Dynamic Training

The dynamic entity training uses a web service call to automatically train the Natural Language Understanding (NLP) model of your bot.

You have the ability to call a web service and retrieve the values for your entity type without manually defining them.

Endpoint URL

The web service address from which you want to extract the data.

Method

The HTTP method - GET, POST.

Headers

Optional headers for making the request.

Payload

Any payload defined in a JSON format that you would like to send together with the request.

Selector

An optional JSONPath expression to extract data from the HTTP response. We recommend you to create your JSONPath expressions using the jsonpath.com.

Authentication method

An optional authentication method configuration. If Default is selected, the NativeChat service will try to find authentication methods based on the URL starts with filters of the created authentication methods for the bot. If No authentication is selected, no authentication method will be used for the HTTP request. If any other option is selected, it will be used to set the authentication-method property of the data-source.

Value Template

The template that will be used to generate the value for each of your entities.

Example:

  • {{Title}} {{FirstName}} {{LastName}}

Synonym Templates

For keywords entities, you can also generate synonyms based on one or more template. Each template generates one synonym.

Example:

  • {{Title}} {{LastName}}
  • {{LastName}}
  • {{FirstName}} {{LastName}}

Expression Templates

For trait entities, you can define a number of expression templates to generate expressions for the value. This is similar to synonym templates above.

Manual entry of synonyms

You can define additional examples for the dynamically generated values.