Response model

Define the information sent or retrieved from data requests in your NLX workspace

What's the Response model of a Data request?

The Response model of your Data request allows you to specify and shape the response body of your external data to be retrieved for relay during a conversation. This could include a user's name registered in a profile, a list of available appointment times, and so on.

Response model tab of a Data request

Data property types

  • String: A simple text value, such as a customer's name

  • Number: An integer, such as a customer's age

  • Boolean: A value consisting of true or false

  • Object: A well-defined structure of multiple values, such as name, age, occupation. Use if wanting to reference the values in the payload of the Data request node

  • List: A list of values that can have other response types nested within

  • List: A list of values that can have other response types nested within

    • Use if wanting to provide the values to a user for selection when employing a User choice node in your flow. Either set your overall schema to List or set it to an Object with a nested List type of the properties you want to provide as choices (you will need to use the Loop node to process properties in a List schema when wanting to reference those values in messaging or in a User choice node of your flow)

Auto-generate response schema

The simplest method for inputting your response schema is to use the model generation tool:

  • Select ✨ Auto-generate

  • Enter/paste sample JSON response

  • Click Set response model

  • Click Save

Manually enter response schema

When selecting Object or List response schemas, a sub-items section will display to specify the multiple values you may want to reference:

  • Expand Items section > Click + Add property

  • Expand new property section > Enter Field name matching the value's name

  • Choose the specific value's schema type using the dropdown

  • Repeat steps to add properties, as needed

  • Click Save

Optional:

  • Sensitive: Enable if you would like the values to be scrubbed from any resulting conversation logs

  • Description: Provide a statement describing the response model or intended function of the setup, or for providing context to an LLM when assigning the Data request as a tool in agentic mode

Last updated