google-api-python-client 2.160.0__py2.py3-none-any.whl → 2.162.0__py2.py3-none-any.whl

googleapiclient/discovery_cache/documents/aiplatform.v1beta1.json

@@ -765,6 +765,35 @@
 "https://www.googleapis.com/auth/cloud-platform.read-only"
 ]
 },
+"predict": {
+"description": "Perform an online prediction.",
+"flatPath": "v1beta1/endpoints/{endpointsId}:predict",
+"httpMethod": "POST",
+"id": "aiplatform.endpoints.predict",
+"parameterOrder": [
+"endpoint"
+],
+"parameters": {
+"endpoint": {
+"description": "Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`",
+"location": "path",
+"pattern": "^endpoints/[^/]+$",
+"required": true,
+"type": "string"
+}
+},
+"path": "v1beta1/{+endpoint}:predict",
+"request": {
+"$ref": "GoogleCloudAiplatformV1beta1PredictRequest"
+},
+"response": {
+"$ref": "GoogleCloudAiplatformV1beta1PredictResponse"
+},
+"scopes": [
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+},
 "streamGenerateContent": {
 "description": "Generate content with multimodal inputs with streaming support.",
 "flatPath": "v1beta1/endpoints/{endpointsId}:streamGenerateContent",
@@ -983,6 +1012,34 @@
 "https://www.googleapis.com/auth/cloud-platform"
 ]
 },
+"evaluateDataset": {
+"description": "Evaluates a dataset based on a set of given metrics.",
+"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}:evaluateDataset",
+"httpMethod": "POST",
+"id": "aiplatform.projects.locations.evaluateDataset",
+"parameterOrder": [
+"location"
+],
+"parameters": {
+"location": {
+"description": "Required. The resource name of the Location to evaluate the dataset. Format: `projects/{project}/locations/{location}`",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+$",
+"required": true,
+"type": "string"
+}
+},
+"path": "v1beta1/{+location}:evaluateDataset",
+"request": {
+"$ref": "GoogleCloudAiplatformV1beta1EvaluateDatasetRequest"
+},
+"response": {
+"$ref": "GoogleLongrunningOperation"
+},
+"scopes": [
+"https://www.googleapis.com/auth/cloud-platform"
+]
+},
 "evaluateInstances": {
 "description": "Evaluates instances based on a given metric.",
 "flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}:evaluateInstances",
@@ -6294,7 +6351,7 @@
 "type": "string"
 },
 "updateMask": {
-"description": "Field mask is used to specify the fields to be overwritten in the FeatureGroup resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then only the non-empty fields present in the request will be overwritten. Set the update_mask to `*` to override all fields. Updatable fields: * `labels` * `description` * `big_query` * `big_query.entity_id_columns`",
+"description": "Field mask is used to specify the fields to be overwritten in the FeatureGroup resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then only the non-empty fields present in the request will be overwritten. Set the update_mask to `*` to override all fields. Updatable fields: * `labels` * `description` * `big_query` * `big_query.entity_id_columns` * `service_agent_type`",
 "format": "google-fieldmask",
 "location": "query",
 "type": "string"
@@ -6502,6 +6559,40 @@
 "scopes": [
 "https://www.googleapis.com/auth/cloud-platform"
 ]
+},
+"patch": {
+"description": "Updates the parameters of a single FeatureMonitor.",
+"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/featureGroups/{featureGroupsId}/featureMonitors/{featureMonitorsId}",
+"httpMethod": "PATCH",
+"id": "aiplatform.projects.locations.featureGroups.featureMonitors.patch",
+"parameterOrder": [
+"name"
+],
+"parameters": {
+"name": {
+"description": "Identifier. Name of the FeatureMonitor. Format: `projects/{project}/locations/{location}/featureGroups/{featureGroup}/featureMonitors/{featureMonitor}`",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+/featureGroups/[^/]+/featureMonitors/[^/]+$",
+"required": true,
+"type": "string"
+},
+"updateMask": {
+"description": "Optional. Field mask is used to specify the fields to be overwritten in the FeatureMonitor resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then only the non-empty fields present in the request will be overwritten. Set the update_mask to `*` to override all fields. Updatable fields: * `labels` * `description` * `schedule_config` * `feature_selection_config`",
+"format": "google-fieldmask",
+"location": "query",
+"type": "string"
+}
+},
+"path": "v1beta1/{+name}",
+"request": {
+"$ref": "GoogleCloudAiplatformV1beta1FeatureMonitor"
+},
+"response": {
+"$ref": "GoogleLongrunningOperation"
+},
+"scopes": [
+"https://www.googleapis.com/auth/cloud-platform"
+]
 }
 },
 "resources": {
@@ -10007,7 +10098,7 @@
 ]
 },
 "deployIndex": {
-"description": "Deploys an Index into this IndexEndpoint, creating a DeployedIndex within it. Only non-empty Indexes can be deployed.",
+"description": "Deploys an Index into this IndexEndpoint, creating a DeployedIndex within it.",
 "flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/indexEndpoints/{indexEndpointsId}:deployIndex",
 "httpMethod": "POST",
 "id": "aiplatform.projects.locations.indexEndpoints.deployIndex",
@@ -13781,6 +13872,42 @@
 "https://www.googleapis.com/auth/cloud-platform"
 ]
 },
+"listCheckpoints": {
+"description": "Lists checkpoints of the specified model version.",
+"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/models/{modelsId}:listCheckpoints",
+"httpMethod": "GET",
+"id": "aiplatform.projects.locations.models.listCheckpoints",
+"parameterOrder": [
+"name"
+],
+"parameters": {
+"name": {
