Rich Text Editor Demos: Built-in AI Provider Resolvers

Built-in AI Provider Resolvers

Three drop-in IRichTextBoxAiResolver implementations so the AI Toolkit lights up without writing HTTP client plumbing. One line of DI registration; keys read from your secrets store. Works with OpenAI, Anthropic (Claude), Azure OpenAI, and any OpenAI-compatible endpoint (Groq, Together.ai, local Ollama) via a BaseUrl override.

These resolvers live in the RichTextBox.AspNetCore NuGet package (1.0.0-preview.11+). The JS side stays the same — your server picks the provider.

1. OpenAI

using RichTextBox.AiResolvers;

builder.Services.AddRichTextBox();
builder.Services.AddRichTextBoxOpenAiResolver(opts =>
{
    opts.ApiKey = builder.Configuration["OpenAI:ApiKey"];
    opts.Model  = "gpt-4o-mini";
});

var app = builder.Build();
app.MapRichTextBoxUploads();

2. Anthropic (Claude)

builder.Services.AddRichTextBoxAnthropicResolver(opts =>
{
    opts.ApiKey = builder.Configuration["Anthropic:ApiKey"];
    opts.Model  = "claude-3-5-haiku-latest";
});

3. Azure OpenAI

builder.Services.AddRichTextBoxAzureOpenAiResolver(opts =>
{
    opts.ApiKey         = builder.Configuration["AzureOpenAI:ApiKey"];
    opts.Endpoint       = builder.Configuration["AzureOpenAI:Endpoint"];
    opts.DeploymentName = builder.Configuration["AzureOpenAI:Deployment"];
});

Shared options

All three share AiResolverOptions: ApiKey, Model, BaseUrl, MaxTokens, Temperature, SystemSuffix, Timeout. Customize brand voice / tone across every mode by setting SystemSuffix — it’s appended after the built-in system prompt for each action (Proofread, Rewrite, Translate, etc.).

Streaming responses