Manage tasks
    • PDF

    Manage tasks

    • PDF

    Article Summary

    Available in Classic and VPC

    Task management explains how to run and save tasks from the Playground menu, get a URL to share your saved tasks, and create a test app.

    Run tasks in general mode

    You can create a task in general mode in Playground, run it, save it, and then share the task via a shared URL or create a test app to test it.

    The following describes how to create a new task in general mode.

    1. In NAVER Cloud Platform console, click the Services > AI Services > CLOVA Studio menus, in that order.
    2. Click the My Product menu, and then click the [Go to CLOVA Studio] button.
    3. Click the Playground menu.
    4. Set the parameter.
      • For more details of the parameter, see Parameter.
      • We recommend setting the top P value among the parameters 0.8 and 1 and the top K value at 0 except for special cases.
    5. Please enter a working title and directive.
      • Directives help you contextualize the text you enter into a prompt.
    6. Please provide an example for what the AI will do.
      • We recommend entering more than one pair of samples into the prompt for better accuracy.
      • Please press [Enter] to create a line break.
    7. Please enter an input statement to output the result value.
    8. Proceed with the following steps according to the desired function to perform.
    Caution

    Avoid putting in blank as the last character of the Inject start text.

    Note

    For more information on how to enter prompts in general mode, see CLOVA Studio examples.

    Run tasks in chat mode

    You can create a new task in chat mode in Playground, run it, save it, share it via a shared URL, or create a test app to test it.

    The following describes how to use chat mode in Playground.

    1. In NAVER Cloud Platform console, click the Services > AI Services > CLOVA Studio menus, in that order.

    2. Click the My Product menu, and then click the [Go to CLOVA Studio] button.

    3. Click the Playground menu.

    4. Set the parameter.

      • For more details of the parameter, see Parameter.
      • We recommend setting the top P value among the parameters 0.8 and 1 and the top K value at 0 except for special cases.
    5. Enter a task title.

    6. In the system area, enter specific instructions or examples of what you want the model to do.

    7. On the right side of the screen, enter a question and answer.

      • User: enter the message you expect the user to ask
      • Assistant: enter an answer to the user's question
      Note

      To break a line, press [Enter].

    8. If necessary, click the [Add conversation turn] button to add more questions and answers.

    9. Click the [Run] button.

      • If you are not satisfied with the execution result, clear the contents and run again to generate new result values or edit the example and run again.
    10. Proceed with the following steps according to the desired function to perform.

    Save Playground task

    The following describes how to save a task.

    1. In NAVER Cloud Platform console, click the Services > AI Services > CLOVA Studio menus, in that order.
    2. Click the My Product menu, and then click the [Go to CLOVA Studio] button.
    3. Click the Playground menu in CLOVA Studio.
    4. Write the prompts and click the [Save] button in the top right corner of the screen.
    5. Enter the name and description for the task.
      • Disclosure option
        • Public disclosure: disclose to other organizations
        • Only me: only visible to main/sub accounts
    6. Please set tags if necessary.
      • To add tags, select Please click tags, click the desired tag to add, and select Please click tag again.
      • You can use tags when searching for tasks.
    7. Click the [Save new] button.
      • If you want to save a saved task by recalling it, the [Overwrite] button is activated, and you can overwrite and save the previously saved task by clicking the button.
      • You can view your saved tasks in the Profile > [My tasks] menu.

    Load Playground task

    You can load a sample or saved My tasks to rerun or share the task, and you can also create a test app of the imported task.

    The following describes how to load a task to Playground.

    1. In NAVER Cloud Platform console, click the Services > AI Services > CLOVA Studio menus, in that order.
    2. Click the My Product menu, and then click the [Go to CLOVA Studio] button.
    3. Click the Playground menu in CLOVA Studio.
    4. After clicking the [Load] button, click the task to load.
      • You can only load samples or tasks that you have saved.
    5. Adjust the parameters, or edit the title or prompt in the loaded task, then run it again.

    To select a task to load from my task list.

    1. In NAVER Cloud Platform console, click the Services > AI Services > CLOVA Studio menus, in that order.
    2. Click on the My Product menu, followed by the [Go to CLOVA Studio] button
    3. Click the profile area in the top right corner of the CLOVA Studio screen, and then click the My task menu.
    4. Click the [Explorer] tab > [Prompt] button.
    5. Search for tasks to view in Playground by selecting a tag or entering a search keyword if necessary.
    6. Click the task to open in Playground.
    7. Click the [Open in Playground] button if you see the preview pop-up window.
      • Go to the Playground screen where the task is open.
      • For more information on Playground, see Playground.

    Share Playground task

    You can share your tasks in the Playground with users in other groups. To share a task, first save the task and then click the [Share] button.