+"description": "Required. The name of the model version to list checkpoints for. `projects/{project}/locations/{location}/models/{model}@{version}` Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` If no version ID or alias is specified, the latest version will be used.",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+/models/[^/]+$",
+"required": true,
+"type": "string"
+},
+"pageSize": {
+"description": "Optional. The standard list page size.",
+"format": "int32",
+"location": "query",
+"type": "integer"
+},
+"pageToken": {
+"description": "Optional. The standard list page token. Typically obtained via next_page_token of the previous ListModelVersionCheckpoints call.",
+"location": "query",
+"type": "string"
+}
+},
+"path": "v1beta1/{+name}:listCheckpoints",
+"response": {
+"$ref": "GoogleCloudAiplatformV1beta1ListModelVersionCheckpointsResponse"
+},
+"scopes": [
+"https://www.googleapis.com/auth/cloud-platform"
+]
+},
 "listVersions": {
 "description": "Lists versions of the specified model.",
 "flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/models/{modelsId}:listVersions",
@@ -21930,6 +22057,35 @@
 "https://www.googleapis.com/auth/cloud-platform"
 ]
 },
+"predict": {
+"description": "Perform an online prediction.",
+"flatPath": "v1beta1/publishers/{publishersId}/models/{modelsId}:predict",
+"httpMethod": "POST",
+"id": "aiplatform.publishers.models.predict",
+"parameterOrder": [
+"endpoint"
+],
+"parameters": {
+"endpoint": {
+"description": "Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`",
+"location": "path",
+"pattern": "^publishers/[^/]+/models/[^/]+$",
+"required": true,
+"type": "string"
+}
+},
+"path": "v1beta1/{+endpoint}:predict",
+"request": {
+"$ref": "GoogleCloudAiplatformV1beta1PredictRequest"
+},
+"response": {
+"$ref": "GoogleCloudAiplatformV1beta1PredictResponse"
+},
+"scopes": [
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+},
 "streamGenerateContent": {
 "description": "Generate content with multimodal inputs with streaming support.",
 "flatPath": "v1beta1/publishers/{publishersId}/models/{modelsId}:streamGenerateContent",
@@ -21964,7 +22120,7 @@
 }
 }
 },
-"revision": "20250114",
+"revision": "20250212",
 "rootUrl": "https://aiplatform.googleapis.com/",
 "schemas": {
 "CloudAiLargeModelsVisionGenerateVideoResponse": {
@@ -22968,12 +23124,32 @@
 "id": "GoogleCloudAiplatformV1beta1AutomaticResources",
 "properties": {
 "maxReplicaCount": {
-"description": "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.",
+"description": "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.",
 "format": "int32",
 "type": "integer"
 },
 "minReplicaCount": {
-"description": "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.",
+"description": "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.",
+"format": "int32",
+"type": "integer"
+}
+},
+"type": "object"
+},
+"GoogleCloudAiplatformV1beta1AutoraterConfig": {
+"description": "The configs for autorater. This is applicable to both EvaluateInstances and EvaluateDataset.",
+"id": "GoogleCloudAiplatformV1beta1AutoraterConfig",
+"properties": {
+"autoraterModel": {
+"description": "Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`",
+"type": "string"
+},
+"flipEnabled": {
+"description": "Optional. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.",
+"type": "boolean"
+},
+"samplingCount": {
+"description": "Optional. Number of samples for each instance in the dataset. If not specified, the default is 4. Minimum value is 1, maximum value is 32.",
 "format": "int32",
 "type": "integer"
 }
@@ -23789,6 +23965,10 @@
 "format": "byte",
 "type": "string"
 },
+"displayName": {
+"description": "Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is not currently used in the Gemini GenerateContent calls.",
+"type": "string"
+},
 "mimeType": {
 "description": "Required. The IANA standard MIME type of the source data.",
 "type": "string"
@@ -23849,7 +24029,7 @@
 "type": "array"
 },
 "createTime": {
-"description": "Output only. Creatation time of the cache entry.",
+"description": "Output only. Creation time of the cache entry.",
 "format": "google-datetime",
 "readOnly": true,
 "type": "string"
@@ -23864,7 +24044,7 @@
 "type": "string"
 },
 "model": {
-"description": "Immutable. The name of the publisher model to use for cached content. Format: projects/{project}/locations/{location}/publishers/{publisher}/models/{model}",
+"description": "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}",
 "type": "string"
 },
 "name": {
@@ -24753,6 +24933,14 @@
 "description": "Response message for PredictionService.CountTokens.",
 "id": "GoogleCloudAiplatformV1beta1CountTokensResponse",
 "properties": {
+"promptTokensDetails": {
+"description": "Output only. List of modalities that were processed in the request input.",
+"items": {
+"$ref": "GoogleCloudAiplatformV1beta1ModalityTokenCount"
+},
+"readOnly": true,
+"type": "array"
+},
 "totalBillableCharacters": {
 "description": "The total number of billable characters counted across all instances from the request.",
 "format": "int32",
@@ -25840,7 +26028,7 @@
 "type": "object"
 },
 "GoogleCloudAiplatformV1beta1DedicatedResources": {
-"description": "A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration.",
+"description": "A description of resources that are dedicated to a DeployedModel or DeployedIndex, and that need a higher degree of manual configuration.",
 "id": "GoogleCloudAiplatformV1beta1DedicatedResources",
 "properties": {
 "autoscalingMetricSpecs": {
@@ -25852,20 +26040,20 @@
 },
 "machineSpec": {
 "$ref": "GoogleCloudAiplatformV1beta1MachineSpec",
-"description": "Required. Immutable. The specification of a single machine used by the prediction."
