.Net: Prepare AzureOpenAIAudioToTextService for migration to the Azure.AI.OpenAI SDK V2

dotnet/src/Connectors/Connectors.AzureOpenAI/Connectors.AzureOpenAI.csproj

@@ -22,7 +22,9 @@
   </PropertyGroup>
 
   <ItemGroup>
+    <Compile Remove="Core\ClientCore.AudioToText.cs" />
     <Compile Remove="Core\ClientCore.TextToAudio.cs" />
+    <Compile Remove="Services\AzureOpenAIAudioToTextService.cs" />
     <Compile Remove="Services\AzureOpenAITextToAudioService.cs" />
   </ItemGroup>
 
@@ -31,7 +33,9 @@
   </ItemGroup>
 
   <ItemGroup>
+    <None Include="Core\ClientCore.AudioToText.cs" />
     <None Include="Core\ClientCore.TextToAudio.cs" />
+    <None Include="Services\AzureOpenAIAudioToTextService.cs" />
     <None Include="Services\AzureOpenAITextToAudioService.cs" />
   </ItemGroup>
 

dotnet/src/Connectors/Connectors.AzureOpenAI/Core/ClientCore.AudioToText.cs

@@ -0,0 +1,89 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+using System;
+using System.Collections.Generic;
+using System.IO;
+using System.Threading;
+using System.Threading.Tasks;
+using OpenAI.Audio;
+
+namespace Microsoft.SemanticKernel.Connectors.AzureOpenAI;
+
+/// <summary>
+/// Base class for AI clients that provides common functionality for interacting with Azure OpenAI services.
+/// </summary>
+internal partial class ClientCore
+{
+    /// <summary>
+    /// Generates an image with the provided configuration.
+    /// </summary>
+    /// <param name="input">Input audio to generate the text</param>
+    /// <param name="executionSettings">Audio-to-text execution settings for the prompt</param>
+    /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
+    /// <returns>Url of the generated image</returns>
+    internal async Task<IReadOnlyList<TextContent>> GetTextFromAudioContentsAsync(
+        AudioContent input,
+        PromptExecutionSettings? executionSettings,
+        CancellationToken cancellationToken)
+    {
+        if (!input.CanRead)
+        {
+            throw new ArgumentException("The input audio content is not readable.", nameof(input));
+        }
+
+        OpenAIAudioToTextExecutionSettings audioExecutionSettings = OpenAIAudioToTextExecutionSettings.FromExecutionSettings(executionSettings)!;
+        AudioTranscriptionOptions? audioOptions = AudioOptionsFromExecutionSettings(audioExecutionSettings);
+
+        Verify.ValidFilename(audioExecutionSettings?.Filename);
+
+        using var memoryStream = new MemoryStream(input.Data!.Value.ToArray());
+
+        AudioTranscription responseData = (await RunRequestAsync(() => this.Client.GetAudioClient(this.ModelId).TranscribeAudioAsync(memoryStream, audioExecutionSettings?.Filename, audioOptions)).ConfigureAwait(false)).Value;
+
+        return [new(responseData.Text, this.ModelId, metadata: GetResponseMetadata(responseData))];
+    }
+
+    /// <summary>
+    /// Converts <see cref="PromptExecutionSettings"/> to <see cref="AudioTranscriptionOptions"/> type.
+    /// </summary>
+    /// <param name="executionSettings">Instance of <see cref="PromptExecutionSettings"/>.</param>
+    /// <returns>Instance of <see cref="AudioTranscriptionOptions"/>.</returns>
+    private static AudioTranscriptionOptions? AudioOptionsFromExecutionSettings(OpenAIAudioToTextExecutionSettings executionSettings)
+        => new()
+        {
+            Granularities = ConvertToAudioTimestampGranularities(executionSettings!.Granularities),
+            Language = executionSettings.Language,
+            Prompt = executionSettings.Prompt,
+            Temperature = executionSettings.Temperature
+        };
+
+    private static AudioTimestampGranularities ConvertToAudioTimestampGranularities(IEnumerable<OpenAIAudioToTextExecutionSettings.TimeStampGranularities>? granularities)
+    {
+        AudioTimestampGranularities result = AudioTimestampGranularities.Default;
+
+        if (granularities is not null)
+        {
+            foreach (var granularity in granularities)
+            {
+                var openAIGranularity = granularity switch
+                {
+                    OpenAIAudioToTextExecutionSettings.TimeStampGranularities.Word => AudioTimestampGranularities.Word,
+                    OpenAIAudioToTextExecutionSettings.TimeStampGranularities.Segment => AudioTimestampGranularities.Segment,
+                    _ => AudioTimestampGranularities.Default
+                };
+
+                result |= openAIGranularity;
+            }
+        }
+
+        return result;
+    }
+
+    private static Dictionary<string, object?> GetResponseMetadata(AudioTranscription audioTranscription)
+        => new(3)
+        {
+            [nameof(audioTranscription.Language)] = audioTranscription.Language,
+            [nameof(audioTranscription.Duration)] = audioTranscription.Duration,
+            [nameof(audioTranscription.Segments)] = audioTranscription.Segments
+        };
+}

dotnet/src/Connectors/Connectors.AzureOpenAI/Services/AzureOpenAIAudioToTextService.cs

