gcloud alpha ai index-endpoints deploy-index - deploy an index to a Vertex AI index endpoint

gcloud alpha ai index-endpoints deploy-index(INDEX_ENDPOINT :--region=REGION)--deployed-index-id=DEPLOYED_INDEX_ID--display-name=DISPLAY_NAME--index=INDEX[--allowed-issuers=[ALLOWED_ISSUERS,…]][--audiences=[AUDIENCES,…]][--deployment-group=DEPLOYMENT_GROUP][--deployment-tier=DEPLOYMENT_TIER][--enable-access-logging][--machine-type=MACHINE_TYPE][--max-replica-count=MAX_REPLICA_COUNT][--min-replica-count=MIN_REPLICA_COUNT][--psc-automation-configs=[network=NETWORK],[project-id=PROJECT-ID]][--reserved-ip-ranges=[RESERVED_IP_RANGES,…]][GCLOUD_WIDE_FLAG …]

Index endpoint resource - The index endpoint to deploy an index. The argumentsin this group can be used to specify the attributes of this resource. (NOTE)Some attributes are not given arguments in this group but can be set in otherways.

To set theproject attribute:

• provide the argumentindex_endpoint on the command line with afully specified name;
• provide the argument--project on the command line;
• set the propertycore/project.

This must be specified.

INDEX_ENDPOINT

ID of the index_endpoint or fully qualified identifier for the index_endpoint.

To set thename attribute:

• provide the argumentindex_endpoint on the command line.

This positional argument must be specified if any of the other arguments in thisgroup are specified.

--region=REGION

Cloud region for the index_endpoint.

To set theregion attribute:

• provide the argumentindex_endpoint on the command line with afully specified name;
• provide the argument--region on the command line;
• set the propertyai/region;
• choose one from the prompted list of available regions.

--deployed-index-id=DEPLOYED_INDEX_ID

Id of the deployed index.

--display-name=DISPLAY_NAME

Display name of the deployed index.

--index=INDEX

ID of the index.

--allowed-issuers=[ALLOWED_ISSUERS,…]

List of allowed JWT issuers for a deployed index.

Each entry must be a valid Google service account, in the following format:service-account-name@project-id.iam.gserviceaccount.com

--audiences=[AUDIENCES,…]

List of JWT audiences that are allowed to access a deployed index.

JWT containing any of these audiences (https://tools.ietf.org/html/draft-ietf-oauth-json-web-token-32#section-4.1.3) will be accepted.

--deployment-group=DEPLOYMENT_GROUP

Deployment group can be no longer than 64 characters (eg:test,prod). If not set, we will use thedefault deploymentgroup.

Creating deployment_groups withreserved_ip_ranges is a recommendedpractice when the peered network has multiple peering ranges.This creates yourdeployments from predictable IP spaces for easier traffic administration.

--deployment-tier=DEPLOYMENT_TIER

The deployment tier that the deployed index is deployed to. If not specified, asystem-chosen default tier is used.DEPLOYMENT_TIER mustbe (only one value is supported):storage.

--enable-access-logging

If true, online prediction access logs are sent to Cloud Logging.

These logs are standard server access logs, containing information liketimestamp and latency for each prediction request.

--machine-type=MACHINE_TYPE

The machine resources to be used for each node of this deployment. For availablemachine types, seehttps://cloud.google.com/ai-platform-unified/docs/predictions/machine-types.

--max-replica-count=MAX_REPLICA_COUNT

Maximum number of machine replicas the deployed index will be always deployedon.

--min-replica-count=MIN_REPLICA_COUNT

Minimum number of machine replicas the deployed index will be always deployedon. If specified, the value must be equal to or larger than 1.

--psc-automation-configs=[network=NETWORK],[project-id=PROJECT-ID]

A pair ofproject-id andnetwork the PSC index will bedeployed to. For example:--psc-automation-configs=project-id=my-project,network=my-network.For multiple networks, this flag can be repeated:--psc-automation-configs=project-id=my-project,network=my-network--psc-automation-configs=project-id=my-project2,network=my-network2

--reserved-ip-ranges=[RESERVED_IP_RANGES,…]

List of reserved IP ranges deployed index will be deployed to.

Run$gcloud help for details.