+"description": "Required. Immutable. The specification of a single machine being used."
 },
 "maxReplicaCount": {
-"description": "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).",
+"description": "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).",
 "format": "int32",
 "type": "integer"
 },
 "minReplicaCount": {
-"description": "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.",
+"description": "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.",
 "format": "int32",
 "type": "integer"
 },
 "requiredReplicaCount": {
-"description": "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.",
+"description": "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.",
 "format": "int32",
 "type": "integer"
 },
@@ -26107,7 +26295,7 @@
 "type": "string"
 },
 "model": {
-"description": "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`.",
+"description": "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`.",
 "type": "string"
 },
 "modelDisplayName": {
@@ -26310,6 +26498,10 @@
 "description": "Output only. Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.",
 "readOnly": true
 },
+"rolloutOptions": {
+"$ref": "GoogleCloudAiplatformV1beta1RolloutOptions",
+"description": "Options for configuring rolling deployments."
+},
 "serviceAccount": {
 "description": "The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the `iam.serviceAccounts.actAs` permission on this service account.",
 "type": "string"
@@ -26318,6 +26510,10 @@
 "description": "The resource name of the shared DeploymentResourcePool to deploy on. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`",
 "type": "string"
 },
+"speculativeDecodingSpec": {
+"$ref": "GoogleCloudAiplatformV1beta1SpeculativeDecodingSpec",
+"description": "Optional. Spec for configuring speculative decoding."
+},
 "status": {
 "$ref": "GoogleCloudAiplatformV1beta1DeployedModelStatus",
 "description": "Output only. Runtime status of the deployed model.",
@@ -26704,6 +26900,10 @@
 "description": "Used to perform consistent read-modify-write updates. If not set, a blind \"overwrite\" update happens.",
 "type": "string"
 },
+"genAiAdvancedFeaturesConfig": {
+"$ref": "GoogleCloudAiplatformV1beta1GenAiAdvancedFeaturesConfig",
+"description": "Optional. Configuration for GenAiAdvancedFeatures. If the endpoint is serving GenAI models, advanced features like native RAG integration can be configured. Currently, only Model Garden models are supported."
+},
 "labels": {
 "additionalProperties": {
 "type": "string"
@@ -26903,10 +27103,40 @@
 },
 "type": "object"
 },
+"GoogleCloudAiplatformV1beta1EvaluateDatasetRequest": {
+"description": "Request message for EvaluationService.EvaluateDataset.",
+"id": "GoogleCloudAiplatformV1beta1EvaluateDatasetRequest",
+"properties": {
+"autoraterConfig": {
+"$ref": "GoogleCloudAiplatformV1beta1AutoraterConfig",
+"description": "Optional. Autorater config used for evaluation."
+},
+"dataset": {
+"$ref": "GoogleCloudAiplatformV1beta1EvaluationDataset",
+"description": "Required. The dataset used for evaluation."
+},
+"metrics": {
+"description": "Required. The metrics used for evaluation.",
+"items": {
+"$ref": "GoogleCloudAiplatformV1beta1Metric"
+},
+"type": "array"
+},
+"outputConfig": {
+"$ref": "GoogleCloudAiplatformV1beta1OutputConfig",
+"description": "Required. Config for evaluation output."
+}
+},
+"type": "object"
+},
 "GoogleCloudAiplatformV1beta1EvaluateInstancesRequest": {
 "description": "Request message for EvaluationService.EvaluateInstances.",
 "id": "GoogleCloudAiplatformV1beta1EvaluateInstancesRequest",
 "properties": {
+"autoraterConfig": {
+"$ref": "GoogleCloudAiplatformV1beta1AutoraterConfig",
+"description": "Optional. Autorater config used for evaluation."
+},
 "bleuInput": {
 "$ref": "GoogleCloudAiplatformV1beta1BleuInput",
 "description": "Instances and metric spec for bleu metric."
