Added transcription for Helmholtz and Groq, embeddings for GWDG, and fixed Mistral model capabilities (#942)

app/MindWork AI Studio/Provider/BaseProvider.cs

@@ -375,7 +375,36 @@ public abstract class BaseProvider : IProvider, ISecretId
 
         errorCode = TryGetString(root, "code");
         errorType = TryGetString(root, "type");
-        errorMessage = TryGetString(root, "message");
+
+        // Services built on FastAPI, such as Helmholtz Blablador, word their errors as "detail":
+        errorMessage = TryGetString(root, "message") ?? TryGetString(root, "detail");
+    }
+
+    /// <summary>
+    /// Reads the error message a provider sent in the body of a failed response.
+    /// </summary>
+    /// <remarks>
+    /// Providers word their errors differently, but they all put a sentence somewhere into the
+    /// body. Passing that sentence on is what lets a user act on the problem instead of only
+    /// learning that something went wrong.
+    /// </remarks>
+    /// <param name="responseBody">The body of the failed response.</param>
+    /// <returns>The message, or an empty string when the body carries none.</returns>
+    private static string ReadProviderErrorMessage(string responseBody)
+    {
+        if (string.IsNullOrWhiteSpace(responseBody))
+            return string.Empty;
+
+        try
+        {
+            using var document = JsonDocument.Parse(responseBody);
+            TryGetProviderStreamError(document.RootElement, out _, out _, out var errorMessage);
+            return errorMessage ?? string.Empty;
+        }
+        catch (JsonException)
+        {
+            return string.Empty;
+        }
     }
 
     private static bool TryGetErrorElement(JsonElement root, out JsonElement errorElement)
@@ -1013,6 +1042,35 @@ public abstract class BaseProvider : IProvider, ISecretId
             yield return content;
     }
 
+    /// <summary>
+    /// Builds the message a user gets to see when a transcription request failed.
+    /// </summary>
+    /// <remarks>
+    /// AI Studio always sends WebM/Opus. Some providers run their speech recognition behind a
+    /// decoder which reads WAV only, and they answer with a bad request whose body says that it
+    /// could not decode the file. Nobody can do anything about that inside AI Studio, so we name
+    /// the likely cause and point at the provider instead of showing the raw message.
+    /// </remarks>
+    /// <param name="statusCode">The status code the provider answered with.</param>
+    /// <param name="responseBody">The body the provider answered with.</param>
+    /// <returns>The message to show, or an empty string when we have nothing to say.</returns>
+    private string GetTranscriptionFailureUserMessage(HttpStatusCode statusCode, string responseBody)
+    {
+        var failureReason = this.ClassifyProviderRequestFailure(statusCode, responseBody);
+        var classifiedMessage = this.GetProviderRequestFailureUserMessage(failureReason);
+        if (!string.IsNullOrWhiteSpace(classifiedMessage))
+            return classifiedMessage;
+
+        if (statusCode is HttpStatusCode.BadRequest && responseBody.Contains("not decode", StringComparison.OrdinalIgnoreCase))
+            return string.Format(TB("The provider '{0}' was not able to read the audio file. It probably does not support the WebM/Opus format which AI Studio sends. Please contact the provider about it."), this.InstanceName);
+
+        var providerMessage = ReadProviderErrorMessage(responseBody);
+        if (!string.IsNullOrWhiteSpace(providerMessage))
+            return string.Format(TB("The provider '{0}' reported an error: {1}"), this.InstanceName, providerMessage);
+
+        return string.Empty;
+    }
+
     protected async Task<TranscriptionResult> PerformStandardTranscriptionRequest(RequestedSecret requestedSecret, Model transcriptionModel, string audioFilePath, Host host = Host.NONE, CancellationToken token = default)
     {
         try
@@ -1082,8 +1140,7 @@ public abstract class BaseProvider : IProvider, ISecretId
             if (!response.IsSuccessStatusCode)
             {
                 this.logger.LogError("Transcription request failed with status code {ResponseStatusCode} and body: '{ResponseBody}'.", response.StatusCode, responseBody);
-                var providerRequestFailure = this.ClassifyProviderRequestFailure(response.StatusCode, responseBody);
-                return TranscriptionResult.Failure(this.GetProviderRequestFailureUserMessage(providerRequestFailure));
+                return TranscriptionResult.Failure(this.GetTranscriptionFailureUserMessage(response.StatusCode, responseBody));
             }
 
