ConversationAuthoringClient.GetModelEvaluationResultsAsync Method

Reference

Definition

Namespace:: Azure.AI.Language.Conversations.Authoring

Assembly:: Azure.AI.Language.Conversations.dll

Package:: Azure.AI.Language.Conversations v1.1.0

Source:: ConversationAuthoringClient.cs

Important

Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.

[Protocol Method] Gets the detailed results of the evaluation for a trained model. This includes the raw inference results for the data included in the evaluation process.

This protocol method allows explicit creation of the request and processing of the response for advanced scenarios.

public virtual Azure.AsyncPageable<BinaryData> GetModelEvaluationResultsAsync (string projectName, string trainedModelLabel, string stringIndexType = "Utf16CodeUnit", Azure.RequestContext context = default);

abstract member GetModelEvaluationResultsAsync : string * string * string * Azure.RequestContext -> Azure.AsyncPageable<BinaryData>
override this.GetModelEvaluationResultsAsync : string * string * string * Azure.RequestContext -> Azure.AsyncPageable<BinaryData>

Public Overridable Function GetModelEvaluationResultsAsync (projectName As String, trainedModelLabel As String, Optional stringIndexType As String = "Utf16CodeUnit", Optional context As RequestContext = Nothing) As AsyncPageable(Of BinaryData)

Parameters

projectName: String

The name of the project to use.

trainedModelLabel: String

The trained model label.

stringIndexType: String

Specifies the method used to interpret string offsets. Set this to "Utf16CodeUnit" for .NET strings, which are encoded as UTF-16. Allowed values: "Utf16CodeUnit".

context: RequestContext

The request context, which can override default behaviors of the client pipeline on a per-call basis.

Returns

AsyncPageable<BinaryData>

The AsyncPageable<T> from the service containing a list of BinaryData objects. Details of the body schema for each item in the collection are in the Remarks section below.

Exceptions

ArgumentNullException

projectName, trainedModelLabel or stringIndexType is null.

ArgumentException

projectName or trainedModelLabel is an empty string, and was expected to be non-empty.

RequestFailedException

Service returned a non-success status code.

Examples

This sample shows how to call GetModelEvaluationResultsAsync with required parameters and parse the result.

var credential = new AzureKeyCredential("<key>");
var endpoint = new Uri("<https://my-service.azure.com>");
var client = new ConversationAuthoringClient(endpoint, credential);

await foreach (var item in client.GetModelEvaluationResultsAsync("<projectName>", "<trainedModelLabel>"))
{
    JsonElement result = JsonDocument.Parse(item.ToStream()).RootElement;
    Console.WriteLine(result.GetProperty("text").ToString());
    Console.WriteLine(result.GetProperty("language").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("expectedEntities")[0].GetProperty("category").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("expectedEntities")[0].GetProperty("offset").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("expectedEntities")[0].GetProperty("length").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("predictedEntities")[0].GetProperty("category").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("predictedEntities")[0].GetProperty("offset").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("predictedEntities")[0].GetProperty("length").ToString());
    Console.WriteLine(result.GetProperty("intentsResult").GetProperty("expectedIntent").ToString());
    Console.WriteLine(result.GetProperty("intentsResult").GetProperty("predictedIntent").ToString());
}

This sample shows how to call GetModelEvaluationResultsAsync with all parameters, and how to parse the result.

var credential = new AzureKeyCredential("<key>");
var endpoint = new Uri("<https://my-service.azure.com>");
var client = new ConversationAuthoringClient(endpoint, credential);

await foreach (var item in client.GetModelEvaluationResultsAsync("<projectName>", "<trainedModelLabel>", "Utf16CodeUnit"))
{
    JsonElement result = JsonDocument.Parse(item.ToStream()).RootElement;
    Console.WriteLine(result.GetProperty("text").ToString());
    Console.WriteLine(result.GetProperty("language").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("expectedEntities")[0].GetProperty("category").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("expectedEntities")[0].GetProperty("offset").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("expectedEntities")[0].GetProperty("length").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("predictedEntities")[0].GetProperty("category").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("predictedEntities")[0].GetProperty("offset").ToString());
    Console.WriteLine(result.GetProperty("entitiesResult").GetProperty("predictedEntities")[0].GetProperty("length").ToString());
    Console.WriteLine(result.GetProperty("intentsResult").GetProperty("expectedIntent").ToString());
    Console.WriteLine(result.GetProperty("intentsResult").GetProperty("predictedIntent").ToString());
}

Remarks

Additional information can be found in the service REST API documentation: https://video2.skills-academy.com/rest/api/language/2023-04-01/conversational-analysis-authoring/get-model-evaluation-results

Applies to

Share via