@@ -27244,6 +27474,21 @@
 },
 "type": "object"
 },
+"GoogleCloudAiplatformV1beta1EvaluationDataset": {
+"description": "The dataset used for evaluation.",
+"id": "GoogleCloudAiplatformV1beta1EvaluationDataset",
+"properties": {
+"bigquerySource": {
+"$ref": "GoogleCloudAiplatformV1beta1BigQuerySource",
+"description": "BigQuery source holds the dataset."
+},
+"gcsSource": {
+"$ref": "GoogleCloudAiplatformV1beta1GcsSource",
+"description": "Cloud storage source holds the dataset."
+}
+},
+"type": "object"
+},
 "GoogleCloudAiplatformV1beta1Event": {
 "description": "An edge describing the relationship between an Artifact and an Execution in a lineage graph.",
 "id": "GoogleCloudAiplatformV1beta1Event",
@@ -30055,6 +30300,10 @@
 "description": "URI based data.",
 "id": "GoogleCloudAiplatformV1beta1FileData",
 "properties": {
+"displayName": {
+"description": "Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is not currently used in the Gemini GenerateContent calls.",
+"type": "string"
+},
 "fileUri": {
 "description": "Required. URI.",
 "type": "string"
@@ -30500,6 +30749,28 @@
 },
 "type": "object"
 },
+"GoogleCloudAiplatformV1beta1GenAiAdvancedFeaturesConfig": {
+"description": "Configuration for GenAiAdvancedFeatures.",
+"id": "GoogleCloudAiplatformV1beta1GenAiAdvancedFeaturesConfig",
+"properties": {
+"ragConfig": {
+"$ref": "GoogleCloudAiplatformV1beta1GenAiAdvancedFeaturesConfigRagConfig",
+"description": "Configuration for Retrieval Augmented Generation feature."
+}
+},
+"type": "object"
+},
+"GoogleCloudAiplatformV1beta1GenAiAdvancedFeaturesConfigRagConfig": {
+"description": "Configuration for Retrieval Augmented Generation feature.",
+"id": "GoogleCloudAiplatformV1beta1GenAiAdvancedFeaturesConfigRagConfig",
+"properties": {
+"enableRag": {
+"description": "If true, enable Retrieval Augmented Generation in ChatCompletion request. Once enabled, the endpoint will be identified as GenAI endpoint and Arthedain router will be used.",
+"type": "boolean"
+}
+},
+"type": "object"
+},
 "GoogleCloudAiplatformV1beta1GenerateAccessTokenRequest": {
 "description": "Request message for NotebookInternalService.GenerateAccessToken.",
 "id": "GoogleCloudAiplatformV1beta1GenerateAccessTokenRequest",
@@ -30598,6 +30869,12 @@
 "readOnly": true,
 "type": "array"
 },
+"createTime": {
+"description": "Output only. Timestamp when the request is made to the server.",
+"format": "google-datetime",
+"readOnly": true,
+"type": "string"
+},
 "modelVersion": {
 "description": "Output only. The model version used to generate the response.",
 "readOnly": true,
@@ -30608,6 +30885,11 @@
 "description": "Output only. Content filter results for a prompt sent in the request. Note: Sent only in the first stream chunk. Only happens when no candidates were generated due to content violations.",
 "readOnly": true
 },
+"responseId": {
+"description": "Output only. response_id is used to identify each response. It is the encoding of the event_id.",
+"readOnly": true,
+"type": "string"
+},
 "usageMetadata": {
 "$ref": "GoogleCloudAiplatformV1beta1GenerateContentResponseUsageMetadata",
 "description": "Usage metadata about the response(s)."
