Task Model Run

Prev Next

Available in VPC.

Task Model Run explains the Task Model Run interface and describes how to create and delete Runs. Task Model Run interface

Task Model Run interface

The Task Model Run interface is structured as follows:

nclue-run-vpc_screen_ko

Component Description
① Menu name Shows the current menu name.
② Basic features Basic functions provided in the Task Model Run menu.
  • [Crate a Run] button: Click to create a Run
  • [Features and pricing information] button: Click to go to the NCLUE service overview page.
  • [Refresh]: Click to refresh the Run list.
③ Delete Click to delete a Run
④ Run list List of created Runs
  • Run ID: Unique ID automatically assigned when the Run is created.
  • Run name: Name entered when creating the Run.
  • Status: Current status of the Run.
    • Registered: Run creation has been initiated.
    • Pending: Waiting before proceeding to the next step. If there are many requests, the wait time may be longer.
    • In progress: Run is being generated.
    • Available: Run generation completed and available for use.
    • Failed: Run generation failed.
  • Result data bucket: Name of the Object Storage bucket where Run results are stored.
  • Result data file path: Storage path of the Run results in the Object Storage bucket.
  • System message: Message displayed when Run creation fails (refer to NCLUE Troubleshooting).
  • Creation date: Timestamp when Run creation was requested.
  • Completed at: Timestamp when Run creation was completed.
  • Task Model: The Task used to generate the Run.
  • Feature: Feature used to generate the Run.
  • Row count: Number of rows in the feature set.

Create a Run

A Run is created using user features and a Task Model. To create:

  1. In the VPC environment of the NAVER Cloud Platform console, navigate to i_menu > Services > AI Services > NCLUE.
  2. Click Task Model Run menu.
  3. Click [Create a Run] button.
  4. When the Run creation popup appears, configure the new Run.
    • Run name: Enter a unique name within 100 characters
    • Task Model: Select the Task whose performance you want to evaluate from the dropdown
      • For details on creating Tasks, refer to Create a Task.
      • Click i-nclue_refresh to refresh the dropdown.
    • Feature: Select the feature to apply to the Task Model
      • For details on creating features, Create a feature.
      • Click i-nclue_refresh to refresh the dropdown.
    • Result storage path: Path where Run results will be stored
      • Storage bucket: Choose the Object Storage bucket from the dropdown menu.
        • To use a new Object Storage bucket, click [Create an Object Storage] button. After creating i-nclue_refresh, click the refresh icon (i-nclue_refresh) so Object Storage appears in the dropdown. For details, see Object Storage Bucket Creation.
      • File path: Enter the path where the Object Storage result file will be stored in the bucket
        • The following special characters cannot be used in file paths:
          • &$@;:+,?*\{}^%`[]<>~#|"'
          • Characters with ASCII codes 0–31 and 128–255 are also not allowed.
        • File naming rules:
          • If the input string ends with /, it is treated as a directory. A file named nclue_{random}_{YYYYMMDDHH}.tsv will be created inside the directory.
          • Otherwise, the input string is treated as a filename prefix, and a file named {input}_{random}_{YYYYMMDDHH}.tsv will be created.
  5. Click [Create] button.
    • The Run appears in the list with the Registered status, and once creation is complete, the status updates to Available.
Note

Run results are values between 0 and 1. A score closer to 0 indicates lower probability, and a score closer to 1 indicates higher probability.

Caution

Result data is stored as a TSV file at the specified Run output path (not in a separate service-managed space). Object Storage fees apply based on the data size.

Delete a Run

To delete a Run:

Caution
  • Deleted Runs cannot be recovered. Please be careful when deleting a run.
  • Even if you delete the Run, its result files remain in Object Storage and may continue to incur storage fees. Delete the Object Storage files separately to avoid charges.
Note
  • Runs in Pending or In progress cannot be deleted (the [Delete] button will be disabled).
  • Multiple Runs can be selected and deleted at once.
  1. In the VPC environment of the NAVER Cloud Platform console, navigate to i_menu > Services > AI Services > NCLUE.
  2. Click Task Model Run menu.
  3. Select the Run you want to delete, then click [Delete] button.
  4. Review the content in the deletion popup and click [Delete] button.
    • The Run will be removed from the list.