@maxim_mazurok/gapi.client.aiplatform-v1beta1 0.0.20240725 → 0.0.20240727
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/index.d.ts +194 -5
- package/package.json +1 -1
package/index.d.ts
CHANGED
|
@@ -9,7 +9,7 @@
|
|
|
9
9
|
// This file was generated by https://github.com/Maxim-Mazurok/google-api-typings-generator. Please do not edit it manually.
|
|
10
10
|
// In case of any problems please post issue to https://github.com/Maxim-Mazurok/google-api-typings-generator
|
|
11
11
|
// Generated from: https://aiplatform.googleapis.com/$discovery/rest?version=v1beta1
|
|
12
|
-
// Revision:
|
|
12
|
+
// Revision: 20240727
|
|
13
13
|
|
|
14
14
|
/// <reference types="gapi.client" />
|
|
15
15
|
|
|
@@ -39,6 +39,8 @@ declare namespace gapi.client {
|
|
|
39
39
|
interface CloudAiLargeModelsVisionImage {
|
|
40
40
|
/** Image encoding, encoded as "image/png" or "image/jpg". */
|
|
41
41
|
encoding?: string;
|
|
42
|
+
/** Generation seed for the sampled image. This parameter is exposed to the user only if one of the following is true: 1. The user specified per-example seeds in the request. 2. The user doesn't specify the generation seed in the request. */
|
|
43
|
+
generationSeed?: number;
|
|
42
44
|
/** Raw bytes. */
|
|
43
45
|
image?: string;
|
|
44
46
|
/** RAI scores for generated image. */
|
|
@@ -457,6 +459,10 @@ declare namespace gapi.client {
|
|
|
457
459
|
partialFailures?: GoogleRpcStatus[];
|
|
458
460
|
/** Output only. Information about resources that had been consumed by this job. Provided in real time at best effort basis, as well as a final value once the job completes. Note: This field currently may be not populated for batch predictions that use AutoML Models. */
|
|
459
461
|
resourcesConsumed?: GoogleCloudAiplatformV1beta1ResourcesConsumed;
|
|
462
|
+
/** Output only. Reserved for future use. */
|
|
463
|
+
satisfiesPzi?: boolean;
|
|
464
|
+
/** Output only. Reserved for future use. */
|
|
465
|
+
satisfiesPzs?: boolean;
|
|
460
466
|
/** The service account that the DeployedModel's container runs as. If not specified, a system generated one will be used, which has minimal permissions and the custom container, if used, may not have enough permission to access other Google Cloud resources. Users deploying the Model must have the `iam.serviceAccounts.actAs` permission on this service account. */
|
|
461
467
|
serviceAccount?: string;
|
|
462
468
|
/** Output only. Time when the BatchPredictionJob for the first time entered the `JOB_STATE_RUNNING` state. */
|
|
@@ -636,8 +642,6 @@ declare namespace gapi.client {
|
|
|
636
642
|
index?: number;
|
|
637
643
|
/** Output only. List of ratings for the safety of a response candidate. There is at most one rating per category. */
|
|
638
644
|
safetyRatings?: GoogleCloudAiplatformV1beta1SafetyRating[];
|
|
639
|
-
/** Output only. Confidence score of the candidate. */
|
|
640
|
-
score?: number;
|
|
641
645
|
}
|
|
642
646
|
interface GoogleCloudAiplatformV1beta1CheckTrialEarlyStoppingStateMetatdata {
|
|
643
647
|
/** Operation metadata for suggesting Trials. */
|
|
@@ -977,6 +981,10 @@ declare namespace gapi.client {
|
|
|
977
981
|
labels?: {[P in string]: string};
|
|
978
982
|
/** Output only. Resource name of a CustomJob. */
|
|
979
983
|
name?: string;
|
|
984
|
+
/** Output only. Reserved for future use. */
|
|
985
|
+
satisfiesPzi?: boolean;
|
|
986
|
+
/** Output only. Reserved for future use. */
|
|
987
|
+
satisfiesPzs?: boolean;
|
|
980
988
|
/** Output only. Time when the CustomJob for the first time entered the `JOB_STATE_RUNNING` state. */
|
|
981
989
|
startTime?: string;
|
|
982
990
|
