AI-Studio/app/MindWork AI Studio/Provider/LiteLLM/ProviderLiteLLM.cs

using System.Runtime.CompilerServices;

using AIStudio.Chat;
using AIStudio.Provider.OpenAI;
using AIStudio.Settings;

namespace AIStudio.Provider.LiteLLM;

public sealed class ProviderLiteLLM(string hostname) : BaseProvider(LLMProviders.LITE_LLM, BuildBaseUri(hostname), ExternalHttpTrustPolicy.ALLOW_CUSTOM_ROOTS_WHEN_HOST_WHITELISTED, LOGGER)
{
    private static readonly ILogger<ProviderLiteLLM> LOGGER = Program.LOGGER_FACTORY.CreateLogger<ProviderLiteLLM>();

    #region Implementation of IProvider

    /// <inheritdoc />
    public override string Id => LLMProviders.LITE_LLM.ToSecretId();

    /// <inheritdoc />
    public override string InstanceName { get; set; } = "LiteLLM";

    /// <inheritdoc />
    public override bool HasModelLoadingCapability => true;

    /// <inheritdoc />
    public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
    {
        await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>(
                           "LiteLLM",
                           chatModel,
                           chatThread,
                           settingsManager,
                           async (systemPrompt, apiParameters) =>
                           {
                               // Build the list of messages:
                               var messages = await chatThread.Blocks.BuildMessagesUsingDirectImageUrlAsync(this.Provider, chatModel);

                               return new ChatCompletionAPIRequest
                               {
                                   Model = chatModel.Id,

                                   // Build the messages:
                                   // - First of all the system prompt
                                   // - Then none-empty user and AI messages
                                   Messages = [systemPrompt, ..messages],

                                   Stream = true,
                                   AdditionalApiParameters = apiParameters
                               };
                           },
                           token: token))
            yield return content;
    }

    #pragma warning disable CS1998 // Async method lacks 'await' operators and will run synchronously
    /// <inheritdoc />
    public override async IAsyncEnumerable<ImageURL> StreamImageCompletion(Model imageModel, string promptPositive, string promptNegative = FilterOperator.String.Empty, ImageURL referenceImageURL = default, [EnumeratorCancellation] CancellationToken token = default)
    {
        yield break;
    }
    #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)
    {
        return Task.FromResult(TranscriptionResult.Failure());
    }

    /// <inheritdoc />
    public override Task<IReadOnlyList<IReadOnlyList<float>>> EmbedTextAsync(Model embeddingModel, SettingsManager settingsManager, CancellationToken token = default, params List<string> texts)
    {
        return Task.FromResult<IReadOnlyList<IReadOnlyList<float>>>([]);
    }

    /// <inheritdoc />
    public override Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
    {
        return this.LoadModels(SecretStoreType.LLM_PROVIDER, token, apiKeyProvisional);
    }

    /// <inheritdoc />
    public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
    {
        return Task.FromResult(ModelLoadResult.FromModels([]));
    }

    /// <inheritdoc />
    public override Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
    {
        return Task.FromResult(ModelLoadResult.FromModels([]));
    }

    /// <inheritdoc />
    public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
    {
        return Task.FromResult(ModelLoadResult.FromModels([]));
    }

    #endregion

    private static Uri BuildBaseUri(string hostname)
    {
        // LiteLLM exposes an OpenAI-compatible API under the "/v1/" path. Users configure the
        // base URL of their LiteLLM proxy (e.g. http://localhost:4000); we normalize any trailing
        // slash and append the OpenAI-compatible path.
        var normalizedHostname = (hostname ?? string.Empty).TrimEnd('/');
        return new Uri($"{normalizedHostname}/v1/");
    }

    private Task<ModelLoadResult> LoadModels(SecretStoreType storeType, CancellationToken token, string? apiKeyProvisional = null)
    {
        return this.LoadModelsResponse<ModelsResponse>(
            storeType,
            "models",
            modelResponse => modelResponse.Data,
            token,
            apiKeyProvisional);
    }
}