.TH "GCLOUD_ALPHA_ML_LANGUAGE_CLASSIFY\-TEXT" 1



.SH "NAME"
.HP
gcloud alpha ml language classify\-text \- classifies input document into categories



.SH "SYNOPSIS"
.HP
\f5gcloud alpha ml language classify\-text\fR (\fB\-\-content\fR=\fICONTENT\fR\ |\ \fB\-\-content\-file\fR=\fICONTENT_FILE\fR) [\fB\-\-content\-type\fR=\fICONTENT_TYPE\fR;\ default="plain\-text"] [\fB\-\-language\fR=\fILANGUAGE\fR] [\fIGCLOUD_WIDE_FLAG\ ...\fR]



.SH "DESCRIPTION"

\fB(ALPHA)\fR Classifies input document into categories. Returns a list of
categories representing the document. Only the most relevant categories a
document are returned e.g. if \f5/Science\fR and \f5/Science/Astronomy\fR both
apply to a document, then only the \f5/Science/Astronomy\fR category is
returned, as it is the more specific result.

Currently only English is supported for this feature.



.SH "EXAMPLES"

To classify text in raw content 'Long Political Text.':

.RS 2m
$ gcloud alpha ml language classify\-text \e
    \-\-content='Long Political Text.'
.RE

To classify text in file 'myfile.txt':

.RS 2m
$ gcloud alpha ml language classify\-text \-\-content\-file='myfile.txt'
.RE

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

.RS 2m
$ gcloud alpha ml language classify\-text \e
    \-\-content\-file='gs://bucket_name/mycontent.html' \e
    \-\-content\-type=HTML \-\-language=ja\-JP
.RE



.SH "REQUIRED FLAGS"

.RS 2m
.TP 2m

Exactly one of these must be specified:


.RS 2m
.TP 2m
\fB\-\-content\fR=\fICONTENT\fR

Specify input text on the command line. Useful for experiments, or for extremely
short text.

.TP 2m
\fB\-\-content\-file\fR=\fICONTENT_FILE\fR

Specify a local file or Google Cloud Storage (format \f5gs://bucket/object\fR)
file path containing the text to be analyzed. More useful for longer text or
data output from another system.


.RE
.RE
.sp

.SH "OPTIONAL FLAGS"

.RS 2m
.TP 2m
\fB\-\-content\-type\fR=\fICONTENT_TYPE\fR; default="plain\-text"

Specify the format of the input text. \fICONTENT_TYPE\fR must be one of:
\fBhtml\fR, \fBplain\-text\fR.

.TP 2m
\fB\-\-language\fR=\fILANGUAGE\fR

Specify the language of the input text. If omitted, the server will attempt to
auto\-detect. Both ISO (such as \f5en\fR or \f5es\fR) and BCP\-47 (such as
\f5en\-US\fR or \f5ja\-JP\fR) language codes are accepted.


.RE
.sp

.SH "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 \fB$ gcloud help\fR for details.



.SH "API REFERENCE"

This command uses the \fBlanguage/v1beta2\fR API. The full documentation for
this API can be found at: https://cloud.google.com/natural\-language/



.SH "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:

.RS 2m
$ gcloud ml language classify\-text
.RE

.RS 2m
$ gcloud beta ml language classify\-text
.RE