configured.
},
"industryVertical": "A String", # Immutable. The industry vertical that the data store registers.
"isInfobotFaqDataStore": True or False, # Optional. If set, this DataStore is an Infobot FAQ DataStore.
"kmsKeyName": "A String", # Input only. The KMS key to be used to protect this DataStore at creation time. Must be set for requests that need to comply with CMEK Org Policy protections. If this field is set and processed successfully, the DataStore will be protected by the KMS key, as indicated in the cmek_config field.
"languageInfo": { # Language info for DataStore. # Language info for DataStore.
"language": "A String", # Output only. Language part of normalized_language_code. E.g.: `en-US` -> `en`, `zh-Hans-HK` -> `zh`, `en` -> `en`.
"languageCode": "A String", # The language code for the DataStore.
"normalizedLanguageCode": "A String", # Output only. This is the normalized form of language_code. E.g.: language_code of `en-GB`, `en_GB`, `en-UK` or `en-gb` will have normalized_language_code of `en-GB`.
"region": "A String", # Output only. Region part of normalized_language_code, if present. E.g.: `en-US` -> `US`, `zh-Hans-HK` -> `HK`, `en` -> ``.
},
"name": "A String", # Immutable. Identifier. The full resource name of the data store. Format: `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"naturalLanguageQueryUnderstandingConfig": { # Configuration for Natural Language Query Understanding. # Optional. Configuration for Natural Language Query Understanding.
"mode": "A String", # Mode of Natural Language Query Understanding. If this field is unset, the behavior defaults to NaturalLanguageQueryUnderstandingConfig.Mode.DISABLED.
},
"servingConfigDataStore": { # Stores information regarding the serving configurations at DataStore level. # Optional. Stores serving config at DataStore level.
"disabledForServing": True or False, # Optional. If set true, the DataStore will not be available for serving search requests.
},
"solutionTypes": [ # The solutions that the data store enrolls. Available solutions for each industry_vertical: * `MEDIA`: `SOLUTION_TYPE_RECOMMENDATION` and `SOLUTION_TYPE_SEARCH`. * `SITE_SEARCH`: `SOLUTION_TYPE_SEARCH` is automatically enrolled. Other solutions cannot be enrolled.
"A String",
],
"startingSchema": { # Defines the structure and layout of a type of document data. # The start schema to use for this DataStore when provisioning it. If unset, a default vertical specialized schema will be used. This field is only used by CreateDataStore API, and will be ignored if used in other APIs. This field will be omitted from all API responses including CreateDataStore API. To retrieve a schema of a DataStore, use SchemaService.GetSchema API instead. The provided schema will be validated against certain rules on schema. Learn more from [this doc](https://cloud.google.com/generative-ai-app-builder/docs/provide-schema).
"fieldConfigs": [ # Output only. Configurations for fields of the schema.
{ # Configurations for fields of a schema. For example, configuring a field is indexable, or searchable.
"advancedSiteSearchDataSources": [ # If this field is set, only the corresponding source will be indexed for this field. Otherwise, the values from different sources are merged. Assuming a page with `` in meta tag, and `` in page map: if this enum is set to METATAGS, we will only index ``; if this enum is not set, we will merge them and index ``.
"A String",
],
"completableOption": "A String", # If completable_option is COMPLETABLE_ENABLED, field values are directly used and returned as suggestions for Autocomplete in CompletionService.CompleteQuery. If completable_option is unset, the server behavior defaults to COMPLETABLE_DISABLED for fields that support setting completable options, which are just `string` fields. For those fields that do not support setting completable options, the server will skip completable option setting, and setting completable_option for those fields will throw `INVALID_ARGUMENT` error.
"dynamicFacetableOption": "A String", # If dynamic_facetable_option is DYNAMIC_FACETABLE_ENABLED, field values are available for dynamic facet. Could only be DYNAMIC_FACETABLE_DISABLED if FieldConfig.indexable_option is INDEXABLE_DISABLED. Otherwise, an `INVALID_ARGUMENT` error will be returned. If dynamic_facetable_option is unset, the server behavior defaults to DYNAMIC_FACETABLE_DISABLED for fields that support setting dynamic facetable options. For those fields that do not support setting dynamic facetable options, such as `object` and `boolean`, the server will skip dynamic facetable option setting, and setting dynamic_facetable_option for those fields will throw `INVALID_ARGUMENT` error.
"fieldPath": "A String", # Required. Field path of the schema field. For example: `title`, `description`, `release_info.release_year`.
"fieldType": "A String", # Output only. Raw type of the field.
"indexableOption": "A String", # If indexable_option is INDEXABLE_ENABLED, field values are indexed so that it can be filtered or faceted in SearchService.Search. If indexable_option is unset, the server behavior defaults to INDEXABLE_DISABLED for fields that support setting indexable options. For those fields that do not support setting indexable options, such as `object` and `boolean` and key properties, the server will skip indexable_option setting, and setting indexable_option for those fields will throw `INVALID_ARGUMENT` error.
