steampipe plugin install gcp

Table: gcp_vertex_ai_endpoint - Query GCP Vertex AI Endpoints using SQL

Google Cloud's Vertex AI is a unified ML platform for building, deploying, and scaling AI applications. It offers a suite of tools and services for data scientists and ML engineers, which includes the ability to manage endpoints. An endpoint in Vertex AI is a resource that serves predictions from one or more deployed models.

Table Usage Guide

The gcp_vertex_ai_endpoint table provides insights into Vertex AI endpoints within Google Cloud Platform. As a data scientist or ML engineer, explore endpoint-specific details through this table, including deployed models, traffic split, and associated metadata. Utilize it to manage and monitor your AI application endpoints, such as those serving high traffic, the distribution of traffic among deployed models, and the status of each endpoint.

Examples

Basic info

Explore which AI endpoints are active within your Google Cloud Platform, gaining insights into their creation time and associated networks. This can be particularly useful for managing and auditing your AI resources.

select
name,
display_name,
create_time,
network
from
gcp_vertex_ai_endpoint;
select
name,
display_name,
create_time,
network
from
gcp_vertex_ai_endpoint;

List endpoints that are exposed via private service connect

Explore which endpoints are made accessible through private service connect to enhance your understanding of the network's security and accessibility. This can help in assessing potential vulnerabilities and managing access controls.

select
name,
display_name,
create_time,
enable_private_service_connect
from
gcp_vertex_ai_endpoint
where
enable_private_service_connect;
select
name,
display_name,
create_time,
enable_private_service_connect
from
gcp_vertex_ai_endpoint
where
enable_private_service_connect;

List endpoints created in the last 30 days

Determine the areas in which new endpoints have been established within the past month. This can be useful for tracking recent changes and developments in your network.

select
name,
display_name,
network,
create_time,
update_time
from
gcp_vertex_ai_endpoint
where
create_time >= now() - interval '30' day;
select
name,
display_name,
network,
create_time,
update_time
from
gcp_vertex_ai_endpoint
where
create_time >= datetime('now', '-30 day');

Get customer-managed key details of endpoints

Explore the encryption specifics of your AI endpoints to understand their security setup and creation time. This information could be useful in assessing the security measures in place and identifying potential areas for improvement.

select
name,
create_time,
encryption_spec ->> 'KmsKeyName' as kms_key_name
from
gcp_vertex_ai_endpoint;
select
name,
create_time,
json_extract(encryption_spec, '$.KmsKeyName') as kms_key_name
from
gcp_vertex_ai_endpoint;

Get prediction request response config of endpoints

Explore the configuration of prediction request responses in AI endpoints to understand if logging is enabled, the sampling rate, and whether the destination is BigQuery. This can help optimize your data analysis process by ensuring the right logs are being captured and stored at the correct location.

select
name,
network,
predict_request_response_logging_config ->> 'Enabled' as enabled,
predict_request_response_logging_config ->> 'SamplingRate' as sampling_rate,
predict_request_response_logging_config ->> 'BigqueryDestination' as bigquery_destination
from
gcp_vertex_ai_endpoint;
select
name,
network,
json_extract(
predict_request_response_logging_config,
'$.Enabled'
) as enabled,
json_extract(
predict_request_response_logging_config,
'$.SamplingRate'
) as sampling_rate,
json_extract(
predict_request_response_logging_config,
'$.BigqueryDestination'
) as bigquery_destination
from
gcp_vertex_ai_endpoint;

Schema for gcp_vertex_ai_endpoint

NameTypeOperatorsDescription
_ctxjsonbSteampipe context in JSON form.
akasjsonbArray of globally unique identifier strings (also known as) for the resource.
create_timetimestamp with time zoneTimestamp when this Endpoint was created.
deployed_modelsjsonbThe models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
descriptiontextThe description of the Endpoint.
display_nametextHuman-readable display name of this key that you can modify.
enable_private_service_connectbooleanIf true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.
encryption_specjsonbCustomer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
etagtextUsed to perform consistent read-modify-write updates. If not set, a blind 'overwrite' update happens.
labelsjsonbThe labels with user-defined metadata to organize your Endpoints.
locationtextThe GCP multi-region, region, or zone in which the resource is located.
model_deployment_monitoring_jobtextResource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob.
nametext=The resource name of the Endpoint.
networktextThe full name of the Google Compute Engine network (https://cloud.google.com//compute/docs/networks-and-firewalls#networks) to which the Endpoint should be peered.
predict_request_response_logging_configjsonbConfigures the request-response logging for online prediction.
projecttext=, !=, ~~, ~~*, !~~, !~~*The GCP Project in which the resource is located.
sp_connection_nametext=, !=, ~~, ~~*, !~~, !~~*Steampipe connection name.
sp_ctxjsonbSteampipe context in JSON form.
tagsjsonbA map of tags for the resource.
titletextTitle of the resource.
traffic_splitjsonbA map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel.
update_timetimestamp with time zoneTimestamp when this Endpoint was last updated.

Export

This table is available as a standalone Exporter CLI. Steampipe exporters are stand-alone binaries that allow you to extract data using Steampipe plugins without a database.

You can download the tarball for your platform from the Releases page, but it is simplest to install them with the steampipe_export_installer.sh script:

/bin/sh -c "$(curl -fsSL https://steampipe.io/install/export.sh)" -- gcp

You can pass the configuration to the command with the --config argument:

steampipe_export_gcp --config '<your_config>' gcp_vertex_ai_endpoint