@maxim_mazurok/gapi.client.aiplatform-v1beta1 0.0.20250205 → 0.0.20250212

package/index.d.ts

@@ -9,7 +9,7 @@
 // This file was generated by https://github.com/Maxim-Mazurok/google-api-typings-generator. Please do not edit it manually.
 // In case of any problems please post issue to https://github.com/Maxim-Mazurok/google-api-typings-generator
 // Generated from: https://aiplatform.googleapis.com/$discovery/rest?version=v1beta1
-// Revision: 20250205
+// Revision: 20250212
 
 /// <reference types="gapi.client" />
 
@@ -350,9 +350,9 @@ declare namespace gapi.client {
       serviceAccount?: string;
     }
     interface GoogleCloudAiplatformV1beta1AutomaticResources {
-      /** Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number. */
+      /** Immutable. The maximum number of replicas that may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale to that many replicas is guaranteed (barring service outages). If traffic increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number. */
       maxReplicaCount?: number;
-      /** Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error. */
+      /** Immutable. The minimum number of replicas that will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error. */
       minReplicaCount?: number;
     }
     interface GoogleCloudAiplatformV1beta1AutoraterConfig {
@@ -663,7 +663,7 @@ declare namespace gapi.client {
       displayName?: string;
       /** Timestamp of when this resource is considered expired. This is *always* provided on output, regardless of what was sent on input. */
       expireTime?: string;
-      /** Immutable. The name of the publisher model to use for cached content. Format: projects/{project}/locations/{location}/publishers/{publisher}/models/{model} */
+      /** Immutable. The name of the `Model` to use for cached content. Currently, only the published Gemini base models are supported, in form of projects/{PROJECT}/locations/{LOCATION}/publishers/google/models/{MODEL} */
       model?: string;
       /** Immutable. Identifier. The server-generated resource name of the cached content Format: projects/{project}/locations/{location}/cachedContents/{cached_content} */
       name?: string;
@@ -1344,13 +1344,13 @@ declare namespace gapi.client {
     interface GoogleCloudAiplatformV1beta1DedicatedResources {
       /** Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and autoscaling_metric_specs.target to `80`. */
       autoscalingMetricSpecs?: GoogleCloudAiplatformV1beta1AutoscalingMetricSpec[];
-      /** Required. Immutable. The specification of a single machine used by the prediction. */
+      /** Required. Immutable. The specification of a single machine being used. */
       machineSpec?: GoogleCloudAiplatformV1beta1MachineSpec;
-      /** Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type). */
+      /** Immutable. The maximum number of replicas that may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale to that many replicas is guaranteed (barring service outages). If traffic increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type). */
       maxReplicaCount?: number;
-      /** 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. */
+      /** Required. Immutable. The minimum number of machine replicas that will be always deployed on. This value must be greater than or equal to 1. If traffic increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed. */
       minReplicaCount?: number;
-      /** Optional. Number of required available replicas for the deployment to succeed. This field is only needed when partial model deployment/mutation is desired. If set, the model deploy/mutate operation will succeed once available_replica_count reaches required_replica_count, and the rest of the replicas will be retried. If not set, the default required_replica_count will be min_replica_count. */
+      /** Optional. Number of required available replicas for the deployment to succeed. This field is only needed when partial deployment/mutation is desired. If set, the deploy/mutate operation will succeed once available_replica_count reaches required_replica_count, and the rest of the replicas will be retried. If not set, the default required_replica_count will be min_replica_count. */
       requiredReplicaCount?: number;
       /** Optional. If true, schedule the deployment workload on [spot VMs](https://cloud.google.com/kubernetes-engine/docs/concepts/spot-vms). */
       spot?: boolean;
@@ -1560,7 +1560,7 @@ declare namespace gapi.client {
       endpointDisplayName?: string;
       /** Optional. The Hugging Face read access token used to access the model artifacts of gated models. */
       huggingFaceAccessToken?: string;
-      /** Required. The name of the PublisherModel resource. Format: `publishers/{publisher}/models/{publisher_model}@{version_id}`, or `publishers/hf-{hugging-face-author}/models/{hugging-face-model-name}@001` or Hugging Face model ID like `google/gemma-2-2b-it`. */