"keyPropertyType": "A String", # Output only. Type of the key property that this field is mapped to. Empty string if this is not annotated as mapped to a key property. Example types are `title`, `description`. Full list is defined by `keyPropertyMapping` in the schema field annotation. If the schema field has a `KeyPropertyMapping` annotation, `indexable_option` and `searchable_option` of this field cannot be modified.
"metatagName": "A String", # Optional. The metatag name found in the HTML page. If user defines this field, the value of this metatag name will be used to extract metatag. If the user does not define this field, the FieldConfig.field_path will be used to extract metatag.
"recsFilterableOption": "A String", # If recs_filterable_option is FILTERABLE_ENABLED, field values are filterable by filter expression in RecommendationService.Recommend. If FILTERABLE_ENABLED but the field type is numerical, field values are not filterable by text queries in RecommendationService.Recommend. Only textual fields are supported. If recs_filterable_option is unset, the default setting is FILTERABLE_DISABLED for fields that support setting filterable options. When a field set to [FILTERABLE_DISABLED] is filtered, a warning is generated and an empty result is returned.
"retrievableOption": "A String", # If retrievable_option is RETRIEVABLE_ENABLED, field values are included in the search results. If retrievable_option is unset, the server behavior defaults to RETRIEVABLE_DISABLED for fields that support setting retrievable options. For those fields that do not support setting retrievable options, such as `object` and `boolean`, the server will skip retrievable option setting, and setting retrievable_option for those fields will throw `INVALID_ARGUMENT` error.
"schemaOrgPaths": [ # Field paths for indexing custom attribute from schema.org data. More details of schema.org and its defined types can be found at [schema.org](https://schema.org). It is only used on advanced site search schema. Currently only support full path from root. The full path to a field is constructed by concatenating field names, starting from `_root`, with a period `.` as the delimiter. Examples: * Publish date of the root: _root.datePublished * Publish date of the reviews: _root.review.datePublished
"A String",
],
"searchableOption": "A String", # If searchable_option is SEARCHABLE_ENABLED, field values are searchable by text queries in SearchService.Search. If SEARCHABLE_ENABLED but field type is numerical, field values will not be searchable by text queries in SearchService.Search, as there are no text values associated to numerical fields. If searchable_option is unset, the server behavior defaults to SEARCHABLE_DISABLED for fields that support setting searchable options. Only `string` fields that have no key property mapping support setting searchable_option. For those fields that do not support setting searchable options, the server will skip searchable option setting, and setting searchable_option for those fields will throw `INVALID_ARGUMENT` error.
},
],
"jsonSchema": "A String", # The JSON representation of the schema.
"name": "A String", # Immutable. The full resource name of the schema, in the format of `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/schemas/{schema}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"structSchema": { # The structured representation of the schema.
"a_key": "", # Properties of the object.
},
},
"workspaceConfig": { # Config to store data store type configuration for workspace data # Config to store data store type configuration for workspace data. This must be set when DataStore.content_config is set as DataStore.ContentConfig.GOOGLE_WORKSPACE.
"dasherCustomerId": "A String", # Obfuscated Dasher customer ID.
"superAdminEmailAddress": "A String", # Optional. The super admin email address for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
"superAdminServiceAccount": "A String", # Optional. The super admin service account for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
"type": "A String", # The Google Workspace data source.
},
},
],
"nextPageToken": "A String", # A token that can be sent as ListDataStoresRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.
}</pre>
</div>
<div class="method">
<code class="details" id="list_next">list_next()</code>
<pre>Retrieves the next page of results.
Args:
previous_request: The request for the previous page. (required)
previous_response: The response from the request for the previous page. (required)
Returns:
A request object that you can call 'execute()' on to request the next
page. Returns None if there are no more items in the collection.
</pre>
</div>
<div class="method">
<code class="details" id="patch">patch(name, body=None, updateMask=None, x__xgafv=None)</code>
<pre>Updates a DataStore
Args:
name: string, Immutable. Identifier. The full resource name of the data store. Format: `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters. (required)
body: object, The request body.
The object takes the form of:
{ # DataStore captures global settings and configs at the DataStore level.
"aclEnabled": True or False, # Immutable. Whether data in the DataStore has ACL information. If set to `true`, the source data must have ACL. ACL will be ingested when data is ingested by DocumentService.ImportDocuments methods. When ACL is enabled for the DataStore, Document can't be accessed by calling DocumentService.GetDocument or DocumentService.ListDocuments. Currently ACL is only supported in `GENERIC` industry vertical with non-`PUBLIC_WEBSITE` content config.
"advancedSiteSearchConfig": { # Configuration data for advance site search. # Optional. Configuration for advanced site search.
"disableAutomaticRefresh": True or False, # If set true, automatic refresh is disabled for the DataStore.
"disableInitialIndex": True or False, # If set true, initial indexing is disabled for the DataStore.
},
"billingEstimation": { # Estimation of data size per data store. # Output only. Data size estimation for billing.