@@ -30658,6 +30940,14 @@
 "description": "Usage metadata about response(s).",
 "id": "GoogleCloudAiplatformV1beta1GenerateContentResponseUsageMetadata",
 "properties": {
+"cacheTokensDetails": {
+"description": "Output only. List of modalities of the cached content in the request input.",
+"items": {
+"$ref": "GoogleCloudAiplatformV1beta1ModalityTokenCount"
+},
+"readOnly": true,
+"type": "array"
+},
 "cachedContentTokenCount": {
 "description": "Output only. Number of tokens in the cached part in the input (the cached content).",
 "format": "int32",
@@ -30669,11 +30959,27 @@
 "format": "int32",
 "type": "integer"
 },
+"candidatesTokensDetails": {
+"description": "Output only. List of modalities that were returned in the response.",
+"items": {
+"$ref": "GoogleCloudAiplatformV1beta1ModalityTokenCount"
+},
+"readOnly": true,
+"type": "array"
+},
 "promptTokenCount": {
 "description": "Number of tokens in the request. When `cached_content` is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.",
 "format": "int32",
 "type": "integer"
 },
+"promptTokensDetails": {
+"description": "Output only. List of modalities that were processed in the request input.",
+"items": {
+"$ref": "GoogleCloudAiplatformV1beta1ModalityTokenCount"
+},
+"readOnly": true,
+"type": "array"
+},
 "totalTokenCount": {
 "description": "Total token count for prompt and response candidates.",
 "format": "int32",
@@ -32778,6 +33084,24 @@
 },
 "type": "object"
 },
+"GoogleCloudAiplatformV1beta1ListModelVersionCheckpointsResponse": {
+"description": "Response message for ModelService.ListModelVersionCheckpoints",
+"id": "GoogleCloudAiplatformV1beta1ListModelVersionCheckpointsResponse",
+"properties": {
+"checkpoints": {
+"description": "List of Model Version checkpoints.",
+"items": {
+"$ref": "GoogleCloudAiplatformV1beta1ModelVersionCheckpoint"
+},
+"type": "array"
+},
+"nextPageToken": {
+"description": "A token to retrieve the next page of results. Pass to ListModelVersionCheckpointsRequest.page_token to obtain that page.",
+"type": "string"
+}
+},
+"type": "object"
+},
 "GoogleCloudAiplatformV1beta1ListModelVersionsResponse": {
 "description": "Response message for ModelService.ListModelVersions",
 "id": "GoogleCloudAiplatformV1beta1ListModelVersionsResponse",
@@ -33556,6 +33880,66 @@ false
 },
 "type": "object"
 },
+"GoogleCloudAiplatformV1beta1Metric": {
+"description": "The metric used for dataset level evaluation.",
+"id": "GoogleCloudAiplatformV1beta1Metric",
+"properties": {
+"aggregationMetrics": {
+"description": "Optional. The aggregation metrics to use.",
+"items": {
+"enum": [
+"AGGREGATION_METRIC_UNSPECIFIED",
+"AVERAGE",
+"MODE",
+"STANDARD_DEVIATION",
+"VARIANCE",
+"MINIMUM",
+"MAXIMUM",
+"MEDIAN",
+"PERCENTILE_P90",
+"PERCENTILE_P95",
+"PERCENTILE_P99"
+],
+"enumDescriptions": [
+"Unspecified aggregation metric.",
+"Average aggregation metric.",
+"Mode aggregation metric.",
+"Standard deviation aggregation metric.",
+"Variance aggregation metric.",
+"Minimum aggregation metric.",
+"Maximum aggregation metric.",
+"Median aggregation metric.",
+"90th percentile aggregation metric.",
+"95th percentile aggregation metric.",
+"99th percentile aggregation metric."
+],
+"type": "string"
+},
+"type": "array"
+},
+"bleuSpec": {
+"$ref": "GoogleCloudAiplatformV1beta1BleuSpec",
+"description": "Spec for bleu metric."
+},
+"exactMatchSpec": {
+"$ref": "GoogleCloudAiplatformV1beta1ExactMatchSpec",
+"description": "Spec for exact match metric."
+},
+"pairwiseMetricSpec": {
+"$ref": "GoogleCloudAiplatformV1beta1PairwiseMetricSpec",
+"description": "Spec for pairwise metric."
+},
+"pointwiseMetricSpec": {
+"$ref": "GoogleCloudAiplatformV1beta1PointwiseMetricSpec",
+"description": "Spec for pointwise metric."
+},
+"rougeSpec": {
+"$ref": "GoogleCloudAiplatformV1beta1RougeSpec",
+"description": "Spec for rouge metric."
+}
+},
+"type": "object"
+},
 "GoogleCloudAiplatformV1beta1MetricxInput": {
 "description": "Input for MetricX metric.",
 "id": "GoogleCloudAiplatformV1beta1MetricxInput",
@@ -33879,6 +34263,38 @@ false
 },
 "type": "object"
 },
+"GoogleCloudAiplatformV1beta1ModalityTokenCount": {
+"description": "Represents token counting info for a single modality.",
+"id": "GoogleCloudAiplatformV1beta1ModalityTokenCount",
+"properties": {
+"modality": {
+"description": "The modality associated with this token count.",
+"enum": [
+"MODALITY_UNSPECIFIED",
+"TEXT",
+"IMAGE",
+"VIDEO",
+"AUDIO",
+"DOCUMENT"
+],
+"enumDescriptions": [
+"Unspecified modality.",
+"Plain text.",
+"Image.",
+"Video.",
+"Audio.",
+"Document, e.g. PDF."