@@ -0,0 +1,94 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+using System.Collections.Generic;
+using System.Diagnostics.CodeAnalysis;
+using System.Net.Http;
+using System.Threading;
+using System.Threading.Tasks;
+using Azure.AI.OpenAI;
+using Azure.Core;
+using Microsoft.Extensions.Logging;
+using Microsoft.SemanticKernel.AudioToText;
+using Microsoft.SemanticKernel.Services;
+
+namespace Microsoft.SemanticKernel.Connectors.AzureOpenAI;
+
+/// <summary>
+/// Azure OpenAI audio-to-text service.
+/// </summary>
+[Experimental("SKEXP0001")]
+public sealed class AzureOpenAIAudioToTextService : IAudioToTextService
+{
+    /// <summary>Core implementation shared by Azure OpenAI services.</summary>
+    private readonly AzureOpenAIClientCore _core;
+
+    /// <inheritdoc/>
+    public IReadOnlyDictionary<string, object?> Attributes => this._core.Attributes;
+
+    /// <summary>
+    /// Creates an instance of the <see cref="AzureOpenAIAudioToTextService"/> with API key auth.
+    /// </summary>
+    /// <param name="deploymentName">Azure OpenAI deployment name, see https://learn.microsoft.com/azure/cognitive-services/openai/how-to/create-resource</param>
+    /// <param name="endpoint">Azure OpenAI deployment URL, see https://learn.microsoft.com/azure/cognitive-services/openai/quickstart</param>
+    /// <param name="apiKey">Azure OpenAI API key, see https://learn.microsoft.com/azure/cognitive-services/openai/quickstart</param>
+    /// <param name="modelId">Azure OpenAI model id, see https://learn.microsoft.com/azure/cognitive-services/openai/how-to/create-resource</param>
+    /// <param name="httpClient">Custom <see cref="HttpClient"/> for HTTP requests.</param>
+    /// <param name="loggerFactory">The <see cref="ILoggerFactory"/> to use for logging. If null, no logging will be performed.</param>
+    public AzureOpenAIAudioToTextService(
+        string deploymentName,
+        string endpoint,
+        string apiKey,
+        string? modelId = null,
+        HttpClient? httpClient = null,
+        ILoggerFactory? loggerFactory = null)
+    {
+        this._core = new(deploymentName, endpoint, apiKey, httpClient, loggerFactory?.CreateLogger(typeof(AzureOpenAIAudioToTextService)));
+        this._core.AddAttribute(AIServiceExtensions.ModelIdKey, modelId);
+    }
+
+    /// <summary>
+    /// Creates an instance of the <see cref="AzureOpenAIAudioToTextService"/> with AAD auth.
+    /// </summary>
+    /// <param name="deploymentName">Azure OpenAI deployment name, see https://learn.microsoft.com/azure/cognitive-services/openai/how-to/create-resource</param>
+    /// <param name="endpoint">Azure OpenAI deployment URL, see https://learn.microsoft.com/azure/cognitive-services/openai/quickstart</param>
+    /// <param name="credentials">Token credentials, e.g. DefaultAzureCredential, ManagedIdentityCredential, EnvironmentCredential, etc.</param>
+    /// <param name="modelId">Azure OpenAI model id, see https://learn.microsoft.com/azure/cognitive-services/openai/how-to/create-resource</param>
+    /// <param name="httpClient">Custom <see cref="HttpClient"/> for HTTP requests.</param>
+    /// <param name="loggerFactory">The <see cref="ILoggerFactory"/> to use for logging. If null, no logging will be performed.</param>
+    public AzureOpenAIAudioToTextService(
+        string deploymentName,
+        string endpoint,
+        TokenCredential credentials,
+        string? modelId = null,
+        HttpClient? httpClient = null,
+        ILoggerFactory? loggerFactory = null)
+    {
+        this._core = new(deploymentName, endpoint, credentials, httpClient, loggerFactory?.CreateLogger(typeof(AzureOpenAIAudioToTextService)));
+        this._core.AddAttribute(AIServiceExtensions.ModelIdKey, modelId);
+    }
+
+    /// <summary>
+    /// Creates an instance of the <see cref="AzureOpenAIAudioToTextService"/> using the specified <see cref="OpenAIClient"/>.
+    /// </summary>
+    /// <param name="deploymentName">Azure OpenAI deployment name, see https://learn.microsoft.com/azure/cognitive-services/openai/how-to/create-resource</param>
+    /// <param name="openAIClient">Custom <see cref="OpenAIClient"/>.</param>
+    /// <param name="modelId">Azure OpenAI model id, see https://learn.microsoft.com/azure/cognitive-services/openai/how-to/create-resource</param>
+    /// <param name="loggerFactory">The <see cref="ILoggerFactory"/> to use for logging. If null, no logging will be performed.</param>
+    public AzureOpenAIAudioToTextService(
+        string deploymentName,
+        OpenAIClient openAIClient,
+        string? modelId = null,
+        ILoggerFactory? loggerFactory = null)
+    {
+        this._core = new(deploymentName, openAIClient, loggerFactory?.CreateLogger(typeof(AzureOpenAIAudioToTextService)));
+        this._core.AddAttribute(AIServiceExtensions.ModelIdKey, modelId);
+    }
+
+    /// <inheritdoc/>
+    public Task<IReadOnlyList<TextContent>> GetTextContentsAsync(
+        AudioContent content,
+        PromptExecutionSettings? executionSettings = null,
+        Kernel? kernel = null,
+        CancellationToken cancellationToken = default)
+        => this._core.GetTextContentFromAudioAsync(content, executionSettings, cancellationToken);
+}