"structuredDataSize": "A String", # Data size for structured data in terms of bytes.
"structuredDataUpdateTime": "A String", # Last updated timestamp for structured data.
"unstructuredDataSize": "A String", # Data size for unstructured data in terms of bytes.
"unstructuredDataUpdateTime": "A String", # Last updated timestamp for unstructured data.
"websiteDataSize": "A String", # Data size for websites in terms of bytes.
"websiteDataUpdateTime": "A String", # Last updated timestamp for websites.
},
"cmekConfig": { # Configurations used to enable CMEK data encryption with Cloud KMS keys. # Output only. CMEK-related information for the DataStore.
"isDefault": True or False, # Output only. The default CmekConfig for the Customer.
"kmsKey": "A String", # Required. KMS key resource name which will be used to encrypt resources `projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}`.
"kmsKeyVersion": "A String", # Output only. KMS key version resource name which will be used to encrypt resources `/cryptoKeyVersions/{keyVersion}`.
"lastRotationTimestampMicros": "A String", # Output only. The timestamp of the last key rotation.
"name": "A String", # Required. The name of the CmekConfig of the form `projects/{project}/locations/{location}/cmekConfig` or `projects/{project}/locations/{location}/cmekConfigs/{cmek_config}`.
"notebooklmState": "A String", # Output only. Whether the NotebookLM Corpus is ready to be used.
"singleRegionKeys": [ # Optional. Single-regional CMEKs that are required for some VAIS features.
{ # Metadata for single-regional CMEKs.
"kmsKey": "A String", # Required. Single-regional kms key resource name which will be used to encrypt resources `projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}`.
},
],
"state": "A String", # Output only. The states of the CmekConfig.
},
"contentConfig": "A String", # Immutable. The content config of the data store. If this field is unset, the server behavior defaults to ContentConfig.NO_CONTENT.
"createTime": "A String", # Output only. Timestamp the DataStore was created at.
"defaultSchemaId": "A String", # Output only. The id of the default Schema associated to this data store.
"displayName": "A String", # Required. The data store display name. This field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.
"documentProcessingConfig": { # A singleton resource of DataStore. If it's empty when DataStore is created and DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED, the default parser will default to digital parser. # Configuration for Document understanding and enrichment.
"chunkingConfig": { # Configuration for chunking config. # Whether chunking mode is enabled.
"layoutBasedChunkingConfig": { # Configuration for the layout based chunking. # Configuration for the layout based chunking.
"chunkSize": 42, # The token size limit for each chunk. Supported values: 100-500 (inclusive). Default value: 500.
"includeAncestorHeadings": True or False, # Whether to include appending different levels of headings to chunks from the middle of the document to prevent context loss. Default value: False.
},
},
"defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
"name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
"parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and layout parsing are supported. * `docx`: Override parsing config for DOCX files, only digital parsing and layout parsing are supported. * `pptx`: Override parsing config for PPTX files, only digital parsing and layout parsing are supported. * `xlsm`: Override parsing config for XLSM files, only digital parsing and layout parsing are supported. * `xlsx`: Override parsing config for XLSX files, only digital parsing and layout parsing are supported.
"a_key": { # Related configurations applied to a specific type of document parser.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
},
},
"healthcareFhirConfig": { # Config to data store for `HEALTHCARE_FHIR` vertical. # Optional. Configuration for `HEALTHCARE_FHIR` vertical.
"enableConfigurableSchema": True or False, # Whether to enable configurable schema for `HEALTHCARE_FHIR` vertical. If set to `true`, the predefined healthcare fhir schema can be extended for more customized searching and filtering.
"enableStaticIndexingForBatchIngestion": True or False, # Whether to enable static indexing for `HEALTHCARE_FHIR` batch ingestion. If set to `true`, the batch ingestion will be processed in a static indexing mode which is slower but more capable of handling larger volume.
},
"identityMappingStore": "A String", # Immutable. The fully qualified resource name of the associated IdentityMappingStore. This field can only be set for acl_enabled DataStores with `THIRD_PARTY` or `GSUITE` IdP. Format: `projects/{project}/locations/{location}/identityMappingStores/{identity_mapping_store}`.
"idpConfig": { # Identity Provider Config. # Output only. Data store level identity provider config.
"externalIdpConfig": { # Third party IDP Config. # External Identity provider config.
"workforcePoolName": "A String", # Workforce pool name. Example: "locations/global/workforcePools/pool_id"
},
"idpType": "A String", # Identity provider type configured.
},
"industryVertical": "A String", # Immutable. The industry vertical that the data store registers.
"isInfobotFaqDataStore": True or False, # Optional. If set, this DataStore is an Infobot FAQ DataStore.
"kmsKeyName": "A String", # Input only. The KMS key to be used to protect this DataStore at creation time. Must be set for requests that need to comply with CMEK Org Policy protections. If this field is set and processed successfully, the DataStore will be protected by the KMS key, as indicated in the cmek_config field.