/** Output only. The detailed state of the job. */
|
|
@@ -1027,6 +1035,10 @@ declare namespace gapi.client {
|
|
|
1027
1035
|
name?: string;
|
|
1028
1036
|
/** Required. The data that the DataItem represents (for example, an image or a text snippet). The schema of the payload is stored in the parent Dataset's metadata schema's dataItemSchemaUri field. */
|
|
1029
1037
|
payload?: any;
|
|
1038
|
+
/** Output only. Reserved for future use. */
|
|
1039
|
+
satisfiesPzi?: boolean;
|
|
1040
|
+
/** Output only. Reserved for future use. */
|
|
1041
|
+
satisfiesPzs?: boolean;
|
|
1030
1042
|
/** Output only. Timestamp when this DataItem was last updated. */
|
|
1031
1043
|
updateTime?: string;
|
|
1032
1044
|
}
|
|
@@ -1101,11 +1113,59 @@ declare namespace gapi.client {
|
|
|
1101
1113
|
modelReference?: string;
|
|
1102
1114
|
/** Output only. Identifier. The resource name of the Dataset. */
|
|
1103
1115
|
name?: string;
|
|
1116
|
+
/** Output only. Reserved for future use. */
|
|
1117
|
+
satisfiesPzi?: boolean;
|
|
1118
|
+
/** Output only. Reserved for future use. */
|
|
1119
|
+
satisfiesPzs?: boolean;
|
|
1104
1120
|
/** All SavedQueries belong to the Dataset will be returned in List/Get Dataset response. The annotation_specs field will not be populated except for UI cases which will only use annotation_spec_count. In CreateDataset request, a SavedQuery is created together if this field is set, up to one SavedQuery can be set in CreateDatasetRequest. The SavedQuery should not contain any AnnotationSpec. */
|
|
1105
1121
|
savedQueries?: GoogleCloudAiplatformV1beta1SavedQuery[];
|
|
1106
1122
|
/** Output only. Timestamp when this Dataset was last updated. */
|
|
1107
1123
|
updateTime?: string;
|
|
1108
1124
|
}
|
|
1125
|
+
interface GoogleCloudAiplatformV1beta1DatasetDistribution {
|
|
1126
|
+
/** Output only. Defines the histogram bucket. */
|
|
1127
|
+
buckets?: GoogleCloudAiplatformV1beta1DatasetDistributionDistributionBucket[];
|
|
1128
|
+
/** Output only. The maximum of the population values. */
|
|
1129
|
+
max?: number;
|
|
1130
|
+
/** Output only. The arithmetic mean of the values in the population. */
|
|
1131
|
+
mean?: number;
|
|
1132
|
+
/** Output only. The median of the values in the population. */
|
|
1133
|
+
median?: number;
|
|
1134
|
+
/** Output only. The minimum of the population values. */
|
|
1135
|
+
min?: number;
|
|
1136
|
+
/** Output only. The 5th percentile of the values in the population. */
|
|
1137
|
+
p5?: number;
|
|
1138
|
+
/** Output only. The 95th percentile of the values in the population. */
|
|
1139
|
+
p95?: number;
|
|
1140
|
+
/** Output only. Sum of a given population of values. */
|
|
1141
|
+
sum?: number;
|
|
1142
|
+
}
|
|
1143
|
+
interface GoogleCloudAiplatformV1beta1DatasetDistributionDistributionBucket {
|
|
1144
|
+
/** Output only. Number of values in the bucket. */
|
|
1145
|
+
count?: string;
|
|
1146
|
+
/** Output only. Left bound of the bucket. */
|
|
1147
|
+
left?: number;
|
|
1148
|
+
/** Output only. Right bound of the bucket. */
|
|
1149
|
+
right?: number;
|
|
1150
|
+
}
|
|
1151
|
+
interface GoogleCloudAiplatformV1beta1DatasetStats {
|
|
1152
|
+
/** Output only. Number of billable characters in the tuning dataset. */
|
|
1153
|
+
totalBillableCharacterCount?: string;
|
|
1154
|
+
/** Output only. Number of tuning characters in the tuning dataset. */
|
|
1155
|
+
totalTuningCharacterCount?: string;
|
|
1156
|
+
/** Output only. Number of examples in the tuning dataset. */
|
|
1157
|
+
tuningDatasetExampleCount?: string;
|
|
1158
|
+
/** Output only. Number of tuning steps for this Tuning Job. */
|
|
1159
|
+
tuningStepCount?: string;
