gcloud alpha ai endpoints raw-predict - run Vertex AI online raw prediction
gcloud alpha ai endpoints raw-predict (ENDPOINT : --region=REGION) --request=REQUEST [--http-headers=[HEADER=VALUE,...]] [GCLOUD_WIDE_FLAG ...]
(ALPHA) gcloud alpha ai endpoints raw-predict sends a raw prediction request to a Vertex AI endpoint. The request can be given on the command line or read from a file or stdin.
To predict against an endpoint 123 under project example in region us-central1, reading the request from the command line, run:
$ gcloud alpha ai endpoints raw-predict 123 --project=example \ --region=us-central1 --request='{ "instances": [ { "values": [1, 2, 3, 4], "key": 1 }, { "values": [5, 6, 7, 8], "key": 2 } ] }'
If the request body was in the file input.json, run:
$ gcloud alpha ai endpoints raw-predict 123 --project=example \ --region=us-central1 --request=@input.json
To send the image file image.jpeg and set the content type, run:
$ gcloud alpha ai endpoints raw-predict 123 --project=example \ --region=us-central1 --http-headers=Content-Type=image/jpeg \ --request=@image.jpeg
- Endpoint resource - The endpoint to do online raw prediction. 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 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.
- ENDPOINT
ID of the endpoint or fully qualified identifier for the endpoint. To set the name attribute:
provide the argument 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 endpoint. To set the region attribute:
provide the argument 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.
- --request=REQUEST
The request to send to the endpoint.
If the request starts with the letter '@', the rest should be a file name to read the request from, or '@-' to read from stdin. If the request body actually starts with '@', it must be placed in a file.
If required, the Content-Type header should also be set appropriately, particularly for binary data.
- --http-headers=[HEADER=VALUE,...]
List of header and value pairs to send as part of the request. For example, to set the Content-Type and X-Header:
--http-headers=Content-Type="application/json",X-Header=Value
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.
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 endpoints raw-predict
$ gcloud beta ai endpoints raw-predict