"languageInfo": { # Language info for DataStore. # Language info for DataStore.
"language": "A String", # Output only. Language part of normalized_language_code. E.g.: `en-US` -> `en`, `zh-Hans-HK` -> `zh`, `en` -> `en`.
"languageCode": "A String", # The language code for the DataStore.
"normalizedLanguageCode": "A String", # Output only. This is the normalized form of language_code. E.g.: language_code of `en-GB`, `en_GB`, `en-UK` or `en-gb` will have normalized_language_code of `en-GB`.
"region": "A String", # Output only. Region part of normalized_language_code, if present. E.g.: `en-US` -> `US`, `zh-Hans-HK` -> `HK`, `en` -> ``.
},
"name": "A String", # Immutable. Identifier. The full resource name of the data store. Format: `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"naturalLanguageQueryUnderstandingConfig": { # Configuration for Natural Language Query Understanding. # Optional. Configuration for Natural Language Query Understanding.
"mode": "A String", # Mode of Natural Language Query Understanding. If this field is unset, the behavior defaults to NaturalLanguageQueryUnderstandingConfig.Mode.DISABLED.
},
"servingConfigDataStore": { # Stores information regarding the serving configurations at DataStore level. # Optional. Stores serving config at DataStore level.
"disabledForServing": True or False, # Optional. If set true, the DataStore will not be available for serving search requests.
},
"solutionTypes": [ # The solutions that the data store enrolls. Available solutions for each industry_vertical: * `MEDIA`: `SOLUTION_TYPE_RECOMMENDATION` and `SOLUTION_TYPE_SEARCH`. * `SITE_SEARCH`: `SOLUTION_TYPE_SEARCH` is automatically enrolled. Other solutions cannot be enrolled.
"A String",
],
"startingSchema": { # Defines the structure and layout of a type of document data. # The start schema to use for this DataStore when provisioning it. If unset, a default vertical specialized schema will be used. This field is only used by CreateDataStore API, and will be ignored if used in other APIs. This field will be omitted from all API responses including CreateDataStore API. To retrieve a schema of a DataStore, use SchemaService.GetSchema API instead. The provided schema will be validated against certain rules on schema. Learn more from [this doc](https://cloud.google.com/generative-ai-app-builder/docs/provide-schema).
"fieldConfigs": [ # Output only. Configurations for fields of the schema.
{ # Configurations for fields of a schema. For example, configuring a field is indexable, or searchable.
"advancedSiteSearchDataSources": [ # If this field is set, only the corresponding source will be indexed for this field. Otherwise, the values from different sources are merged. Assuming a page with `` in meta tag, and `` in page map: if this enum is set to METATAGS, we will only index ``; if this enum is not set, we will merge them and index ``.
"A String",
],
"completableOption": "A String", # If completable_option is COMPLETABLE_ENABLED, field values are directly used and returned as suggestions for Autocomplete in CompletionService.CompleteQuery. If completable_option is unset, the server behavior defaults to COMPLETABLE_DISABLED for fields that support setting completable options, which are just `string` fields. For those fields that do not support setting completable options, the server will skip completable option setting, and setting completable_option for those fields will throw `INVALID_ARGUMENT` error.
"dynamicFacetableOption": "A String", # If dynamic_facetable_option is DYNAMIC_FACETABLE_ENABLED, field values are available for dynamic facet. Could only be DYNAMIC_FACETABLE_DISABLED if FieldConfig.indexable_option is INDEXABLE_DISABLED. Otherwise, an `INVALID_ARGUMENT` error will be returned. If dynamic_facetable_option is unset, the server behavior defaults to DYNAMIC_FACETABLE_DISABLED for fields that support setting dynamic facetable options. For those fields that do not support setting dynamic facetable options, such as `object` and `boolean`, the server will skip dynamic facetable option setting, and setting dynamic_facetable_option for those fields will throw `INVALID_ARGUMENT` error.
"fieldPath": "A String", # Required. Field path of the schema field. For example: `title`, `description`, `release_info.release_year`.
"fieldType": "A String", # Output only. Raw type of the field.
"indexableOption": "A String", # If indexable_option is INDEXABLE_ENABLED, field values are indexed so that it can be filtered or faceted in SearchService.Search. If indexable_option is unset, the server behavior defaults to INDEXABLE_DISABLED for fields that support setting indexable options. For those fields that do not support setting indexable options, such as `object` and `boolean` and key properties, the server will skip indexable_option setting, and setting indexable_option for those fields will throw `INVALID_ARGUMENT` error.
"keyPropertyType": "A String", # Output only. Type of the key property that this field is mapped to. Empty string if this is not annotated as mapped to a key property. Example types are `title`, `description`. Full list is defined by `keyPropertyMapping` in the schema field annotation. If the schema field has a `KeyPropertyMapping` annotation, `indexable_option` and `searchable_option` of this field cannot be modified.
"metatagName": "A String", # Optional. The metatag name found in the HTML page. If user defines this field, the value of this metatag name will be used to extract metatag. If the user does not define this field, the FieldConfig.field_path will be used to extract metatag.
