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:
Navigate to NLU → Deployments section.
Select a deployed model and click on it. The following page opens:
![2024-02-14_18-56-40.png](../__attachments/563937441/2024-02-14_18-56-40.png?inst-v=568e3e19-9d0b-42a7-be69-113cad850346)
Click on the Test box.
![2024-02-14_18-57-18.png](../__attachments/563937441/2024-02-14_18-57-18.png?inst-v=568e3e19-9d0b-42a7-be69-113cad850346)
You can only test running models. If a deployed model is stopped, the Test box will be greyed out.
Enter your query into the input field and press Enter on your keyboard.
![2024-02-14_18-58-13.png](../__attachments/563937441/2024-02-14_18-58-13.png?inst-v=568e3e19-9d0b-42a7-be69-113cad850346)
The response is returned as JSON and displayed in the Response tab. Click the Copy icon to copy the response body.
![2024-02-14_18-58-57.png](../__attachments/563937441/2024-02-14_18-58-57.png?inst-v=568e3e19-9d0b-42a7-be69-113cad850346)
6. To see the request body, select the Request tab. Click the Copy icon to copy the request body.
![2024-02-14_18-59-49.png](../__attachments/563937441/2024-02-14_18-59-49.png?inst-v=568e3e19-9d0b-42a7-be69-113cad850346)
Below you can find the description of both request and response properties.
JSON request description
Property | Description | |
---|---|---|
| The NLU workflow ID that indicates the engine running an annotation. | |
| User input. | |
|
| Utterances input by the user. |
| 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. | |
|
| Reserved. |
|
| Reserved. |
|
| User’s previous utterance(s) in cases the status of the previous step’s intent was ambiguous. |
|
| System actions. |
JSON response description
Property | Description | |
---|---|---|
| Phrase under query | |
| List of intents and their parameters. | |
|
| intent the queried phrase is associated with |
|
| The source the intent is originated from.
|
|
| Details about the constraint that matches this intent. Null for ml intents. |
| List of n best intents and their parameters. | |
|
| intent the queried phrase is associated with |
|
| The source the intent is originated from.
|
|
| The Machine Learning confidence for the intent. |