Skip to main content
Skip table of contents

Testing a deployed model

How to test a deployed model

As soon as you deploy one of your models, you can test it manually.

To test a deployed model, proceed as follows:

  1. Navigate to NLU → Deployments section.

  2. Select a deployed model and click on it. The following page opens:

general_tab.png
  1. Click on the Test box.

test_button_window.png

You can only test running models. If a deployed model is stopped, the Test box will be greyed out.

  1. Enter your query into the input field and press <Enter> on your keyboard.

test_utterance.png
  1. The response is returned as JSON and displayed in the Response tab. Click the Copy icon to copy the response body.

test_utterance2.png

 6. To see the request body, select the Request tab. Click the Copy icon to copy the request body.

test_utterance_request.png

Below you can find the description of both request and response properties.

JSON request description

Property

Description

flow_id

The NLU workflow ID that indicates the engine running an annotation.

input

User input.

 

entries

Utterances input by the user.

dialog_context

Dialog context information used to evaluate user input and decide on the next system actions. Part of this context can be referenced in the creation of context sensitive rules.

 

max_nbest

Reserved.

 

nbest

Reserved.

 

ambiguous_utterance

User’s previous utterance(s) in cases the status of the previous step’s intent was ambiguous.

 

system_actions

System actions.

JSON response description

Property

Description

utterance

Phrase under query

intents

List of intents and their parameters.

 

name

intent the queried phrase is associated with

 

source

The source the intent is originated from.
Valid values:

  • ml is Machine Learning, used to expand your model’s understanding using your custom data.

  • rb is rule-based NLU, the out-of-the-box understanding based on the model’s domain.

 

constraint

Details about the constraint that matches this intent. Null for ml intents.

nbest_intents

List of n best intents and their parameters.

 

name

intent the queried phrase is associated with

 

source

The source the intent is originated from.
Valid values:

  • ml is Machine Learning, used to expand your model’s understanding using your custom data.

  • rb is rule-based NLU, the out-of-the-box understanding based on the model’s domain.

 

confidence

The Machine Learning confidence for the intent.

JavaScript errors detected

Please note, these errors can depend on your browser setup.

If this problem persists, please contact our support.