+],
+"type": "string"
+},
+"tokenCount": {
+"description": "Number of tokens.",
+"format": "int32",
+"type": "integer"
+}
+},
+"type": "object"
+},
 "GoogleCloudAiplatformV1beta1Model": {
 "description": "A trained machine learning Model.",
 "id": "GoogleCloudAiplatformV1beta1Model",
@@ -33901,6 +34317,10 @@ false
 "readOnly": true,
 "type": "string"
 },
+"defaultCheckpointId": {
+"description": "The default checkpoint id of a model version.",
+"type": "string"
+},
 "deployedModels": {
 "description": "Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.",
 "items": {
@@ -34669,7 +35089,7 @@ false
 "type": "array"
 },
 "id": {
-"description": "Output only. The ID of the export format. The possible format IDs are: * `tflite` Used for Android mobile devices. * `edgetpu-tflite` Used for [Edge TPU](https://cloud.google.com/edge-tpu/) devices. * `tf-saved-model` A tensorflow model in SavedModel format. * `tf-js` A [TensorFlow.js](https://www.tensorflow.org/js) model that can be used in the browser and in Node.js using JavaScript. * `core-ml` Used for iOS mobile devices. * `custom-trained` A Model that was uploaded or trained by custom code.",
+"description": "Output only. The ID of the export format. The possible format IDs are: * `tflite` Used for Android mobile devices. * `edgetpu-tflite` Used for [Edge TPU](https://cloud.google.com/edge-tpu/) devices. * `tf-saved-model` A tensorflow model in SavedModel format. * `tf-js` A [TensorFlow.js](https://www.tensorflow.org/js) model that can be used in the browser and in Node.js using JavaScript. * `core-ml` Used for iOS mobile devices. * `custom-trained` A Model that was uploaded or trained by custom code. * `genie` A tuned Model Garden model.",
 "readOnly": true,
 "type": "string"
 }
@@ -34683,6 +35103,14 @@ false
 "publicModelName": {
 "description": "Required. The model garden source model resource name.",
 "type": "string"
+},
+"skipHfModelCache": {
+"description": "Optional. Whether to avoid pulling the model from the HF cache.",
+"type": "boolean"
+},
+"versionId": {
+"description": "Optional. The model garden source model version ID.",
+"type": "string"
 }
 },
 "type": "object"
@@ -35783,6 +36211,31 @@ false
 },
 "type": "object"
 },
+"GoogleCloudAiplatformV1beta1ModelVersionCheckpoint": {
+"description": "Describes the machine learning model version checkpoint.",
+"id": "GoogleCloudAiplatformV1beta1ModelVersionCheckpoint",
+"properties": {
+"checkpointId": {
+"description": "The ID of the checkpoint.",
+"type": "string"
+},
+"epoch": {
+"description": "The epoch of the checkpoint.",
+"format": "int64",
+"type": "string"
+},
+"name": {
+"description": "Identifier. The resource name of the ModelVersionCheckpoint. Format: `projects/{project}/locations/{location}/models/{model}/versions/{version}/checkpoints/{checkpoint}`",
+"type": "string"
+},
+"step": {
+"description": "The step of the checkpoint.",
+"format": "int64",
+"type": "string"
+}
+},
+"type": "object"
+},
 "GoogleCloudAiplatformV1beta1MutateDeployedIndexOperationMetadata": {
 "description": "Runtime operation information for IndexEndpointService.MutateDeployedIndex.",
 "id": "GoogleCloudAiplatformV1beta1MutateDeployedIndexOperationMetadata",
@@ -36945,6 +37398,11 @@ false
 "description": "Output only. Runtime Shielded VM spec.",
 "readOnly": true
 },
+"softwareConfig": {
+"$ref": "GoogleCloudAiplatformV1beta1NotebookSoftwareConfig",
+"description": "Output only. Software config of the notebook runtime.",
+"readOnly": true
+},
 "updateTime": {
 "description": "Output only. Timestamp when this NotebookRuntime was most recently updated.",
 "format": "google-datetime",
@@ -37052,6 +37510,10 @@ false
 "$ref": "GoogleCloudAiplatformV1beta1ShieldedVmConfig",
 "description": "Optional. Immutable. Runtime Shielded VM spec."
 },
+"softwareConfig": {
+"$ref": "GoogleCloudAiplatformV1beta1NotebookSoftwareConfig",
+"description": "Optional. The notebook software configuration of the notebook runtime."
+},
 "updateTime": {
 "description": "Output only. Timestamp when this NotebookRuntimeTemplate was most recently updated.",
 "format": "google-datetime",
@@ -37072,6 +37534,35 @@ false
 },
 "type": "object"
 },
+"GoogleCloudAiplatformV1beta1NotebookSoftwareConfig": {
+"description": "Notebook Software Config.",
+"id": "GoogleCloudAiplatformV1beta1NotebookSoftwareConfig",
+"properties": {
+"env": {
+"description": "Optional. Environment variables to be passed to the container. Maximum limit is 100.",
+"items": {
+"$ref": "GoogleCloudAiplatformV1beta1EnvVar"
+},
+"type": "array"
+},
+"postStartupScriptConfig": {
+"$ref": "GoogleCloudAiplatformV1beta1PostStartupScriptConfig",
+"description": "Optional. Post startup script config."
+}
+},
+"type": "object"
+},
+"GoogleCloudAiplatformV1beta1OutputConfig": {
+"description": "Config for evaluation output.",
+"id": "GoogleCloudAiplatformV1beta1OutputConfig",
+"properties": {
+"gcsDestination": {
+"$ref": "GoogleCloudAiplatformV1beta1GcsDestination",
+"description": "Cloud storage destination for evaluation output."