"recsFilterableOption": "A String", # If recs_filterable_option is FILTERABLE_ENABLED, field values are filterable by filter expression in RecommendationService.Recommend. If FILTERABLE_ENABLED but the field type is numerical, field values are not filterable by text queries in RecommendationService.Recommend. Only textual fields are supported. If recs_filterable_option is unset, the default setting is FILTERABLE_DISABLED for fields that support setting filterable options. When a field set to [FILTERABLE_DISABLED] is filtered, a warning is generated and an empty result is returned.
"retrievableOption": "A String", # If retrievable_option is RETRIEVABLE_ENABLED, field values are included in the search results. If retrievable_option is unset, the server behavior defaults to RETRIEVABLE_DISABLED for fields that support setting retrievable options. For those fields that do not support setting retrievable options, such as `object` and `boolean`, the server will skip retrievable option setting, and setting retrievable_option for those fields will throw `INVALID_ARGUMENT` error.
"schemaOrgPaths": [ # Field paths for indexing custom attribute from schema.org data. More details of schema.org and its defined types can be found at [schema.org](https://schema.org). It is only used on advanced site search schema. Currently only support full path from root. The full path to a field is constructed by concatenating field names, starting from `_root`, with a period `.` as the delimiter. Examples: * Publish date of the root: _root.datePublished * Publish date of the reviews: _root.review.datePublished
"A String",
],
"searchableOption": "A String", # If searchable_option is SEARCHABLE_ENABLED, field values are searchable by text queries in SearchService.Search. If SEARCHABLE_ENABLED but field type is numerical, field values will not be searchable by text queries in SearchService.Search, as there are no text values associated to numerical fields. If searchable_option is unset, the server behavior defaults to SEARCHABLE_DISABLED for fields that support setting searchable options. Only `string` fields that have no key property mapping support setting searchable_option. For those fields that do not support setting searchable options, the server will skip searchable option setting, and setting searchable_option for those fields will throw `INVALID_ARGUMENT` error.
},
],
"jsonSchema": "A String", # The JSON representation of the schema.
"name": "A String", # Immutable. The full resource name of the schema, in the format of `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/schemas/{schema}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"structSchema": { # The structured representation of the schema.
"a_key": "", # Properties of the object.
},
},
"workspaceConfig": { # Config to store data store type configuration for workspace data # Config to store data store type configuration for workspace data. This must be set when DataStore.content_config is set as DataStore.ContentConfig.GOOGLE_WORKSPACE.
"dasherCustomerId": "A String", # Obfuscated Dasher customer ID.
"superAdminEmailAddress": "A String", # Optional. The super admin email address for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
"superAdminServiceAccount": "A String", # Optional. The super admin service account for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
"type": "A String", # The Google Workspace data source.
},
}
updateMask: string, Indicates which fields in the provided DataStore to update. If an unsupported or unknown field is provided, an INVALID_ARGUMENT error is returned.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # DataStore captures global settings and configs at the DataStore level.
"aclEnabled": True or False, # Immutable. Whether data in the DataStore has ACL information. If set to `true`, the source data must have ACL. ACL will be ingested when data is ingested by DocumentService.ImportDocuments methods. When ACL is enabled for the DataStore, Document can't be accessed by calling DocumentService.GetDocument or DocumentService.ListDocuments. Currently ACL is only supported in `GENERIC` industry vertical with non-`PUBLIC_WEBSITE` content config.
"advancedSiteSearchConfig": { # Configuration data for advance site search. # Optional. Configuration for advanced site search.
"disableAutomaticRefresh": True or False, # If set true, automatic refresh is disabled for the DataStore.
"disableInitialIndex": True or False, # If set true, initial indexing is disabled for the DataStore.
},
"billingEstimation": { # Estimation of data size per data store. # Output only. Data size estimation for billing.
"structuredDataSize": "A String", # Data size for structured data in terms of bytes.
"structuredDataUpdateTime": "A String", # Last updated timestamp for structured data.
"unstructuredDataSize": "A String", # Data size for unstructured data in terms of bytes.
"unstructuredDataUpdateTime": "A String", # Last updated timestamp for unstructured data.
"websiteDataSize": "A String", # Data size for websites in terms of bytes.
"websiteDataUpdateTime": "A String", # Last updated timestamp for websites.
},
"cmekConfig": { # Configurations used to enable CMEK data encryption with Cloud KMS keys. # Output only. CMEK-related information for the DataStore.
"isDefault": True or False, # Output only. The default CmekConfig for the Customer.
"kmsKey": "A String", # Required. KMS key resource name which will be used to encrypt resources `projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}`.
"kmsKeyVersion": "A String", # Output only. KMS key version resource name which will be used to encrypt resources `/cryptoKeyVersions/{keyVersion}`.
"lastRotationTimestampMicros": "A String", # Output only. The timestamp of the last key rotation.
