Skip to main content

ML Skill

UiPath.MLServices.Activities.MLSkills

Description​

note

This activity requires Studio v2019.10 or higher to function properly.

Retrieves ML Skills available in the AI Center service and requests them. Authenticates under the robot which executes the ML Skill.

Project compatibility​

Windows-Legacy | Windows

How are inputs passed to the activity​

Depending on the input type, the MLSkills activity expects the following format:

JSON

"this is an example of input"
"{""expected-field"":""this is another example""}"

File

"C:/full/path/to/file.ext"

Files

"C:/full/path/to/file1.ext,C:/full/path/to/file2.ext,C:/full/path/to/file3.ext"

Configuration​

Designer panel​

Depending on the chosen Connection mode, you can configure several essential properties directly from the body of the activity.

Connection mode: Robot

Figure 1. The ML Skill activity when the connection mode is made through a Robot

The ML Skill activity when the connection mode is made through a Robot

  • Search - Retrieves the list of available ML Skills and allows you to select the one to which you want to send data. This list is populated after connection.
  • Item - The input that is sent alongside the ML Skill request.
  • JSONResponse - The JSON response returned by the ML Skill request.

Connection mode: Endpoint

Figure 2. The ML Skill activity when the connection mode is made through an endpoint

The ML Skill activity when the connection mode is made through an endpoint

  • ML Skill URL - The URL of the ML Skill to used for prediction. For instance, you can type https://aicentercom/j123/invoices in the Advanced Editor. Once public, it is visible in the Dataset detail page.
  • API Key - The API Key selected from the AI Center Resource. Once public, it is visible in the Dataset detail page.
  • Test Skill - Test your ML Skill.
  • Input type - The input type expected for the ML Skill selected from the drop-down list (JSON, File, or Files)
  • Item - The input that is sent alongside the ML Skill request.
  • JSONResponse - The JSON response returned by the ML Skill request.

Properties panel​

Common

  • ContinueOnError - Specifies if the automation should continue even when the activity throws an error. This field only supports Boolean values (True, False). The default value is False. As a result, if the field is blank and an error is thrown, the execution of the project stops. If the value is set to True, the execution of the project continues regardless of any error.
    note

    If this activity is included in Try Catch and the value of the ContinueOnError property is True, no error is caught when the project is executed.

  • DelayAfter - Delay time (in milliseconds) after executing the activity. This field supports only Int32 variables.
  • DelayBefore - Delay time (in milliseconds) before the activity begins performing any operations. This field supports only Int32 variables.
  • DisplayName - The display name of the activity. This field supports only String variables.
  • NumberOfRetries - The maximum number of attempts to execute the ML Skill request. This field supports only Int32 variables.
  • TimeoutMS - Specifies the amount of time (in milliseconds) to wait for the activity to run before an error is thrown. The default value is 30000 milliseconds (30 seconds). This field supports only Int32 variables.

Input

  • API Key - The API Key of the ML Skill to be predicted. This field supports only String variables.
  • Connection mode - The desired type of connection (Robot or Endpoint)
    • Robot - Deploy the ML Skill inside Robot.
    • Endpoint - Deploy the ML Skill outside Robot.
  • Item - The input string that is sent alongside the ML Skill request. This field supports only strings and String variables.

Misc

  • Private - If selected, the values of variables and arguments are no longer logged at Verbose level.
  • Skill URL - The URL of the ML Skill to used for prediction. This field supports only String variables.

Output

  • Headers - The headers returned by the ML Skill request. This field supports only String variables.
  • JSONResponse - The JSON response returned by the ML Skill request. This field supports only String variables.
  • StatusCode - The Status Code returned by the ML Skill request. This field supports only Int32 variables.