+      /** Required. The model to deploy. Format: 1. `publishers/{publisher}/models/{publisher_model}@{version_id}`, or `publishers/hf-{hugging-face-author}/models/{hugging-face-model-name}@001`. 2. Hugging Face model ID like `google/gemma-2-2b-it`. 3. Custom model Google Cloud Storage URI like `gs://bucket`. 4. Custom model zip file like `https://abc.com/a.zip`. */
       model?: string;
       /** Optional. The user-specified display name of the uploaded model. If not set, a default name will be used. */
       modelDisplayName?: string;
@@ -1762,6 +1762,16 @@ declare namespace gapi.client {
       /** Explanation type. For AutoML Image Classification models, possible values are: * `image-integrated-gradients` * `image-xrai` */
       explanationType?: string;
     }
+    interface GoogleCloudAiplatformV1beta1EvaluateDatasetRequest {
+      /** Optional. Autorater config used for evaluation. */
+      autoraterConfig?: GoogleCloudAiplatformV1beta1AutoraterConfig;
+      /** Required. The dataset used for evaluation. */
+      dataset?: GoogleCloudAiplatformV1beta1EvaluationDataset;
+      /** Required. The metrics used for evaluation. */
+      metrics?: GoogleCloudAiplatformV1beta1Metric[];
+      /** Required. Config for evaluation output. */
+      outputConfig?: GoogleCloudAiplatformV1beta1OutputConfig;
+    }
     interface GoogleCloudAiplatformV1beta1EvaluateInstancesRequest {
       /** Optional. Autorater config used for evaluation. */
       autoraterConfig?: GoogleCloudAiplatformV1beta1AutoraterConfig;
@@ -1892,6 +1902,12 @@ declare namespace gapi.client {
       /** Results for trajectory single tool use metric. */
       trajectorySingleToolUseResults?: GoogleCloudAiplatformV1beta1TrajectorySingleToolUseResults;
     }
+    interface GoogleCloudAiplatformV1beta1EvaluationDataset {
+      /** BigQuery source holds the dataset. */
+      bigquerySource?: GoogleCloudAiplatformV1beta1BigQuerySource;
+      /** Cloud storage source holds the dataset. */
+      gcsSource?: GoogleCloudAiplatformV1beta1GcsSource;
+    }
     interface GoogleCloudAiplatformV1beta1Event {
       /** Required. The relative resource name of the Artifact in the Event. */
       artifact?: string;
@@ -3121,8 +3137,6 @@ declare namespace gapi.client {
       stopSequences?: string[];
       /** Optional. Controls the randomness of predictions. */
       temperature?: number;
-      /** Optional. Config for thinking features. An error will be returned if this field is set for models that don't support thinking. */
-      thinkingConfig?: GoogleCloudAiplatformV1beta1GenerationConfigThinkingConfig;
       /** Optional. If specified, top-k sampling will be used. */
       topK?: number;
       /** Optional. If specified, nucleus sampling will be used. */
@@ -3142,10 +3156,6 @@ declare namespace gapi.client {
       /** The model name to use. Only the public LLM models are accepted. e.g. 'gemini-1.5-pro-001'. */
       modelName?: string;
     }
-    interface GoogleCloudAiplatformV1beta1GenerationConfigThinkingConfig {
-      /** Optional. Indicates whether to include thoughts in the response. If true, thoughts are returned only when available. */
-      includeThoughts?: boolean;
-    }
     interface GoogleCloudAiplatformV1beta1GenericOperationMetadata {
       /** Output only. Time when the operation was created. */
       createTime?: string;
@@ -3965,8 +3975,6 @@ declare namespace gapi.client {
       acceleratorType?: string;
       /** 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. */
       machineType?: string;
-      /** Optional. Immutable. The number of nodes per replica for multihost GPU deployments. */
-      multihostGpuNodeCount?: number;
       /** Optional. Immutable. Configuration controlling how this resource pool consumes reservation. */
       reservationAffinity?: GoogleCloudAiplatformV1beta1ReservationAffinity;
       /** Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1"). */
@@ -4032,6 +4040,20 @@ declare namespace gapi.client {
       /** The disk utilization of the MetadataStore in bytes. */
       diskUtilizationBytes?: string;
     }
+    interface GoogleCloudAiplatformV1beta1Metric {
+      /** Optional. The aggregation metrics to use. */
+      aggregationMetrics?: string[];
+      /** Spec for bleu metric. */
+      bleuSpec?: GoogleCloudAiplatformV1beta1BleuSpec;
+      /** Spec for exact match metric. */
+      exactMatchSpec?: any;
+      /** Spec for pairwise metric. */
+      pairwiseMetricSpec?: GoogleCloudAiplatformV1beta1PairwiseMetricSpec;
+      /** Spec for pointwise metric. */
+      pointwiseMetricSpec?: GoogleCloudAiplatformV1beta1PointwiseMetricSpec;
+      /** Spec for rouge metric. */
+      rougeSpec?: GoogleCloudAiplatformV1beta1RougeSpec;
+    }
     interface GoogleCloudAiplatformV1beta1MetricxInput {
       /** Required. Metricx instance. */