"name": "A String", # Required. The name of the CmekConfig of the form `projects/{project}/locations/{location}/cmekConfig` or `projects/{project}/locations/{location}/cmekConfigs/{cmek_config}`.
"notebooklmState": "A String", # Output only. Whether the NotebookLM Corpus is ready to be used.
"singleRegionKeys": [ # Optional. Single-regional CMEKs that are required for some VAIS features.
{ # Metadata for single-regional CMEKs.
"kmsKey": "A String", # Required. Single-regional kms key resource name which will be used to encrypt resources `projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}`.
},
],
"state": "A String", # Output only. The states of the CmekConfig.
},
"contentConfig": "A String", # Immutable. The content config of the data store. If this field is unset, the server behavior defaults to ContentConfig.NO_CONTENT.
"createTime": "A String", # Output only. Timestamp the DataStore was created at.
"defaultSchemaId": "A String", # Output only. The id of the default Schema associated to this data store.
"displayName": "A String", # Required. The data store display name. This field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.
"documentProcessingConfig": { # A singleton resource of DataStore. If it's empty when DataStore is created and DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED, the default parser will default to digital parser. # Configuration for Document understanding and enrichment.
"chunkingConfig": { # Configuration for chunking config. # Whether chunking mode is enabled.
"layoutBasedChunkingConfig": { # Configuration for the layout based chunking. # Configuration for the layout based chunking.
"chunkSize": 42, # The token size limit for each chunk. Supported values: 100-500 (inclusive). Default value: 500.
"includeAncestorHeadings": True or False, # Whether to include appending different levels of headings to chunks from the middle of the document to prevent context loss. Default value: False.
},
},
"defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
"name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
"parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and layout parsing are supported. * `docx`: Override parsing config for DOCX files, only digital parsing and layout parsing are supported. * `pptx`: Override parsing config for PPTX files, only digital parsing and layout parsing are supported. * `xlsm`: Override parsing config for XLSM files, only digital parsing and layout parsing are supported. * `xlsx`: Override parsing config for XLSX files, only digital parsing and layout parsing are supported.
"a_key": { # Related configurations applied to a specific type of document parser.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
},
},
"healthcareFhirConfig": { # Config to data store for `HEALTHCARE_FHIR` vertical. # Optional. Configuration for `HEALTHCARE_FHIR` vertical.
"enableConfigurableSchema": True or False, # Whether to enable configurable schema for `HEALTHCARE_FHIR` vertical. If set to `true`, the predefined healthcare fhir schema can be extended for more customized searching and filtering.
"enableStaticIndexingForBatchIngestion": True or False, # Whether to enable static indexing for `HEALTHCARE_FHIR` batch ingestion. If set to `true`, the batch ingestion will be processed in a static indexing mode which is slower but more capable of handling larger volume.
},
"identityMappingStore": "A String", # Immutable. The fully qualified resource name of the associated IdentityMappingStore. This field can only be set for acl_enabled DataStores with `THIRD_PARTY` or `GSUITE` IdP. Format: `projects/{project}/locations/{location}/identityMappingStores/{identity_mapping_store}`.
"idpConfig": { # Identity Provider Config. # Output only. Data store level identity provider config.
"externalIdpConfig": { # Third party IDP Config. # External Identity provider config.
"workforcePoolName": "A String", # Workforce pool name. Example: "locations/global/workforcePools/pool_id"
},
"idpType": "A String", # Identity provider type configured.
},
"industryVertical": "A String", # Immutable. The industry vertical that the data store registers.
"isInfobotFaqDataStore": True or False, # Optional. If set, this DataStore is an Infobot FAQ DataStore.
"kmsKeyName": "A String", # Input only. The KMS key to be used to protect this DataStore at creation time. Must be set for requests that need to comply with CMEK Org Policy protections. If this field is set and processed successfully, the DataStore will be protected by the KMS key, as indicated in the cmek_config field.
"languageInfo": { # Language info for DataStore. # Language info for DataStore.
"language": "A String", # Output only. Language part of normalized_language_code. E.g.: `en-US` -> `en`, `zh-Hans-HK` -> `zh`, `en` -> `en`.
"languageCode": "A String", # The language code for the DataStore.
"normalizedLanguageCode": "A String", # Output only. This is the normalized form of language_code. E.g.: language_code of `en-GB`, `en_GB`, `en-UK` or `en-gb` will have normalized_language_code of `en-GB`.
"region": "A String", # Output only. Region part of normalized_language_code, if present. E.g.: `en-US` -> `US`, `zh-Hans-HK` -> `HK`, `en` -> ``.
},
"name": "A String", # Immutable. Identifier. The full resource name of the data store. Format: `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"naturalLanguageQueryUnderstandingConfig": { # Configuration for Natural Language Query Understanding. # Optional. Configuration for Natural Language Query Understanding.
"mode": "A String", # Mode of Natural Language Query Understanding. If this field is unset, the behavior defaults to NaturalLanguageQueryUnderstandingConfig.Mode.DISABLED.