+}
+},
+"type": "object"
+},
 "GoogleCloudAiplatformV1beta1PSCAutomationConfig": {
 "description": "PSC config that is used to automatically create forwarding rule via ServiceConnectionMap.",
 "id": "GoogleCloudAiplatformV1beta1PSCAutomationConfig",
@@ -37146,9 +37637,21 @@ false
 "description": "Spec for pairwise metric.",
 "id": "GoogleCloudAiplatformV1beta1PairwiseMetricSpec",
 "properties": {
+"baselineResponseFieldName": {
+"description": "Optional. The field name of the baseline response.",
+"type": "string"
+},
+"candidateResponseFieldName": {
+"description": "Optional. The field name of the candidate response.",
+"type": "string"
+},
 "metricPromptTemplate": {
 "description": "Required. Metric prompt template for pairwise metric.",
 "type": "string"
+},
+"systemInstruction": {
+"description": "Optional. System instructions for pairwise metric.",
+"type": "string"
 }
 },
 "type": "object"
@@ -38200,6 +38703,10 @@ false
 "metricPromptTemplate": {
 "description": "Required. Metric prompt template for pointwise metric.",
 "type": "string"
+},
+"systemInstruction": {
+"description": "Optional. System instructions for pointwise metric.",
+"type": "string"
 }
 },
 "type": "object"
@@ -38216,6 +38723,37 @@ false
 },
 "type": "object"
 },
+"GoogleCloudAiplatformV1beta1PostStartupScriptConfig": {
+"description": "Post startup script config.",
+"id": "GoogleCloudAiplatformV1beta1PostStartupScriptConfig",
+"properties": {
+"postStartupScript": {
+"description": "Optional. Post startup script to run after runtime is started.",
+"type": "string"
+},
+"postStartupScriptBehavior": {
+"description": "Optional. Post startup script behavior that defines download and execution behavior.",
+"enum": [
+"POST_STARTUP_SCRIPT_BEHAVIOR_UNSPECIFIED",
+"RUN_ONCE",
+"RUN_EVERY_START",
+"DOWNLOAD_AND_RUN_EVERY_START"
+],
+"enumDescriptions": [
+"Unspecified post startup script behavior.",
+"Run post startup script after runtime is started.",
+"Run post startup script after runtime is stopped.",
+"Download and run post startup script every time runtime is started."
+],
+"type": "string"
+},
+"postStartupScriptUrl": {
+"description": "Optional. Post startup script url to download. Example: https://bucket/script.sh",
+"type": "string"
+}
+},
+"type": "object"
+},
 "GoogleCloudAiplatformV1beta1PrebuiltVoiceConfig": {
 "description": "The configuration for the prebuilt speaker to use.",
 "id": "GoogleCloudAiplatformV1beta1PrebuiltVoiceConfig",
@@ -38465,6 +39003,11 @@ false
 "$ref": "GoogleCloudAiplatformV1beta1ProbeExecAction",
 "description": "ExecAction probes the health of a container by executing a command."
 },
+"failureThreshold": {
+"description": "Number of consecutive failures before the probe is considered failed. Defaults to 3. Minimum value is 1. Maps to Kubernetes probe argument 'failureThreshold'.",
+"format": "int32",
+"type": "integer"
+},
 "grpc": {
 "$ref": "GoogleCloudAiplatformV1beta1ProbeGrpcAction",
 "description": "GrpcAction probes the health of a container by sending a gRPC request."
@@ -38473,11 +39016,21 @@ false
 "$ref": "GoogleCloudAiplatformV1beta1ProbeHttpGetAction",
 "description": "HttpGetAction probes the health of a container by sending an HTTP GET request."
 },
+"initialDelaySeconds": {
+"description": "Number of seconds to wait before starting the probe. Defaults to 0. Minimum value is 0. Maps to Kubernetes probe argument 'initialDelaySeconds'.",
+"format": "int32",
+"type": "integer"
+},
 "periodSeconds": {
 "description": "How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.",
 "format": "int32",
 "type": "integer"
 },
+"successThreshold": {
+"description": "Number of consecutive successes before the probe is considered successful. Defaults to 1. Minimum value is 1. Maps to Kubernetes probe argument 'successThreshold'.",
+"format": "int32",
+"type": "integer"
+},
 "tcpSocket": {
 "$ref": "GoogleCloudAiplatformV1beta1ProbeTcpSocketAction",
 "description": "TcpSocketAction probes the health of a container by opening a TCP socket connection."
@@ -39660,6 +40213,12 @@ false
 "deprecated": true,
 "description": "Optional. Immutable. The embedding model config of the RagCorpus."
