Machine Learning Classifier

Desginer panel

Properties panel

• DisplayName - The display name of the activity.

• Private - If selected, the values of variables and arguments are no longer logged at Verbose level.

• ApiKey - The API key used to provide you access to the Machine Learning Classifier. The API Key field is automatically pre-populated if defined in local project settings or in the Document Understanding framework. If you want to add the API Key manually, visit API key for more information about retrieving the API Key.
• Endpoint - Provide the public ML Skill URL from the AI Center service. An Endpoint is required for on-premises or different Orchestrator instance scenarios. Choose only Endpoint or ML Skills, not both.
• MLSkill - Provides the MLSkills list available in the AI Center service. Choose the ML Skill hosting the document classification machine learning model. The ML Skill is the only available option when you connect the robot to the AI Center through the same Orchestrator instance.
• RetryOnFailure - Automatically retries the machine learning model execution, to eliminate transient network errors. If checked, the activity retries the execution.
• Timeout (milliseconds) - Specifies the amount of time (in milliseconds) to wait for a response from the server before an error is thrown. The default value is 100000 milliseconds (100 seconds).
  Note: When an endpoint is added, the dropdown button of the ML Skill option is disabled and the following message is displayed: "The activity works with either an Endpoint or an ML Skill, not both. Enter an Endpoint and leave ML Skill empty, or select an ML Skill and leave Endpoint empty".

1. In the Machine Learning Classifier wizard that automatically opens, provide the ML Skill and the ApiKey information.
   Figure 1. The ML Skill and ApiKey fields to configure for the Machine Learning Classifier
   

   

   
   
   Note: Machine Learning Classifier only works with Machine Learning Classifier Skills. Using any other Skills (receipts, invoices, etc.) with it, will result in an error.
2. Select Update activity arguments if you wish to also use the entered values as input arguments for the activity, more precisely for the ML Skill.
3. Select Get Capabilities.

   The wizard closes after this operation

4. Select Configure Extractors in the Data Extraction Scope.

   A wizard is displayed.

   Figure 2. The Configure Classifiers wizard
   

   

   
   
5. Match Document Type names used in Taxonomy to classification classes used by the ML Skill. The latter can be obtained very easily by using Get Capabilities either by configuring it when you first drop the activity or by selecting the gear icon and then simply selecting the class names from the dropdown list. Selecting one of the options from a dropdown list automatically confirms that field.
6. Select Save once all fields are configured.
   Important: You cannot choose the same option for two distinct fields.

Document Understanding Integration