},
"servingConfigDataStore": { # Stores information regarding the serving configurations at DataStore level. # Optional. Stores serving config at DataStore level.
"disabledForServing": True or False, # Optional. If set true, the DataStore will not be available for serving search requests.
},
"solutionTypes": [ # The solutions that the data store enrolls. Available solutions for each industry_vertical: * `MEDIA`: `SOLUTION_TYPE_RECOMMENDATION` and `SOLUTION_TYPE_SEARCH`. * `SITE_SEARCH`: `SOLUTION_TYPE_SEARCH` is automatically enrolled. Other solutions cannot be enrolled.
"A String",
],
"startingSchema": { # Defines the structure and layout of a type of document data. # The start schema to use for this DataStore when provisioning it. If unset, a default vertical specialized schema will be used. This field is only used by CreateDataStore API, and will be ignored if used in other APIs. This field will be omitted from all API responses including CreateDataStore API. To retrieve a schema of a DataStore, use SchemaService.GetSchema API instead. The provided schema will be validated against certain rules on schema. Learn more from [this doc](https://cloud.google.com/generative-ai-app-builder/docs/provide-schema).
"fieldConfigs": [ # Output only. Configurations for fields of the schema.
{ # Configurations for fields of a schema. For example, configuring a field is indexable, or searchable.
"advancedSiteSearchDataSources": [ # If this field is set, only the corresponding source will be indexed for this field. Otherwise, the values from different sources are merged. Assuming a page with `` in meta tag, and `` in page map: if this enum is set to METATAGS, we will only index ``; if this enum is not set, we will merge them and index ``.
"A String",
],
"completableOption": "A String", # If completable_option is COMPLETABLE_ENABLED, field values are directly used and returned as suggestions for Autocomplete in CompletionService.CompleteQuery. If completable_option is unset, the server behavior defaults to COMPLETABLE_DISABLED for fields that support setting completable options, which are just `string` fields. For those fields that do not support setting completable options, the server will skip completable option setting, and setting completable_option for those fields will throw `INVALID_ARGUMENT` error.
"dynamicFacetableOption": "A String", # If dynamic_facetable_option is DYNAMIC_FACETABLE_ENABLED, field values are available for dynamic facet. Could only be DYNAMIC_FACETABLE_DISABLED if FieldConfig.indexable_option is INDEXABLE_DISABLED. Otherwise, an `INVALID_ARGUMENT` error will be returned. If dynamic_facetable_option is unset, the server behavior defaults to DYNAMIC_FACETABLE_DISABLED for fields that support setting dynamic facetable options. For those fields that do not support setting dynamic facetable options, such as `object` and `boolean`, the server will skip dynamic facetable option setting, and setting dynamic_facetable_option for those fields will throw `INVALID_ARGUMENT` error.
"fieldPath": "A String", # Required. Field path of the schema field. For example: `title`, `description`, `release_info.release_year`.
"fieldType": "A String", # Output only. Raw type of the field.
"indexableOption": "A String", # If indexable_option is INDEXABLE_ENABLED, field values are indexed so that it can be filtered or faceted in SearchService.Search. If indexable_option is unset, the server behavior defaults to INDEXABLE_DISABLED for fields that support setting indexable options. For those fields that do not support setting indexable options, such as `object` and `boolean` and key properties, the server will skip indexable_option setting, and setting indexable_option for those fields will throw `INVALID_ARGUMENT` error.
"keyPropertyType": "A String", # Output only. Type of the key property that this field is mapped to. Empty string if this is not annotated as mapped to a key property. Example types are `title`, `description`. Full list is defined by `keyPropertyMapping` in the schema field annotation. If the schema field has a `KeyPropertyMapping` annotation, `indexable_option` and `searchable_option` of this field cannot be modified.
"metatagName": "A String", # Optional. The metatag name found in the HTML page. If user defines this field, the value of this metatag name will be used to extract metatag. If the user does not define this field, the FieldConfig.field_path will be used to extract metatag.
"recsFilterableOption": "A String", # If recs_filterable_option is FILTERABLE_ENABLED, field values are filterable by filter expression in RecommendationService.Recommend. If FILTERABLE_ENABLED but the field type is numerical, field values are not filterable by text queries in RecommendationService.Recommend. Only textual fields are supported. If recs_filterable_option is unset, the default setting is FILTERABLE_DISABLED for fields that support setting filterable options. When a field set to [FILTERABLE_DISABLED] is filtered, a warning is generated and an empty result is returned.
"retrievableOption": "A String", # If retrievable_option is RETRIEVABLE_ENABLED, field values are included in the search results. If retrievable_option is unset, the server behavior defaults to RETRIEVABLE_DISABLED for fields that support setting retrievable options. For those fields that do not support setting retrievable options, such as `object` and `boolean`, the server will skip retrievable option setting, and setting retrievable_option for those fields will throw `INVALID_ARGUMENT` error.