|
|
1160
|
+
/** Output only. Sample user messages in the training dataset uri. */
|
|
1161
|
+
userDatasetExamples?: GoogleCloudAiplatformV1beta1Content[];
|
|
1162
|
+
/** Output only. Dataset distributions for the user input tokens. */
|
|
1163
|
+
userInputTokenDistribution?: GoogleCloudAiplatformV1beta1DatasetDistribution;
|
|
1164
|
+
/** Output only. Dataset distributions for the messages per example. */
|
|
1165
|
+
userMessagePerExampleDistribution?: GoogleCloudAiplatformV1beta1DatasetDistribution;
|
|
1166
|
+
/** Output only. Dataset distributions for the user output tokens. */
|
|
1167
|
+
userOutputTokenDistribution?: GoogleCloudAiplatformV1beta1DatasetDistribution;
|
|
1168
|
+
}
|
|
1109
1169
|
interface GoogleCloudAiplatformV1beta1DatasetVersion {
|
|
1110
1170
|
/** Output only. Name of the associated BigQuery dataset. */
|
|
1111
1171
|
bigQueryDatasetName?: string;
|
|
@@ -1121,6 +1181,10 @@ declare namespace gapi.client {
|
|
|
1121
1181
|
modelReference?: string;
|
|
1122
1182
|
/** Output only. Identifier. The resource name of the DatasetVersion. */
|
|
1123
1183
|
name?: string;
|
|
1184
|
+
/** Output only. Reserved for future use. */
|
|
1185
|
+
satisfiesPzi?: boolean;
|
|
1186
|
+
/** Output only. Reserved for future use. */
|
|
1187
|
+
satisfiesPzs?: boolean;
|
|
1124
1188
|
/** Output only. Timestamp when this DatasetVersion was last updated. */
|
|
1125
1189
|
updateTime?: string;
|
|
1126
1190
|
}
|
|
@@ -1133,6 +1197,8 @@ declare namespace gapi.client {
|
|
|
1133
1197
|
maxReplicaCount?: number;
|
|
1134
1198
|
/** Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed. */
|
|
1135
1199
|
minReplicaCount?: number;
|
|
1200
|
+
/** Optional. If true, schedule the deployment workload on [spot VMs](https://cloud.google.com/kubernetes-engine/docs/concepts/spot-vms). */
|
|
1201
|
+
spot?: boolean;
|
|
1136
1202
|
}
|
|
1137
1203
|
interface GoogleCloudAiplatformV1beta1DeleteFeatureValuesOperationMetadata {
|
|
1138
1204
|
/** Operation metadata for Featurestore delete Features values. */
|
|
@@ -1289,6 +1355,10 @@ declare namespace gapi.client {
|
|
|
1289
1355
|
encryptionSpec?: GoogleCloudAiplatformV1beta1EncryptionSpec;
|
|
1290
1356
|
/** Immutable. The resource name of the DeploymentResourcePool. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}` */
|
|
1291
1357
|
name?: string;
|
|
1358
|
+
/** Output only. Reserved for future use. */
|
|
1359
|
+
satisfiesPzi?: boolean;
|
|
1360
|
+
/** Output only. Reserved for future use. */
|
|
1361
|
+
satisfiesPzs?: boolean;
|
|
1292
1362
|
/** The service account that the DeploymentResourcePool's container(s) run as. Specify the email address of the service account. If this service account is not specified, the container(s) run as a service account that doesn't have access to the resource project. Users deploying the Models to this DeploymentResourcePool must have the `iam.serviceAccounts.actAs` permission on this service account. */
|
|
1293
1363
|
serviceAccount?: string;
|
|
1294
1364
|
}
|
|
@@ -1345,6 +1415,34 @@ declare namespace gapi.client {
|
|
|
1345
1415
|
/** Type of the boot disk (default is "pd-ssd"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive). */
|
|
1346
1416
|
bootDiskType?: string;
|
|
1347
1417
|
}
|
|
1418
|
+
interface GoogleCloudAiplatformV1beta1DistillationDataStats {
|
|
1419
|
+
/** Output only. Statistics computed for the training dataset. */
|
|
1420
|
+
trainingDatasetStats?: GoogleCloudAiplatformV1beta1DatasetStats;
|
|
1421
|
+
}
|
|
1422
|
+
interface GoogleCloudAiplatformV1beta1DistillationHyperParameters {
|
|
1423
|
+
/** Optional. Adapter size for distillation. */
