Send prediction requests to a deployment

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 through the prediction API or through the client libraries (Azure SDK).

Test deployed model

Once your model is deployed, you can test it by sending prediction requests to evaluate its performance with real utterances. Testing helps you verify that the model accurately identifies intents and extracts entities as expected before integrating it into your production applications. You can test your deployment using either the REST API or the Azure SDK client libraries.

Send a conversational language understanding request

First you 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 use the endpoint and key for the API requests

Query your model

Create a POST request using the following URL, headers, and JSON body to start testing a conversational language understanding model.

Request URL

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

Headers

Use the following header to authenticate your request.

Request body

{
  "kind": "Conversation",
  "analysisInput": {
    "conversationItem": {
      "id": "1",
      "participantId": "1",
      "text": "Text 1"
    }
  },
  "parameters": {
    "projectName": "{PROJECT-NAME}",
    "deploymentName": "{DEPLOYMENT-NAME}",
    "stringIndexType": "TextElement_V8"
  }
}

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

Response body

{
  "kind": "ConversationResult",
  "result": {
    "query": "Text1",
    "prediction": {
      "topIntent": "inten1",
      "projectKind": "Conversation",
      "intents": [
        {
          "category": "intent1",
          "confidenceScore": 1
        },
        {
          "category": "intent2",
          "confidenceScore": 0
        },
        {
          "category": "intent3",
          "confidenceScore": 0
        }
      ],
      "entities": [
        {
          "category": "entity1",
          "text": "text1",
          "offset": 29,
          "length": 12,
          "confidenceScore": 1
        }
      ]
    }
  }
}

API response for a conversations project

In a conversations project, you'll get predictions for both your intents and entities that are present within your project.

• The intents and entities include a confidence score between 0.0 to 1.0 associated with how confident the model is about predicting a certain element in your project.
• The top scoring intent is contained within its own parameter.
• Only predicted entities show up in your response.
• Entities indicate:
  • The text of the entity that was extracted
  • Its start location denoted by an offset value
  • The length of the entity text denoted by a length value.

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

1. Go to your resource overview page in the Azure portal

2. From the menu on the left side, select Keys and Endpoint. Use endpoint for the API requests and you need the key for Ocp-Apim-Subscription-Key header.

   

3. Download and install the client library package for your language of choice:

   Language	Package version
   .NET	1.0.0
   Python	1.0.0

4. After you install the client library, use the following samples on GitHub to start calling the API.

   • C#
   • Python

5. For more information, see the following reference documentation:

   • C#
   • Python

Next steps

• Conversational language understanding overview