    • You can see the share URL in the share pop-up window.
    • If you set the disclosure as Only me, you can see the password to access the shared work.
    • You can click [Copy] to copy the URL and the password to the clipboard.

    Create test app

    The following describes how to create the test app.

    1. Save the task you want to create a test app for.
    2. Click the [Test app] button.
    3. Enter a test app name, and then click the [Create] button.
      • You can create a test app, and see a test app pop-up window.
        clovastudio-playground_testapp_en
        • You can check the API information of the test app, and you can set whether to use an AI Filter. (For more information on APIs, see CLOVA Studio API guide)
        • As for the code type, curl and python are provided.
        • You can click [Copy] to copy the API information to the clipboard.
        • You can click [Reissue] to reissue API Gateway key.
        • You can check AI Filter guide when clicking View guide.
    Note

    After creating a test app and verifying that it works properly, you can apply for a service app. To request a service app, fill out the Service app request form. For more information on service app requests, see Service app request guide.

    Request service app

    The output that can be derived through CLOVA Studio fluctuates greatly depending on the user's input and it is difficult to make a perfect prediction. As a minimum device to prevent this, it goes through a screening process through an application before providing it to the service.
    If you request a service app, you can use it after review and approval.

    The application and issuance process is as follows:

    1. Ensure to create a test app before requesting the service app review. Check that the AI Code of ethics was not violated, and whether a stable service can be provided.
      • Be sure to check the CLOVA Studio AI Code of Ethics in order to understand and prevent various safety issues that may arise.
      • For safe practices, please refer to the CLOVA Studio examples.
      • The service app review can be requested only with a history of test app issuance.
    2. If there are no issues with using the test app, fill out the service app request form.
      • Fill out the service app request form by referring to the information on the review process below.
    3. When approval is complete, you can check the service app API information in the same way as the test app by selecting the [Details] button in the app application status.
      • Review and approval may take 1-3 weeks.
    4. Changes cannot be made when the service app is under review or after it has been approved.
    Note

    Please refer to the contents below for service app review.

    • The service app request is approved or rejected by checking its compliance with the CLOVA Studio AI Code of ethics, whether it is a safe case, and if there are methods of response to risks or potential misuse.
    • The service app should be requested after checking that enough tests produced the planned results on the test app.

    Check application request status

    The following describes how to check the request status of test apps and service apps.

    1. In NAVER Cloud Platform console, click the Services > AI Services > CLOVA Studio menus, in that order.
    2. Click the My Product menu, and then click the [Go to CLOVA Studio] button.
    3. Click the [Go to CLOVA Studio] button.
    4. Click the user name on the top right corner of the home screen, then click Application request status.
      • Move to the app request status page.
      • You can check the details of an app by clicking [Details].
      • If you don’t have a requested app, you can see the [Request new task] button. Click the button to go to Playground.

    AI Filter

    From the point of view of complying with the NAVER AI Code of Ethics, you can set the AI Filter function. AI Filter detects inappropriate output such as profanity from the test app (or service app included) created in Playground and informs the user.

    Currently, AI Filter provides analysis results for inappropriate language, such as profanity, and assigns a label between 0 and 2 based on the risk level detected in the content. The descriptions for each label are as follows:

    LabelDescription
    0High possibility with inappropriate expressions such as profanity in the text
    1Possibility with inappropriate expressions such as profanity in the text
    2Low possibility with inappropriate expressions such as profanity in the text

    Based on the results of the AI Filter analysis, you must prepare appropriate countermeasures to reduce the risk of content. For example, if the AI Filter response to an output is 0, it is safer to inform the end user that the output cannot be returned, and suggest a new input.
    However, since the AI Filter is a model focused on detecting risks, false positives may occur and risk detection may be difficult depending on continuously changing environmental factors (laws, new words, contextual meaning, changes in meaning of words and sentences according to social changes, arbitrary meaning for specific words, etc.), so it cannot be a perfect safety device. If you are concerned about inappropriate output such as profanity, you should pay attention from the stage of designing the prompt to input, as well as preparing an appropriate countermeasure using the AI Filter. For cases to use a safe app with the recommendation of CLOVA Studio, see the CLOVA Studio example guide.

    Caution

    The restrictions of the AI Filter are as follows:

    • The AI Filter limits the requested text to a maximum of 500 characters. Texts longer than 500 characters cannot be parsed normally.
    • If there are too many unusual formats, emojis, and special characters in the requested text, it may not be analyzed properly.

    Was this article helpful?

    What's Next
    Changing your password will log you out immediately. Use the new password to log back in.
    First name must have atleast 2 characters. Numbers and special characters are not allowed.
    Last name must have atleast 1 characters. Numbers and special characters are not allowed.
    Enter a valid email
    Enter a valid password
    Your profile has been successfully updated.