Skip to main content

endpoints

Creates, updates, deletes, gets or lists a endpoints resource.

Overview

Nameendpoints
TypeResource
Idgoogle.aiplatform.endpoints

Fields

NameDatatypeDescription
namestringOutput only. The resource name of the Endpoint.
descriptionstringThe description of the Endpoint.
createTimestringOutput only. Timestamp when this Endpoint was created.
dedicatedEndpointDnsstringOutput only. DNS of the dedicated endpoint. Will only be populated if dedicated_endpoint_enabled is true. Format: https://{endpoint_id}.{region}-{project_number}.prediction.vertexai.goog.
dedicatedEndpointEnabledbooleanIf true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
deployedModelsarrayOutput only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
displayNamestringRequired. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
enablePrivateServiceConnectbooleanDeprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.
encryptionSpecobjectRepresents a customer-managed encryption key spec that can be applied to a top-level resource.
etagstringUsed to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
labelsobjectThe labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
modelDeploymentMonitoringJobstringOutput only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
networkstringOptional. The full name of the Google Compute Engine network to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. Format: projects/{project}/global/networks/{network}. Where {project} is a project number, as in 12345, and {network} is network name.
predictRequestResponseLoggingConfigobjectConfiguration for logging request-response to a BigQuery table.
privateServiceConnectConfigobjectRepresents configuration for private service connect.
satisfiesPzibooleanOutput only. Reserved for future use.
satisfiesPzsbooleanOutput only. Reserved for future use.
trafficSplitobjectA 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.
updateTimestringOutput only. Timestamp when this Endpoint was last updated.

Methods

NameAccessible byRequired ParamsDescription
getSELECTendpointsId, locationsId, projectsIdGets an Endpoint.
listSELECTlocationsId, projectsIdLists Endpoints in a Location.
createINSERTlocationsId, projectsIdCreates an Endpoint.
deleteDELETEendpointsId, locationsId, projectsIdDeletes an Endpoint.
patchUPDATEendpointsId, locationsId, projectsIdUpdates an Endpoint.
compute_tokensEXECendpointsId, locationsId, projectsIdReturn a list of tokens based on the input text.
count_tokensEXECendpointsId, locationsId, projectsIdPerform a token counting.
deploy_modelEXECendpointsId, locationsId, projectsIdDeploys a Model into this Endpoint, creating a DeployedModel within it.
direct_predictEXECendpointsId, locationsId, projectsIdPerform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks.
direct_raw_predictEXECendpointsId, locationsId, projectsIdPerform an unary online prediction request to a gRPC model server for custom containers.
explainEXECendpointsId, locationsId, projectsIdPerform an online explanation. If deployed_model_id is specified, the corresponding DeployModel must have explanation_spec populated. If deployed_model_id is not specified, all DeployedModels must have explanation_spec populated.
generate_contentEXECendpointsId, locationsId, projectsIdGenerate content with multimodal inputs.
mutate_deployed_modelEXECendpointsId, locationsId, projectsIdUpdates an existing deployed model. Updatable fields include min_replica_count, max_replica_count, autoscaling_metric_specs, disable_container_logging (v1 only), and enable_container_logging (v1beta1 only).
predictEXECendpointsId, locationsId, projectsIdPerform an online prediction.
raw_predictEXECendpointsId, locationsId, projectsIdPerform an online prediction with an arbitrary HTTP payload. The response includes the following HTTP headers: X-Vertex-AI-Endpoint-Id: ID of the Endpoint that served this prediction. X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint's DeployedModel that served this prediction.
server_streaming_predictEXECendpointsId, locationsId, projectsIdPerform a server-side streaming online prediction request for Vertex LLM streaming.
stream_generate_contentEXECendpointsId, locationsId, projectsIdGenerate content with multimodal inputs with streaming support.
stream_raw_predictEXECendpointsId, locationsId, projectsIdPerform a streaming online prediction with an arbitrary HTTP payload.
undeploy_modelEXECendpointsId, locationsId, projectsIdUndeploys a Model from an Endpoint, removing a DeployedModel from it, and freeing all resources it's using.

SELECT examples

Lists Endpoints in a Location.

SELECT
name,
description,
createTime,
dedicatedEndpointDns,
dedicatedEndpointEnabled,
deployedModels,
displayName,
enablePrivateServiceConnect,
encryptionSpec,
etag,
labels,
modelDeploymentMonitoringJob,
network,
predictRequestResponseLoggingConfig,
privateServiceConnectConfig,
satisfiesPzi,
satisfiesPzs,
trafficSplit,
updateTime
FROM google.aiplatform.endpoints
WHERE locationsId = '{{ locationsId }}'
AND projectsId = '{{ projectsId }}';

INSERT example

Use the following StackQL query and manifest file to create a new endpoints resource.

/*+ create */
INSERT INTO google.aiplatform.endpoints (
locationsId,
projectsId,
etag,
enablePrivateServiceConnect,
encryptionSpec,
network,
privateServiceConnectConfig,
displayName,
description,
dedicatedEndpointEnabled,
trafficSplit,
predictRequestResponseLoggingConfig,
labels
)
SELECT
'{{ locationsId }}',
'{{ projectsId }}',
'{{ etag }}',
{{ enablePrivateServiceConnect }},
'{{ encryptionSpec }}',
'{{ network }}',
'{{ privateServiceConnectConfig }}',
'{{ displayName }}',
'{{ description }}',
{{ dedicatedEndpointEnabled }},
'{{ trafficSplit }}',
'{{ predictRequestResponseLoggingConfig }}',
'{{ labels }}'
;

UPDATE example

Updates a endpoints resource.

/*+ update */
UPDATE google.aiplatform.endpoints
SET
etag = '{{ etag }}',
enablePrivateServiceConnect = true|false,
encryptionSpec = '{{ encryptionSpec }}',
network = '{{ network }}',
privateServiceConnectConfig = '{{ privateServiceConnectConfig }}',
displayName = '{{ displayName }}',
description = '{{ description }}',
dedicatedEndpointEnabled = true|false,
trafficSplit = '{{ trafficSplit }}',
predictRequestResponseLoggingConfig = '{{ predictRequestResponseLoggingConfig }}',
labels = '{{ labels }}'
WHERE
endpointsId = '{{ endpointsId }}'
AND locationsId = '{{ locationsId }}'
AND projectsId = '{{ projectsId }}';

DELETE example

Deletes the specified endpoints resource.

/*+ delete */
DELETE FROM google.aiplatform.endpoints
WHERE endpointsId = '{{ endpointsId }}'
AND locationsId = '{{ locationsId }}'
AND projectsId = '{{ projectsId }}';