Query deployment for intent predictions

1. After the deployment job is completed successfully, select the deployment you want to use and from the top menu select Get prediction URL.

   

2. 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.

3. 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}

Headers

Use the following header to authenticate your request.

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://learn.microsoft.com/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.

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 will 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've installed the client library, use the following samples on GitHub to start calling the API.

   • C#
   • Python

5. See the following reference documentation for more information:

   • C#
   • Python