|
|
1424
|
+
adapterSize?: string;
|
|
1425
|
+
/** Optional. Number of complete passes the model makes over the entire training dataset during training. */
|
|
1426
|
+
epochCount?: string;
|
|
1427
|
+
/** Optional. Multiplier for adjusting the default learning rate. */
|
|
1428
|
+
learningRateMultiplier?: number;
|
|
1429
|
+
}
|
|
1430
|
+
interface GoogleCloudAiplatformV1beta1DistillationSpec {
|
|
1431
|
+
/** The base teacher model that is being distilled, e.g., "gemini-1.0-pro-002". */
|
|
1432
|
+
baseTeacherModel?: string;
|
|
1433
|
+
/** Optional. Hyperparameters for Distillation. */
|
|
1434
|
+
hyperParameters?: GoogleCloudAiplatformV1beta1DistillationHyperParameters;
|
|
1435
|
+
/** Required. A path in a Cloud Storage bucket, which will be treated as the root output directory of the distillation pipeline. It is used by the system to generate the paths of output artifacts. */
|
|
1436
|
+
pipelineRootDirectory?: string;
|
|
1437
|
+
/** The student model that is being tuned, e.g., "google/gemma-2b-1.1-it". */
|
|
1438
|
+
studentModel?: string;
|
|
1439
|
+
/** Required. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file. */
|
|
1440
|
+
trainingDatasetUri?: string;
|
|
1441
|
+
/** The resource name of the Tuned teacher model. Format: `projects/{project}/locations/{location}/models/{model}`. */
|
|
1442
|
+
tunedTeacherModelSource?: string;
|
|
1443
|
+
/** Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file. */
|
|
1444
|
+
validationDatasetUri?: string;
|
|
1445
|
+
}
|
|
1348
1446
|
interface GoogleCloudAiplatformV1beta1DoubleArray {
|
|
1349
1447
|
/** A list of double values. */
|
|
1350
1448
|
values?: number[];
|
|
@@ -1384,6 +1482,10 @@ declare namespace gapi.client {
|
|
|
1384
1482
|
predictRequestResponseLoggingConfig?: GoogleCloudAiplatformV1beta1PredictRequestResponseLoggingConfig;
|
|
1385
1483
|
/** Optional. Configuration for private service connect. network and private_service_connect_config are mutually exclusive. */
|
|
1386
1484
|
privateServiceConnectConfig?: GoogleCloudAiplatformV1beta1PrivateServiceConnectConfig;
|
|
1485
|
+
/** Output only. Reserved for future use. */
|
|
1486
|
+
satisfiesPzi?: boolean;
|
|
1487
|
+
/** Output only. Reserved for future use. */
|
|
1488
|
+
satisfiesPzs?: boolean;
|
|
1387
1489
|
/** A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. */
|
|
1388
1490
|
trafficSplit?: {[P in string]: number};
|
|
1389
1491
|
/** Output only. Timestamp when this Endpoint was last updated. */
|
|
@@ -2534,6 +2636,14 @@ declare namespace gapi.client {
|
|
|
2534
2636
|
promptTokenCount?: number;
|
|
2535
2637
|
totalTokenCount?: number;
|
|
2536
2638
|
}
|
|
2639
|
+
interface GoogleCloudAiplatformV1beta1GenerateVideoResponse {
|
|
2640
|
+
/** The cloud storage uris of the generated videos. */
|
|
2641
|
+
generatedSamples?: string[];
|
|
2642
|
+
/** Returns if any videos were filtered due to RAI policies. */
|
|
2643
|
+
raiMediaFilteredCount?: number;
|
|
2644
|
+
/** Returns rai failure reasons if any. */
|
|
2645
|
+
raiMediaFilteredReasons?: string[];
|
|
2646
|
+
}
|
|
2537
2647
|
interface GoogleCloudAiplatformV1beta1GenerationConfig {
|
|
2538
2648
|
/** Optional. Number of candidates to generate. */
|
|
2539
2649
|
candidateCount?: number;
|
|
@@ -2547,6 +2657,8 @@ declare namespace gapi.client {
|
|
|
2547
2657
|
responseMimeType?: string;
|
|
2548
2658
|
/** Optional. The `Schema` object allows the definition of input and output data types. These types can be objects, but also primitives and arrays. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). If set, a compatible response_mime_type must also be set. Compatible mimetypes: `application/json`: Schema for JSON response. */