       instance?: GoogleCloudAiplatformV1beta1MetricxInstance;
@@ -4847,6 +4869,8 @@ declare namespace gapi.client {
       checkpointId?: string;
       /** The epoch of the checkpoint. */
       epoch?: string;
+      /** Identifier. The resource name of the ModelVersionCheckpoint. Format: `projects/{project}/locations/{location}/models/{model}/versions/{version}/checkpoints/{checkpoint}` */
+      name?: string;
       /** The step of the checkpoint. */
       step?: string;
     }
@@ -5277,6 +5301,10 @@ declare namespace gapi.client {
       /** Optional. Post startup script config. */
       postStartupScriptConfig?: GoogleCloudAiplatformV1beta1PostStartupScriptConfig;
     }
+    interface GoogleCloudAiplatformV1beta1OutputConfig {
+      /** Cloud storage destination for evaluation output. */
+      gcsDestination?: GoogleCloudAiplatformV1beta1GcsDestination;
+    }
     interface GoogleCloudAiplatformV1beta1PairwiseMetricInput {
       /** Required. Pairwise metric instance. */
       instance?: GoogleCloudAiplatformV1beta1PairwiseMetricInstance;
@@ -7717,7 +7745,7 @@ declare namespace gapi.client {
       displayName?: string;
     }
     interface GoogleCloudAiplatformV1beta1SchemaTextDataItem {
-      /** Output only. Google Cloud Storage URI points to the original text in user's bucket. The text file is up to 10MB in size. */
+      /** Output only. Google Cloud Storage URI points to a copy of the original text in the Vertex-managed bucket in the user's project. The text file is up to 10MB in size. */
       gcsUri?: string;
     }
     interface GoogleCloudAiplatformV1beta1SchemaTextDatasetMetadata {
@@ -36076,6 +36104,64 @@ declare namespace gapi.client {
         },
         body: GoogleCloudAiplatformV1beta1DeployPublisherModelRequest,
       ): Request<GoogleLongrunningOperation>;
+      /** Evaluates a dataset based on a set of given metrics. */
+      evaluateDataset(request: {
+        /** V1 error format. */
+        '$.xgafv'?: string;
+        /** OAuth access token. */
+        access_token?: string;
+        /** Data format for response. */
+        alt?: string;
+        /** JSONP */
+        callback?: string;
+        /** Selector specifying which fields to include in a partial response. */
+        fields?: string;
+        /** API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token. */
+        key?: string;
+        /** Required. The resource name of the Location to evaluate the dataset. Format: `projects/{project}/locations/{location}` */
+        location: string;
+        /** OAuth 2.0 token for the current user. */
+        oauth_token?: string;
+        /** Returns response with indentations and line breaks. */
+        prettyPrint?: boolean;
+        /** Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters. */
+        quotaUser?: string;
+        /** Upload protocol for media (e.g. "raw", "multipart"). */
+        upload_protocol?: string;
+        /** Legacy upload protocol for media (e.g. "media", "multipart"). */
+        uploadType?: string;
+        /** Request body */
+        resource: GoogleCloudAiplatformV1beta1EvaluateDatasetRequest;
+      }): Request<GoogleLongrunningOperation>;
+      evaluateDataset(
+        request: {
+          /** V1 error format. */
+          '$.xgafv'?: string;
+          /** OAuth access token. */
+          access_token?: string;
+          /** Data format for response. */
+          alt?: string;
+          /** JSONP */
+          callback?: string;
+          /** Selector specifying which fields to include in a partial response. */
+          fields?: string;
+          /** API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token. */
+          key?: string;
+          /** Required. The resource name of the Location to evaluate the dataset. Format: `projects/{project}/locations/{location}` */
+          location: string;
+          /** OAuth 2.0 token for the current user. */
+          oauth_token?: string;
+          /** Returns response with indentations and line breaks. */
+          prettyPrint?: boolean;
+          /** Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters. */
+          quotaUser?: string;
+          /** Upload protocol for media (e.g. "raw", "multipart"). */
+          upload_protocol?: string;
+          /** Legacy upload protocol for media (e.g. "media", "multipart"). */
+          uploadType?: string;
+        },
+        body: GoogleCloudAiplatformV1beta1EvaluateDatasetRequest,
+      ): Request<GoogleLongrunningOperation>;
       /** Evaluates instances based on a given metric. */
       evaluateInstances(request: {
         /** V1 error format. */

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@maxim_mazurok/gapi.client.aiplatform-v1beta1",
-  "version": "0.0.20250205",
+  "version": "0.0.20250212",
   "description": "TypeScript typings for Vertex AI API v1beta1",
   "repository": {
     "type": "git",