             var transcriptionResponse = JsonSerializer.Deserialize<TranscriptionResponse>(responseBody, JSON_SERIALIZER_OPTIONS);
@@ -1162,6 +1219,15 @@ public abstract class BaseProvider : IProvider, ISecretId
                 this.logger.LogError("Embedding request failed with status code {ResponseStatusCode} and body: '{ResponseBody}'.", response.StatusCode, responseBody);
                 var providerRequestFailure = this.ClassifyProviderRequestFailure(response.StatusCode, responseBody);
                 var userMessage = this.GetProviderRequestFailureUserMessage(providerRequestFailure);
+
+                // We know nothing about this failure, so we pass on what the provider said about it:
+                if (string.IsNullOrWhiteSpace(userMessage))
+                {
+                    var providerMessage = ReadProviderErrorMessage(responseBody);
+                    if (!string.IsNullOrWhiteSpace(providerMessage))
+                        userMessage = string.Format(TB("The provider '{0}' reported an error: {1}"), this.InstanceName, providerMessage);
+                }
+
                 if (!string.IsNullOrWhiteSpace(userMessage))
                     await MessageBus.INSTANCE.SendError(new(Icons.Material.Filled.CloudOff, userMessage));
 
@@ -1214,7 +1280,7 @@ public abstract class BaseProvider : IProvider, ISecretId
     
     protected static bool TryPopIntParameter(IDictionary<string, object> parameters, string key, out int value)
     {
-        value = default;
+        value = 0;
         if (!TryPopParameter(parameters, key, out var raw) || raw is null)
             return false;
         
@@ -1224,15 +1290,15 @@ public abstract class BaseProvider : IProvider, ISecretId
                 value = i;
                 return true;
             
-            case long l when l is >= int.MinValue and <= int.MaxValue:
+            case long l and >= int.MinValue and <= int.MaxValue:
                 value = (int)l;
                 return true;
             
-            case double d when d is >= int.MinValue and <= int.MaxValue:
+            case double d and >= int.MinValue and <= int.MaxValue:
                 value = (int)d;
                 return true;
             
-            case decimal m when m is >= int.MinValue and <= int.MaxValue:
+            case decimal m and >= int.MinValue and <= int.MaxValue:
                 value = (int)m;
                 return true;
         }
@@ -1242,7 +1308,7 @@ public abstract class BaseProvider : IProvider, ISecretId
     
     protected static bool TryPopBoolParameter(IDictionary<string, object> parameters, string key, out bool value)
     {
-        value = default;
+        value = false;
         if (!TryPopParameter(parameters, key, out var raw) || raw is null)
             return false;
         

app/MindWork AI Studio/Provider/GWDG/ProviderGWDG.cs

@@ -10,6 +10,14 @@ public sealed class ProviderGWDG() : BaseProvider(LLMProviders.GWDG, new Uri("ht
 {
     private static readonly ILogger<ProviderGWDG> LOGGER = Program.LOGGER_FACTORY.CreateLogger<ProviderGWDG>();
 
+    // Source: https://docs.hpc.gwdg.de/services/saia/index.html#embeddings
+    private static readonly Model[] KNOWN_EMBEDDING_MODELS =
+    [
+        new("e5-mistral-7b-instruct", "E5 Mistral 7B Instruct"),
+        new("multilingual-e5-large-instruct", "Multilingual E5 Large Instruct"),
+        new("qwen3-embedding-4b", "Qwen3 Embedding 4B"),
+    ];
+
     #region Implementation of IProvider
 
     /// <inheritdoc />
@@ -67,9 +75,10 @@ public sealed class ProviderGWDG() : BaseProvider(LLMProviders.GWDG, new Uri("ht
     }
     
     /// <inhertidoc />
-    public override Task<IReadOnlyList<IReadOnlyList<float>>> EmbedTextAsync(Model embeddingModel, SettingsManager settingsManager, CancellationToken token = default, params List<string> texts)
+    public override async Task<IReadOnlyList<IReadOnlyList<float>>> EmbedTextAsync(Model embeddingModel, SettingsManager settingsManager, CancellationToken token = default, params List<string> texts)
     {
-        return Task.FromResult<IReadOnlyList<IReadOnlyList<float>>>([]);
+        var requestedSecret = await Program.RUST_SERVICE.GetAPIKey(this, SecretStoreType.EMBEDDING_PROVIDER);
+        return await this.PerformStandardTextEmbeddingRequest(requestedSecret, embeddingModel, token: token, texts: texts);
     }
 