|
|
2549
2659
|
responseSchema?: GoogleCloudAiplatformV1beta1Schema;
|
|
2660
|
+
/** Optional. Routing configuration. */
|
|
2661
|
+
routingConfig?: GoogleCloudAiplatformV1beta1GenerationConfigRoutingConfig;
|
|
2550
2662
|
/** Optional. Stop sequences. */
|
|
2551
2663
|
stopSequences?: string[];
|
|
2552
2664
|
/** Optional. Controls the randomness of predictions. */
|
|
@@ -2556,6 +2668,20 @@ declare namespace gapi.client {
|
|
|
2556
2668
|
/** Optional. If specified, nucleus sampling will be used. */
|
|
2557
2669
|
topP?: number;
|
|
2558
2670
|
}
|
|
2671
|
+
interface GoogleCloudAiplatformV1beta1GenerationConfigRoutingConfig {
|
|
2672
|
+
/** Automated routing. */
|
|
2673
|
+
autoMode?: GoogleCloudAiplatformV1beta1GenerationConfigRoutingConfigAutoRoutingMode;
|
|
2674
|
+
/** Manual routing. */
|
|
2675
|
+
manualMode?: GoogleCloudAiplatformV1beta1GenerationConfigRoutingConfigManualRoutingMode;
|
|
2676
|
+
}
|
|
2677
|
+
interface GoogleCloudAiplatformV1beta1GenerationConfigRoutingConfigAutoRoutingMode {
|
|
2678
|
+
/** The model routing preference. */
|
|
2679
|
+
modelRoutingPreference?: string;
|
|
2680
|
+
}
|
|
2681
|
+
interface GoogleCloudAiplatformV1beta1GenerationConfigRoutingConfigManualRoutingMode {
|
|
2682
|
+
/** The model name to use. Only the public LLM models are accepted. e.g. gemini-1.5-pro-001. */
|
|
2683
|
+
modelName?: string;
|
|
2684
|
+
}
|
|
2559
2685
|
interface GoogleCloudAiplatformV1beta1GenericOperationMetadata {
|
|
2560
2686
|
/** Output only. Time when the operation was created. */
|
|
2561
2687
|
createTime?: string;
|
|
@@ -2662,6 +2788,10 @@ declare namespace gapi.client {
|
|
|
2662
2788
|
name?: string;
|
|
2663
2789
|
/** Required. The desired number of Trials to run in parallel. */
|
|
2664
2790
|
parallelTrialCount?: number;
|
|
2791
|
+
/** Output only. Reserved for future use. */
|
|
2792
|
+
satisfiesPzi?: boolean;
|
|
2793
|
+
/** Output only. Reserved for future use. */
|
|
2794
|
+
satisfiesPzs?: boolean;
|
|
2665
2795
|
/** Output only. Time when the HyperparameterTuningJob for the first time entered the `JOB_STATE_RUNNING` state. */
|
|
2666
2796
|
startTime?: string;
|
|
2667
2797
|
/** Output only. The detailed state of the job. */
|
|
@@ -3310,6 +3440,8 @@ declare namespace gapi.client {
|
|
|
3310
3440
|
acceleratorType?: string;
|
|
3311
3441
|
/** Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. */
|
|
3312
3442
|
machineType?: string;
|
|
3443
|
+
/** Optional. Immutable. Configuration controlling how this resource pool consumes reservation. */
|
|
3444
|
+
reservationAffinity?: GoogleCloudAiplatformV1beta1ReservationAffinity;
|
|
3313
3445
|
/** Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1"). */
|
|
3314
3446
|
tpuTopology?: string;
|
|
3315
3447
|
}
|
|
@@ -4184,6 +4316,10 @@ declare namespace gapi.client {
|
|
|
4184
4316
|
nasJobOutput?: GoogleCloudAiplatformV1beta1NasJobOutput;
|
|
4185
4317
|
/** Required. The specification of a NasJob. */
|
|
4186
4318
|
nasJobSpec?: GoogleCloudAiplatformV1beta1NasJobSpec;
|
|
4319
|
+
/** Output only. Reserved for future use. */
|
|
4320
|
+
satisfiesPzi?: boolean;
|
|
4321
|
+
/** Output only. Reserved for future use. */
|
|
4322
|
+
satisfiesPzs?: boolean;
|
|
4187
4323
|
/** Output only. Time when the NasJob for the first time entered the `JOB_STATE_RUNNING` state. */
|
|
4188
4324
|
startTime?: string;
|
|
4189
4325
|
/** Output only. The detailed state of the job. */
|
|
@@ -4392,6 +4528,8 @@ declare namespace gapi.client {
|
|
|
4392
4528
|
