gcloud alpha ai index-endpoints deploy-index

NAME
gcloud alpha ai index-endpoints deploy-index - deploy an index to a Vertex AI index endpoint
SYNOPSIS
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] [--enable-access-logging] [--machine-type=MACHINE_TYPE] [--max-replica-count=MAX_REPLICA_COUNT] [--min-replica-count=MIN_REPLICA_COUNT] [--reserved-ip-ranges=[RESERVED_IP_RANGES,…]] [GCLOUD_WIDE_FLAG …]
DESCRIPTION
(ALPHA) Deploy an index to a Vertex AI index endpoint.
EXAMPLES
To deploy index 345 to an index endpoint 456 with 2 min replica count and 10 max replica count under project example in region us-central1, within reserved ip ranges vertex-ai-ip-range-1 and vertex-ai-ip-range-2 run: 
gcloud alpha ai index-endpoints deploy-index 456 --project=example --region=us-central1 --index=345 --deployed-index-id=deployed-index-345 --display-name=deployed-index-345 --min-replica-count=2 --max-replica-count=10 --reserved-ip-ranges=vertex-ai-ip-range-1,vertex-ai-ip-range-2
POSITIONAL ARGUMENTS
Index endpoint resource - The index endpoint to deploy an index. The arguments in 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 other ways.

To set the project attribute:

  • provide the argument index_endpoint on the command line with a fully specified name;
  • provide the argument --project on the command line;
  • set the property core/project.

This must be specified.

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

To set the name attribute:

  • provide the argument index_endpoint on the command line.

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

--region=REGION
Cloud region for the index_endpoint.

To set the region attribute:

  • provide the argument index_endpoint on the command line with a fully specified name;
  • provide the argument --region on the command line;
  • set the property ai/region;
  • choose one from the prompted list of available regions.
REQUIRED FLAGS
--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.
OPTIONAL FLAGS
--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 the default deployment group.

Creating deployment_groups with reserved_ip_ranges is a recommended practice when the peered network has multiple peering ranges.This creates your deployments from predictable IP spaces for easier traffic administration.

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

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

--machine-type=MACHINE_TYPE
The machine resources to be used for each node of this deployment. For available machine types, see https://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 deployed on.
--min-replica-count=MIN_REPLICA_COUNT
Minimum number of machine replicas the deployed index will be always deployed on. If specified, the value must be equal to or larger than 1.
--reserved-ip-ranges=[RESERVED_IP_RANGES,…]
List of reserved IP ranges deployed index will be deployed to.
GCLOUD WIDE FLAGS
These flags are available to all commands: --access-token-file, --account, --billing-project, --configuration, --flags-file, --flatten, --format, --help, --impersonate-service-account, --log-http, --project, --quiet, --trace-token, --user-output-enabled, --verbosity.

Run $ gcloud help for details.

NOTES
This command is currently in alpha and might change without notice. If this command fails with API permission errors despite specifying the correct project, you might be trying to access an API with an invitation-only early access allowlist. These variants are also available: 
gcloud ai index-endpoints deploy-index
 
gcloud beta ai index-endpoints deploy-index