Query deployment for intent predictions

Article
08/28/2024

After the deployment is added successfully, you can query the deployment for intent and entities predictions from your utterance based on the model you assigned to the deployment. You can query the deployment programmatically Prediction API or through the Client libraries (Azure SDK).

Test deployed model

You can use Language Studio to submit an utterance, get predictions and visualize the results.

To test your model from Language Studio

Select Testing deployments from the left side menu.
Select the model you want to test. You can only test models that are assigned to deployments.
From deployment name dropdown, select your deployment name.
In the text box, enter an utterance to test.
From the top menu, select Run the test.
After you run the test, you should see the response of the model in the result. You can view the results in entities cards view, or view it in JSON format.

Send an orchestration workflow request

After the deployment job is completed successfully, select the deployment you want to use and from the top menu select Get prediction URL.
In the window that appears, copy the sample request URL and body into your command line. Replace <YOUR_QUERY_HERE> with the actual text you want to send to extract intents and entities from.
Submit the POST cURL request in your terminal or command prompt. You'll receive a 202 response with the API results if the request was successful.

First you will need to get your resource key and endpoint:

Go to your resource overview page in the Azure portal. From the menu on the left side, select Keys and Endpoint. You will use the endpoint and key for API requests.

Query your model

Create a POST request using the following URL, headers, and JSON body to start testing an orchestration workflow model.

Request URL

{ENDPOINT}/language/:analyze-conversations?api-version={API-VERSION}

Placeholder	Value	Example
`{ENDPOINT}`	The endpoint for authenticating your API request.	`https://<your-custom-subdomain>.cognitiveservices.azure.com`
`{API-VERSION}`	The version of the API you are calling.	`2023-04-01`

Headers

Use the following header to authenticate your request.

Key	Value
`Ocp-Apim-Subscription-Key`	The key to your resource. Used for authenticating your API requests.

Request Body

{
  "kind": "Conversation",
  "analysisInput": {
    "conversationItem": {
      "text": "Text1",
      "participantId": "1",
      "id": "1"
    }
  },
  "parameters": {
    "projectName": "{PROJECT-NAME}",
    "deploymentName": "{DEPLOYMENT-NAME}",
    "directTarget": "qnaProject",
    "targetProjectParameters": {
      "qnaProject": {
        "targetProjectKind": "QuestionAnswering",
        "callingOptions": {
          "context": {
            "previousUserQuery": "Meet Surface Pro 4",
            "previousQnaId": 4
          },
          "top": 1,
          "question": "App Service overview"
        }
      }
    }
  }
}

Response Body

Once you send the request, you will get the following response for the prediction!

{
  "kind": "ConversationResult",
  "result": {
    "query": "App Service overview",
    "prediction": {
      "projectKind": "Orchestration",
      "topIntent": "qnaTargetApp",
      "intents": {
        "qnaTargetApp": {
          "targetProjectKind": "QuestionAnswering",
          "confidenceScore": 1,
          "result": {
            "answers": [
              {
                "questions": [
                  "App Service overview"
                ],
                "answer": "The compute resources you use are determined by the *App Service plan* that you run your apps on.",
                "confidenceScore": 0.7384000000000001,
                "id": 1,
                "source": "https://zcusa.951200.xyz/azure/app-service/overview",
                "metadata": {},
                "dialog": {
                  "isContextOnly": false,
                  "prompts": []
                }
              }
            ]
          }
        }
      }
    }
  }
}

First you will need to get your resource key and endpoint:

Go to your resource overview page in the Azure portal. From the menu on the left side, select Keys and Endpoint. You will use the endpoint and key for API requests.

Use the client libraries (Azure SDK)

You can also use the client libraries provided by the Azure SDK to send requests to your model.

Note

The client library for conversational language understanding is only available for:

.NET
Python

Go to your resource overview page in the Azure portal
From the menu on the left side, select Keys and Endpoint. Use endpoint for the API requests and you will need the key for Ocp-Apim-Subscription-Key header.
Download and install the client library package for your language of choice:

Language Package version

.NET 1.0.0

Python 1.0.0
After you've installed the client library, use the following samples on GitHub to start calling the API.
- C#
- Python
See the following reference documentation for more information:
- C#
- Python

Language	Package version
.NET	1.0.0
Python	1.0.0

Next steps

Orchestration workflow overview

Share via