directNotebookSource?: GoogleCloudAiplatformV1beta1NotebookExecutionJobDirectNotebookSource;
|
|
4393
4529
|
/** The display name of the NotebookExecutionJob. The name can be up to 128 characters long and can consist of any UTF-8 characters. */
|
|
4394
4530
|
displayName?: string;
|
|
4531
|
+
/** Customer-managed encryption key spec for the notebook execution job. This field is auto-populated if the NotebookRuntimeTemplate has an encryption spec. */
|
|
4532
|
+
encryptionSpec?: GoogleCloudAiplatformV1beta1EncryptionSpec;
|
|
4395
4533
|
/** Max running time of the execution job in seconds (default 86400s / 24 hrs). */
|
|
4396
4534
|
executionTimeout?: string;
|
|
4397
4535
|
/** The user email to run the execution as. Only supported by Colab runtimes. */
|
|
@@ -4793,6 +4931,11 @@ declare namespace gapi.client {
|
|
|
4793
4931
|
/** Required. The key is a name of one of the Dataset's data columns. The value of the key (either the label's value or value in the column) must be one of {`training`, `validation`, `test`}, and it defines to which set the given piece of data is assigned. If for a piece of data the key is not present or has an invalid value, that piece is ignored by the pipeline. */
|
|
4794
4932
|
key?: string;
|
|
4795
4933
|
}
|
|
4934
|
+
interface GoogleCloudAiplatformV1beta1PredictLongRunningMetadata {}
|
|
4935
|
+
interface GoogleCloudAiplatformV1beta1PredictLongRunningResponse {
|
|
4936
|
+
/** The response of the video generation prediction. */
|
|
4937
|
+
generateVideoResponse?: GoogleCloudAiplatformV1beta1GenerateVideoResponse;
|
|
4938
|
+
}
|
|
4796
4939
|
interface GoogleCloudAiplatformV1beta1PredictRequest {
|
|
4797
4940
|
/** Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri. */
|
|
4798
4941
|
instances?: any[];
|
|
@@ -4850,6 +4993,8 @@ declare namespace gapi.client {
|
|
|
4850
4993
|
enablePrivateServiceConnect?: boolean;
|
|
4851
4994
|
/** A list of Projects from which the forwarding rule will target the service attachment. */
|
|
4852
4995
|
projectAllowlist?: string[];
|
|
4996
|
+
/** Output only. The name of the generated service attachment resource. This is only populated if the endpoint is deployed with PrivateServiceConnect. */
|
|
4997
|
+
serviceAttachment?: string;
|
|
4853
4998
|
}
|
|
4854
4999
|
interface GoogleCloudAiplatformV1beta1Probe {
|
|
4855
5000
|
/** ExecAction probes the health of a container by executing a command. */
|
|
@@ -4952,6 +5097,8 @@ declare namespace gapi.client {
|
|
|
4952
5097
|
interface GoogleCloudAiplatformV1beta1PublisherModelCallToActionDeployDeployMetadata {
|
|
4953
5098
|
/** Optional. Labels for the deployment. For managing deployment config like verifying, source of deployment config, etc. */
|
|
4954
5099
|
labels?: {[P in string]: string};
|
|
5100
|
+
/** Optional. Sample request for deployed endpoint. */
|
|
5101
|
+
sampleRequest?: string;
|
|
4955
5102
|
}
|
|
4956
5103
|
interface GoogleCloudAiplatformV1beta1PublisherModelCallToActionDeployGke {
|
|
4957
5104
|
/** Optional. GKE deployment configuration in yaml format. */
|
|
@@ -5222,10 +5369,12 @@ declare namespace gapi.client {
|
|
|
5222
5369
|
contexts?: GoogleCloudAiplatformV1beta1RagContextsContext[];
|
|
5223
5370
|
}
|
|
5224
5371
|
interface GoogleCloudAiplatformV1beta1RagContextsContext {
|
|
5225
|
-
/** The distance between the query vector and the context text vector. */
|
|
5372
|
+
/** The distance between the query dense embedding vector and the context text vector. */
|
|
5226
5373
|
distance?: number;
|
|
5227
5374
|
/** For vertex RagStore, if the file is imported from Cloud Storage or Google Drive, source_uri will be original file URI in Cloud Storage or Google Drive; if file is uploaded, source_uri will be file display name. */
