gcloud ml language classify-text

NAME
gcloud ml language classify-text - classifies input document into categories
SYNOPSIS
gcloud ml language classify-text(--content=CONTENT    |--content-file=CONTENT_FILE)[--content-type=CONTENT_TYPE; default="plain-text"][--language=LANGUAGE][GCLOUD_WIDE_FLAG …]
DESCRIPTION
Classifies input document into categories. Returns a list of categoriesrepresenting the document. Only the most relevant categories a document arereturned e.g. if/Science and/Science/Astronomy bothapply to a document, then only the/Science/Astronomy category isreturned, as it is the more specific result.

Currently only English is supported for this feature.

EXAMPLES
To classify text in raw content 'Long Political Text.':
gcloudmllanguageclassify-text--content='Long Political Text.'

To classify text in file 'myfile.txt':

gcloudmllanguageclassify-text--content-file='myfile.txt'

To classify text in a remote file 'gs://bucket_name/mycontent.html' for Japaneselanguage:

gcloudmllanguageclassify-text--content-file='gs://bucket_name/mycontent.html'--content-type=HTML--language=ja-JP
REQUIRED FLAGS
Exactly one of these must be specified:
--content=CONTENT
Specify input text on the command line. Useful for experiments, or for extremelyshort text.
--content-file=CONTENT_FILE
Specify a local file or Google Cloud Storage (formatgs://bucket/object) file path containing the text to be analyzed.More useful for longer text or data output from another system.
OPTIONAL FLAGS
--content-type=CONTENT_TYPE; default="plain-text"
Specify the format of the input text.CONTENT_TYPE mustbe one of:html,plain-text.
--language=LANGUAGE
Specify the language of the input text. If omitted, the server will attempt toauto-detect. Both ISO (such asen ores) and BCP-47(such asen-US orja-JP) language codes are accepted.
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.

API REFERENCE
This command uses thelanguage/v1 API. The full documentation forthis API can be found at:https://cloud.google.com/natural-language/
NOTES
These variants are also available:
gcloudalphamllanguageclassify-text
gcloudbetamllanguageclassify-text

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-05-07 UTC.