     /// <inheritdoc />
@@ -89,12 +98,26 @@ public sealed class ProviderGWDG() : BaseProvider(LLMProviders.GWDG, new Uri("ht
     }
     
     /// <inheritdoc />
+    /// <remarks>
+    /// SAIA answers the models endpoint with its chat models only, so asking it for the embedding
+    /// models comes back empty. We therefore fall back to the models the documentation names. The
+    /// endpoint is still asked first: should SAIA start reporting them one day, its answer wins
+    /// over our list. A failed request is passed on unchanged, so a wrong API key stays visible
+    /// as such instead of being covered up by the fallback.
+    /// </remarks>
     public override async Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
         var result = await this.LoadModels(SecretStoreType.EMBEDDING_PROVIDER, token, apiKeyProvisional);
+        if (!result.Success)
+            return result;
+
+        var embeddingModels = result.Models.Where(model => model.IsEmbeddingModel()).ToList();
+        if (embeddingModels.Count is 0)
+            return ModelLoadResult.FromModels(KNOWN_EMBEDDING_MODELS);
+
         return result with
         {
-            Models = [..result.Models.Where(model => model.IsEmbeddingModel())]
+            Models = [..embeddingModels]
         };
     }
     

app/MindWork AI Studio/Provider/Groq/ProviderGroq.cs

@@ -64,9 +64,10 @@ public class ProviderGroq() : BaseProvider(LLMProviders.GROQ, new Uri("https://a
     #pragma warning restore CS1998 // Async method lacks 'await' operators and will run synchronously
     
     /// <inheritdoc />
-    public override Task<TranscriptionResult> TranscribeAudioAsync(Model transcriptionModel, string audioFilePath, SettingsManager settingsManager, CancellationToken token = default)
+    public override async Task<TranscriptionResult> TranscribeAudioAsync(Model transcriptionModel, string audioFilePath, SettingsManager settingsManager, CancellationToken token = default)
     {
-        return Task.FromResult(TranscriptionResult.Failure());
+        var requestedSecret = await Program.RUST_SERVICE.GetAPIKey(this, SecretStoreType.TRANSCRIPTION_PROVIDER);
+        return await this.PerformStandardTranscriptionRequest(requestedSecret, transcriptionModel, audioFilePath, token: token);
     }
     
     /// <inhertidoc />
@@ -76,9 +77,13 @@ public class ProviderGroq() : BaseProvider(LLMProviders.GROQ, new Uri("https://a
     }
 
     /// <inheritdoc />
-    public override Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
+        var result = await this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models = [..result.Models.Where(model => model.IsChatModel())]
+        };
     }
 
     /// <inheritdoc />
@@ -94,9 +99,13 @@ public class ProviderGroq() : BaseProvider(LLMProviders.GROQ, new Uri("https://a
     }
     
     /// <inheritdoc />
-    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(ModelLoadResult.FromModels([]));
+        var result = await this.LoadModels(SecretStoreType.TRANSCRIPTION_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models = [..result.Models.Where(model => model.IsTranscriptionModel())]
+        };
     }
     
     #endregion
@@ -106,10 +115,7 @@ public class ProviderGroq() : BaseProvider(LLMProviders.GROQ, new Uri("https://a
         return this.LoadModelsResponse<ModelsResponse>(
             storeType,
             "models",
-            modelResponse => modelResponse.Data.Where(n =>
-                !n.Id.StartsWith("whisper-", StringComparison.OrdinalIgnoreCase) &&
-                !n.Id.StartsWith("distil-", StringComparison.OrdinalIgnoreCase) &&
-                !n.Id.Contains("-tts", StringComparison.OrdinalIgnoreCase)),
+            modelResponse => modelResponse.Data,
             token,
             apiKeyProvisional);
     }

app/MindWork AI Studio/Provider/Helmholtz/ProviderHelmholtz.cs

@@ -62,9 +62,10 @@ public sealed class ProviderHelmholtz() : BaseProvider(LLMProviders.HELMHOLTZ, n
     #pragma warning restore CS1998 // Async method lacks 'await' operators and will run synchronously
     