"schemaOrgPaths": [ # Field paths for indexing custom attribute from schema.org data. More details of schema.org and its defined types can be found at [schema.org](https://schema.org). It is only used on advanced site search schema. Currently only support full path from root. The full path to a field is constructed by concatenating field names, starting from `_root`, with a period `.` as the delimiter. Examples: * Publish date of the root: _root.datePublished * Publish date of the reviews: _root.review.datePublished
"A String",
],
"searchableOption": "A String", # If searchable_option is SEARCHABLE_ENABLED, field values are searchable by text queries in SearchService.Search. If SEARCHABLE_ENABLED but field type is numerical, field values will not be searchable by text queries in SearchService.Search, as there are no text values associated to numerical fields. If searchable_option is unset, the server behavior defaults to SEARCHABLE_DISABLED for fields that support setting searchable options. Only `string` fields that have no key property mapping support setting searchable_option. For those fields that do not support setting searchable options, the server will skip searchable option setting, and setting searchable_option for those fields will throw `INVALID_ARGUMENT` error.
},
],
"jsonSchema": "A String", # The JSON representation of the schema.
"name": "A String", # Immutable. The full resource name of the schema, in the format of `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/schemas/{schema}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"structSchema": { # The structured representation of the schema.
"a_key": "", # Properties of the object.
},
},
"workspaceConfig": { # Config to store data store type configuration for workspace data # Config to store data store type configuration for workspace data. This must be set when DataStore.content_config is set as DataStore.ContentConfig.GOOGLE_WORKSPACE.
"dasherCustomerId": "A String", # Obfuscated Dasher customer ID.
"superAdminEmailAddress": "A String", # Optional. The super admin email address for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
"superAdminServiceAccount": "A String", # Optional. The super admin service account for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
"type": "A String", # The Google Workspace data source.
},
}</pre>
</div>
<div class="method">
<code class="details" id="updateDocumentProcessingConfig">updateDocumentProcessingConfig(name, body=None, updateMask=None, x__xgafv=None)</code>
<pre>Updates the DocumentProcessingConfig. DocumentProcessingConfig is a singleon resource of DataStore. It's empty when DataStore is created. The first call to this method will set up DocumentProcessingConfig.
Args:
name: string, The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`. (required)
body: object, The request body.
The object takes the form of:
{ # A singleton resource of DataStore. If it's empty when DataStore is created and DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED, the default parser will default to digital parser.
"chunkingConfig": { # Configuration for chunking config. # Whether chunking mode is enabled.
"layoutBasedChunkingConfig": { # Configuration for the layout based chunking. # Configuration for the layout based chunking.
"chunkSize": 42, # The token size limit for each chunk. Supported values: 100-500 (inclusive). Default value: 500.
"includeAncestorHeadings": True or False, # Whether to include appending different levels of headings to chunks from the middle of the document to prevent context loss. Default value: False.
},
},
"defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
"name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
"parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and layout parsing are supported. * `docx`: Override parsing config for DOCX files, only digital parsing and layout parsing are supported. * `pptx`: Override parsing config for PPTX files, only digital parsing and layout parsing are supported. * `xlsm`: Override parsing config for XLSM files, only digital parsing and layout parsing are supported. * `xlsx`: Override parsing config for XLSX files, only digital parsing and layout parsing are supported.
"a_key": { # Related configurations applied to a specific type of document parser.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
},
}
updateMask: string, Indicates which fields in the provided DocumentProcessingConfig to update. The following are the only supported fields: * DocumentProcessingConfig.ocr_config If not set, all supported fields are updated.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # A singleton resource of DataStore. If it's empty when DataStore is created and DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED, the default parser will default to digital parser.
"chunkingConfig": { # Configuration for chunking config. # Whether chunking mode is enabled.
"layoutBasedChunkingConfig": { # Configuration for the layout based chunking. # Configuration for the layout based chunking.
"chunkSize": 42, # The token size limit for each chunk. Supported values: 100-500 (inclusive). Default value: 500.
"includeAncestorHeadings": True or False, # Whether to include appending different levels of headings to chunks from the middle of the document to prevent context loss. Default value: False.
},
},
"defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
"name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
"parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and layout parsing are supported. * `docx`: Override parsing config for DOCX files, only digital parsing and layout parsing are supported. * `pptx`: Override parsing config for PPTX files, only digital parsing and layout parsing are supported. * `xlsm`: Override parsing config for XLSM files, only digital parsing and layout parsing are supported. * `xlsx`: Override parsing config for XLSX files, only digital parsing and layout parsing are supported.
"a_key": { # Related configurations applied to a specific type of document parser.
"digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
},
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
"enableGetProcessedDocument": True or False, # Optional. If true, the processed document will be made available for the GetProcessedDocument API.
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
"A String",
],
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
"A String",
],
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
"A String",
],
"structuredContentTypes": [ # Optional. Contains the required structure types to extract from the document. Supported values: * `shareholder-structure`
"A String",
],
},
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
},
},
}</pre>
</div>
</body></html>
|