|
|
5228
5375
|
sourceUri?: string;
|
|
5376
|
+
/** The distance between the query sparse embedding vector and the context text vector. */
|
|
5377
|
+
sparseDistance?: number;
|
|
5229
5378
|
/** The text chunk. */
|
|
5230
5379
|
text?: string;
|
|
5231
5380
|
}
|
|
@@ -5244,9 +5393,29 @@ declare namespace gapi.client {
|
|
|
5244
5393
|
updateTime?: string;
|
|
5245
5394
|
}
|
|
5246
5395
|
interface GoogleCloudAiplatformV1beta1RagEmbeddingModelConfig {
|
|
5247
|
-
/**
|
|
5396
|
+
/** Configuration for hybrid search. */
|
|
5397
|
+
hybridSearchConfig?: GoogleCloudAiplatformV1beta1RagEmbeddingModelConfigHybridSearchConfig;
|
|
5398
|
+
/** The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search. */
|
|
5248
5399
|
vertexPredictionEndpoint?: GoogleCloudAiplatformV1beta1RagEmbeddingModelConfigVertexPredictionEndpoint;
|
|
5249
5400
|
}
|
|
5401
|
+
interface GoogleCloudAiplatformV1beta1RagEmbeddingModelConfigHybridSearchConfig {
|
|
5402
|
+
/** Required. The Vertex AI Prediction Endpoint that hosts the embedding model for dense embedding generations. */
|
|
5403
|
+
denseEmbeddingModelPredictionEndpoint?: GoogleCloudAiplatformV1beta1RagEmbeddingModelConfigVertexPredictionEndpoint;
|
|
5404
|
+
/** Optional. The configuration for sparse embedding generation. This field is optional the default behavior depends on the vector database choice on the RagCorpus. */
|
|
5405
|
+
sparseEmbeddingConfig?: GoogleCloudAiplatformV1beta1RagEmbeddingModelConfigSparseEmbeddingConfig;
|
|
5406
|
+
}
|
|
5407
|
+
interface GoogleCloudAiplatformV1beta1RagEmbeddingModelConfigSparseEmbeddingConfig {
|
|
5408
|
+
/** Use BM25 scoring algorithm. */
|
|
5409
|
+
bm25?: GoogleCloudAiplatformV1beta1RagEmbeddingModelConfigSparseEmbeddingConfigBm25;
|
|
5410
|
+
}
|
|
5411
|
+
interface GoogleCloudAiplatformV1beta1RagEmbeddingModelConfigSparseEmbeddingConfigBm25 {
|
|
5412
|
+
/** Optional. The parameter to control document length normalization. It determines how much the document length affects the final score. b is in the range of [0, 1]. The default value is 0.75. */
|
|
5413
|
+
b?: number;
|
|
5414
|
+
/** Optional. The parameter to control term frequency saturation. It determines the scaling between the matching term frequency and final score. k1 is in the range of [1.2, 3]. The default value is 1.2. */
|
|
5415
|
+
k1?: number;
|
|
5416
|
+
/** Optional. Use multilingual tokenizer if set to true. */
|
|
5417
|
+
multilingual?: boolean;
|
|
5418
|
+
}
|
|
5250
5419
|
interface GoogleCloudAiplatformV1beta1RagEmbeddingModelConfigVertexPredictionEndpoint {
|
|
5251
5420
|
/** Required. The endpoint resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` or `projects/{project}/locations/{location}/endpoints/{endpoint}` */
|
|
5252
5421
|
endpoint?: string;
|
|
@@ -5463,6 +5632,14 @@ declare namespace gapi.client {
|
|
|
5463
5632
|
/** If the idle shutdown is blocked by CP, CP will send the block message. Otherwise, this field is not set. */
|
|
5464
5633
|
idleShutdownMessage?: string;
|
|
5465
5634
|
}
|
|
5635
|
+
interface GoogleCloudAiplatformV1beta1ReservationAffinity {
|
|
5636
|
+
/** Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value. */
|
|
5637
|
+
key?: string;
|
|
5638
|
+
/** Required. Specifies the reservation affinity type. */
|
|
5639
|
+
reservationAffinityType?: string;
|
|
5640
|
+
/** Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation. */
|
|
5641
|
+
values?: string[];
|
|
5642
|
+
}
|
|
5466
5643
|
interface GoogleCloudAiplatformV1beta1ResourcePool {
|
|
5467
5644
|