     /// <inheritdoc />
-    public override Task<TranscriptionResult> TranscribeAudioAsync(Model transcriptionModel, string audioFilePath, SettingsManager settingsManager, CancellationToken token = default)
+    public override async Task<TranscriptionResult> TranscribeAudioAsync(Model transcriptionModel, string audioFilePath, SettingsManager settingsManager, CancellationToken token = default)
     {
-        return Task.FromResult(TranscriptionResult.Failure());
+        var requestedSecret = await Program.RUST_SERVICE.GetAPIKey(this, SecretStoreType.TRANSCRIPTION_PROVIDER);
+        return await this.PerformStandardTranscriptionRequest(requestedSecret, transcriptionModel, audioFilePath, token: token);
     }
     
     /// <inhertidoc />
@@ -107,9 +108,16 @@ public sealed class ProviderHelmholtz() : BaseProvider(LLMProviders.HELMHOLTZ, n
     }
     
     /// <inheritdoc />
-    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    public override async Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
     {
-        return Task.FromResult(ModelLoadResult.FromModels([]));
+        var result = await this.LoadModels(SecretStoreType.TRANSCRIPTION_PROVIDER, token, apiKeyProvisional);
+        return result with
+        {
+            Models =
+            [
+                ..result.Models.Where(model => model.IsTranscriptionModel())
+            ]
+        };
     }
     
     #endregion

app/MindWork AI Studio/Provider/LLMProvidersExtensions.cs

@@ -185,7 +185,9 @@ public static class LLMProvidersExtensions
         LLMProviders.HELMHOLTZ => true,
         LLMProviders.ALIBABA_CLOUD => true,
         LLMProviders.IONOS => true,
-        
+        LLMProviders.GWDG => true,
+        LLMProviders.OPEN_ROUTER => true,
+
         //
         // Providers that do not support embeddings:
         //
@@ -193,11 +195,9 @@ public static class LLMProvidersExtensions
         LLMProviders.ANTHROPIC => false,
         LLMProviders.FIREWORKS => false,
         LLMProviders.X => false,
-        LLMProviders.GWDG => false,
         LLMProviders.DEEP_SEEK => false,
         LLMProviders.HUGGINGFACE => false,
         LLMProviders.PERPLEXITY => false,
-        LLMProviders.OPEN_ROUTER => true,
         LLMProviders.HETZNER => false,
 
         //
@@ -217,7 +217,9 @@ public static class LLMProvidersExtensions
         LLMProviders.MISTRAL => true,
         LLMProviders.FIREWORKS => true,
         LLMProviders.GWDG => true,
-        
+        LLMProviders.HELMHOLTZ => true,
+        LLMProviders.GROQ => true,
+
         //
         // Providers that support transcription but provide no OpenAI-compatible API yet:
         //
@@ -230,20 +232,17 @@ public static class LLMProvidersExtensions
         LLMProviders.OPEN_ROUTER => false,
         LLMProviders.HETZNER => false,
         LLMProviders.IONOS => false,
-        LLMProviders.GROQ => false,
         LLMProviders.ANTHROPIC => false,
         LLMProviders.X => false,
         LLMProviders.DEEP_SEEK => false,
         LLMProviders.HUGGINGFACE => false,
         LLMProviders.PERPLEXITY => false,
-        
-        LLMProviders.HELMHOLTZ => false,
 
         //
         // Self-hosted providers are treated as a special case anyway.
         //
         LLMProviders.SELF_HOSTED => true,
-        
+
         _ => false,
     };
 

app/MindWork AI Studio/Provider/ModelKindExtensions.cs

@@ -105,6 +105,13 @@ public static class ModelKindExtensions
     /// <returns>True, when the model is an embedding model.</returns>
     public static bool IsEmbeddingModel(this Model model) => model.DetermineKind() is ModelKind.EMBEDDING;
 
+    /// <summary>
+    /// Checks whether this model transcribes audio.
+    /// </summary>
+    /// <param name="model">The model to check.</param>
+    /// <returns>True, when the model is a transcription model.</returns>
+    public static bool IsTranscriptionModel(this Model model) => model.DetermineKind() is ModelKind.TRANSCRIPTION;
+
     private static bool HasAnyMarker(string modelId, string[] markers)
     {
         foreach (var marker in markers)