Rldc.Maf 0.5.0

Rldc.Maf

Use Rldc.Maf when an application already uses Microsoft Agent Framework or Microsoft.Extensions.AI and wants to connect that conversational flow to Rldc. The package adapts a registered IInferenceProvider into an IChatClient and agent factory; it does not turn typed decision inference into chat or provide a model by itself.

The package targets .NET 10. AddRldcMaf registers Rldc services and the adapter; provide a conversational inference provider and its model separately. The separate Rldc.Inference.Ollama package implements chat without its own ONNX Runtime or tokenizer dependency. The legacy Rldc.Maf registration still depends on Rldc to preserve existing AddRldcMaf behavior.

services.AddRldcMaf(
    configure: maf =>
    {
        maf.Model = "chat-model";
        maf.Temperature = 0.2;
        maf.MaxOutputTokens = 512;
        maf.TopP = 0.9;
        maf.EnableToolCalls = true;
        maf.EnableStructuredOutput = true;
        maf.EnableStreaming = true;
    },
    configureServices: registrations =>
        registrations.AddSingleton<IInferenceProvider, MyConversationalProvider>());

The package registers IChatClient, IRldcMafProvider, and RldcMafAgentFactory. The provider abstraction keeps the adapter independent from a specific remote chat vendor; applications can replace IRldcMafProvider or IChatClient through configureServices. The MAF options supply default generation settings; per-request ChatOptions.ModelId, temperature, maximum output tokens, top-p, stop sequences, and seed take precedence. IInferenceProvider must be registered for conversational inference, while Rldc options and other service implementations can be configured through the same registration call. Tool calls, JSON response formats, and true provider streaming are disabled by default. Enable them explicitly with the corresponding RldcMafOptions properties; the Ollama provider supports these capabilities. Unsupported content or provider capabilities fail with an informative NotSupportedException rather than being ignored. The adapter also forwards frequency and presence penalties to providers that support them; Ollama reports them as unsupported because its chat API does not provide equivalent controls. Non-streaming token usage maps to ChatResponse.Usage; streamed usage is available on the final update through the rldc.usage additional property. This adapter targets conversational inference through IInferenceProvider; typed decision inference is a separate IDecisionInferenceProvider contract and is not automatically adapted into an MAF chat client.

Use the factory's callback to configure the chat-backed agent:

var agent = serviceProvider
    .GetRequiredService<RldcMafAgentFactory>()
    .Create(static _ => { });

Typed application-input mapping is provided by the separate Rldc.Engine project; see the root README for its attributes, runtime criteria, and keyed mapping examples.

License

Rldc's adapter code is licensed under MIT, and the NuGet package includes the Rldc license text. Its Microsoft Agent Framework and Microsoft.Extensions.AI dependencies retain their own terms; model assets and providers are also separately licensed.