/** Optional. Optional spec to configure GKE or Ray-on-Vertex autoscaling */
|
|
5468
5645
|
autoscalingSpec?: GoogleCloudAiplatformV1beta1ResourcePoolAutoscalingSpec;
|
|
@@ -5527,6 +5704,8 @@ declare namespace gapi.client {
|
|
|
5527
5704
|
ragCorpora?: string[];
|
|
5528
5705
|
/** Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support. */
|
|
5529
5706
|
ragResources?: GoogleCloudAiplatformV1beta1RetrieveContextsRequestVertexRagStoreRagResource[];
|
|
5707
|
+
/** Optional. Configurations for hybrid search results ranking. */
|
|
5708
|
+
ranking?: GoogleCloudAiplatformV1beta1RetrieveContextsRequestVertexRagStoreRanking;
|
|
5530
5709
|
/** Optional. Only return contexts with vector distance smaller than the threshold. */
|
|
5531
5710
|
vectorDistanceThreshold?: number;
|
|
5532
5711
|
}
|
|
@@ -5536,6 +5715,10 @@ declare namespace gapi.client {
|
|
|
5536
5715
|
/** Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field. */
|
|
5537
5716
|
ragFileIds?: string[];
|
|
5538
5717
|
}
|
|
5718
|
+
interface GoogleCloudAiplatformV1beta1RetrieveContextsRequestVertexRagStoreRanking {
|
|
5719
|
+
/** Optional. Alpha value controls the weight between dense and sparse vector search results. The range is [0, 1], while 0 means sparse vector search only and 1 means dense vector search only. The default value is 0.5 which balances sparse and dense vector search equally. */
|
|
5720
|
+
alpha?: number;
|
|
5721
|
+
}
|
|
5539
5722
|
interface GoogleCloudAiplatformV1beta1RetrieveContextsResponse {
|
|
5540
5723
|
/** The contexts of the query. */
|
|
5541
5724
|
contexts?: GoogleCloudAiplatformV1beta1RagContexts;
|
|
@@ -8044,6 +8227,8 @@ declare namespace gapi.client {
|
|
|
8044
8227
|
model?: string;
|
|
8045
8228
|
}
|
|
8046
8229
|
interface GoogleCloudAiplatformV1beta1TuningDataStats {
|
|
8230
|
+
/** Output only. Statistics for distillation. */
|
|
8231
|
+
distillationDataStats?: GoogleCloudAiplatformV1beta1DistillationDataStats;
|
|
8047
8232
|
/** The SFT Tuning data stats. */
|
|
8048
8233
|
supervisedTuningDataStats?: GoogleCloudAiplatformV1beta1SupervisedTuningDataStats;
|
|
8049
8234
|
}
|
|
@@ -8054,6 +8239,8 @@ declare namespace gapi.client {
|
|
|
8054
8239
|
createTime?: string;
|
|
8055
8240
|
/** Optional. The description of the TuningJob. */
|
|
8056
8241
|
description?: string;
|
|
8242
|
+
/** Tuning Spec for Distillation. */
|
|
8243
|
+
distillationSpec?: GoogleCloudAiplatformV1beta1DistillationSpec;
|
|
8057
8244
|
/** Customer-managed encryption key options for a TuningJob. If this is set, then all resources created by the TuningJob will be encrypted with the provided encryption key. */
|
|
8058
8245
|
encryptionSpec?: GoogleCloudAiplatformV1beta1EncryptionSpec;
|
|
8059
8246
|
/** Output only. Time when the TuningJob entered any of the following JobStates: `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED`, `JOB_STATE_CANCELLED`, `JOB_STATE_EXPIRED`. */
|
|
@@ -8066,6 +8253,8 @@ declare namespace gapi.client {
|
|
|
8066
8253
|
labels?: {[P in string]: string};
|
|
8067
8254
|
/** Output only. Identifier. Resource name of a TuningJob. Format: `projects/{project}/locations/{location}/tuningJobs/{tuning_job}` */
|
|
8068
8255
|
name?: string;
|
|
8256
|
+
/** Output only. The resource name of the PipelineJob associated with the TuningJob. Format: `projects/{project}/locations/{location}/pipelineJobs/{pipeline_job}`. */
|
|
8257
|
+
pipelineJob?: string;
|
|
8069
8258
|
/** Output only. Time when the TuningJob for the first time entered the `JOB_STATE_RUNNING` state. */
|
|
8070
8259
|
startTime?: string;
|
|
8071
8260
|
/** Output only. The detailed state of the job. */
|