 },
+"ragFilesCount": {
+"description": "Output only. Number of RagFiles in the RagCorpus.",
+"format": "int32",
+"readOnly": true,
+"type": "integer"
+},
 "ragVectorDbConfig": {
 "$ref": "GoogleCloudAiplatformV1beta1RagVectorDbConfig",
 "deprecated": true,
@@ -39955,7 +40514,7 @@ false
 "type": "integer"
 },
 "modelName": {
-"description": "The name of a LLM model used for parsing. Format: `gemini-1.5-pro-002`",
+"description": "The name of a LLM model used for parsing. Format: * `projects/{project_id}/locations/{location}/publishers/{publisher}/models/{model}`",
 "type": "string"
 }
 },
@@ -41016,6 +41575,43 @@ false
 },
 "type": "object"
 },
+"GoogleCloudAiplatformV1beta1RolloutOptions": {
+"description": "Configuration for rolling deployments.",
+"id": "GoogleCloudAiplatformV1beta1RolloutOptions",
+"properties": {
+"maxSurgePercentage": {
+"description": "Percentage of allowed additional replicas. For autoscaling deployments, this refers to the target replica count.",
+"format": "int32",
+"type": "integer"
+},
+"maxSurgeReplicas": {
+"description": "Absolute count of allowed additional replicas.",
+"format": "int32",
+"type": "integer"
+},
+"maxUnavailablePercentage": {
+"description": "Percentage of replicas allowed to be unavailable. For autoscaling deployments, this refers to the target replica count.",
+"format": "int32",
+"type": "integer"
+},
+"maxUnavailableReplicas": {
+"description": "Absolute count of replicas allowed to be unavailable.",
+"format": "int32",
+"type": "integer"
+},
+"previousDeployedModel": {
+"description": "ID of the DeployedModel that this deployment should replace.",
+"type": "string"
+},
+"revisionNumber": {
+"description": "Output only. Read-only. Revision number determines the relative priority of DeployedModels in the same rollout. The DeployedModel with the largest revision number specifies the intended state of the deployment.",
+"format": "int32",
+"readOnly": true,
+"type": "integer"
+}
+},
+"type": "object"
+},
 "GoogleCloudAiplatformV1beta1RougeInput": {
 "description": "Input for rouge metric.",
 "id": "GoogleCloudAiplatformV1beta1RougeInput",
@@ -44028,7 +44624,7 @@ false
 "id": "GoogleCloudAiplatformV1beta1SchemaTextDataItem",
 "properties": {
 "gcsUri": {
-"description": "Output only. Google Cloud Storage URI points to the original text in user's bucket. The text file is up to 10MB in size.",
+"description": "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.",
 "readOnly": true,
 "type": "string"
 }
@@ -46531,6 +47127,49 @@ false
 },
 "type": "object"
 },
+"GoogleCloudAiplatformV1beta1SpeculativeDecodingSpec": {
+"description": "Configuration for Speculative Decoding.",
+"id": "GoogleCloudAiplatformV1beta1SpeculativeDecodingSpec",
+"properties": {
+"draftModelSpeculation": {
+"$ref": "GoogleCloudAiplatformV1beta1SpeculativeDecodingSpecDraftModelSpeculation",
+"description": "draft model speculation."
+},
+"ngramSpeculation": {
+"$ref": "GoogleCloudAiplatformV1beta1SpeculativeDecodingSpecNgramSpeculation",
+"description": "N-Gram speculation."
+},
+"speculativeTokenCount": {
+"description": "The number of speculative tokens to generate at each step.",
+"format": "int32",
+"type": "integer"
+}
+},
+"type": "object"
+},
+"GoogleCloudAiplatformV1beta1SpeculativeDecodingSpecDraftModelSpeculation": {
+"description": "Draft model speculation works by using the smaller model to generate candidate tokens for speculative decoding.",
+"id": "GoogleCloudAiplatformV1beta1SpeculativeDecodingSpecDraftModelSpeculation",
+"properties": {
+"draftModel": {
+"description": "Required. The resource name of the draft model.",
+"type": "string"
+}
+},
+"type": "object"
+},
+"GoogleCloudAiplatformV1beta1SpeculativeDecodingSpecNgramSpeculation": {
+"description": "N-Gram speculation works by trying to find matching tokens in the previous prompt sequence and use those as speculation for generating new tokens.",
+"id": "GoogleCloudAiplatformV1beta1SpeculativeDecodingSpecNgramSpeculation",
+"properties": {
+"ngramSize": {
+"description": "The number of last N input tokens used as ngram to search/match against the previous prompt sequence. This is equal to the N in N-Gram. The default value is 3 if not specified.",
+"format": "int32",
+"type": "integer"
+}
+},
+"type": "object"
+},
 "GoogleCloudAiplatformV1beta1SpeechConfig": {
 "description": "The speech generation config.",
 "id": "GoogleCloudAiplatformV1beta1SpeechConfig",
@@ -49529,7 +50168,7 @@ false
 "type": "object"
 },
 "GoogleCloudAiplatformV1beta1TunedModel": {
-"description": "The Model Registry Model and Online Prediction Endpoint assiociated with this TuningJob.",
+"description": "The Model Registry Model and Online Prediction Endpoint associated with this TuningJob.",
 "id": "GoogleCloudAiplatformV1beta1TunedModel",
 "properties": {
 "endpoint": {
@@ -49693,7 +50332,7 @@ false
 },
 "tunedModel": {
 "$ref": "GoogleCloudAiplatformV1beta1TunedModel",
-"description": "Output only. The tuned model resources assiociated with this TuningJob.",
+"description": "Output only. The tuned model resources associated with this TuningJob.",
 "readOnly": true
 },
 "tunedModelDisplayName": {