NAME
    gcloud beta model-armor templates sanitize-user-prompt - sanitize User
        Prompt

SYNOPSIS
    gcloud beta model-armor templates sanitize-user-prompt
        (TEMPLATE : --location=LOCATION)
        [--multi-language-detection-metadata-enable]
        [--multi-language-detection-metadata-source=MULTI_LANGUAGE_DETECTION_METADATA_SOURCE]
        [--user-prompt-data-text=USER_PROMPT_DATA_TEXT
          | --byte-item-data-type=BYTE_ITEM_DATA_TYPE
          (--byte-item-data=BYTE_ITEM_DATA
          | --byte-item-data-from-file=PATH_TO_FILE)] [GCLOUD_WIDE_FLAG ...]

DESCRIPTION
    (BETA) Sanitizes a user prompt.

EXAMPLES
    To sanitize a user prompt, run:

        $ gcloud beta model-armor templates sanitize-user-prompt \
            my-template --location=us-central1 \
            --user-prompt-data="test-user-prompt"

POSITIONAL ARGUMENTS
     Template resource - Represents resource name of template e.g.
     name=projects/sample-project/locations/us-central1/templates/templ01 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 template 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.

       TEMPLATE
          ID of the template or fully qualified identifier for the template.

          To set the template attribute:
          ▸ provide the argument template on the command line.

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

       --location=LOCATION
          The location id of the template resource.

          To set the location attribute:
          ▸ provide the argument template on the command line with a fully
            specified name;
          ▸ provide the argument --location on the command line.

FLAGS
     --multi-language-detection-metadata-enable
        Enable detection of multi-language prompts and responses.

     --multi-language-detection-metadata-source=MULTI_LANGUAGE_DETECTION_METADATA_SOURCE
        Optional Source language of the user prompt.

        If multi-language detection is enabled but language is not set in that
        case we would automatically detect the source language.

     Arguments for the data item.

     At most one of these can be specified:

       --user-prompt-data-text=USER_PROMPT_DATA_TEXT
          Plaintext string data for sanitization.

       Or at least one of these can be specified:

         Represents Byte Data item.

         --byte-item-data-type=BYTE_ITEM_DATA_TYPE
            The type of byte data. BYTE_ITEM_DATA_TYPE must be one of:

             csv
                CSV
             excel-document
                XLSX, XLSM, XLTX, XLYM
             pdf
                PDF
             plaintext-utf8
                plain text
             powerpoint-document
                PPTX, PPTM, POTX, POTM, POT
             txt
                TXT
             word-document
                DOCX, DOCM, DOTX, DOTM

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

         Exactly one of these must be specified:

           --byte-item-data=BYTE_ITEM_DATA
              Bytes Data

           --byte-item-data-from-file=PATH_TO_FILE
              Bytes Data. Use a full or relative path to a local file
              containing the value of byte_item_data.

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 the modelarmor/v1beta API. The full documentation for
    this API can be found at:
    https://cloud.google.com/security-command-center/docs/model-armor-overview

NOTES
    This command is currently in beta and might change without notice. These
    variants are also available:

        $ gcloud model-armor templates sanitize-user-prompt

        $ gcloud alpha model-armor templates sanitize-user-prompt

