Why should you care?

Agents are useless if the web API cannot talk to the model reliably.

See it live — copy this example

Run CLI steps in a terminal. Run C# samples in a .NET 8 console or Web API project with Ollama running on localhost:11434.

// Streaming Tokens to the Browser
public sealed class AiChatService(HttpClient http, IConfiguration config)
{
    public async Task<string> CompleteAsync(string userMessage, CancellationToken ct = default)
    {
        var model = config["Ollama:Model"] ?? "phi3:mini";
        var body = new {
            model,
            messages = new[] { new { role = "user", content = userMessage } },
            stream = false
        };
        using var res = await http.PostAsJsonAsync("/api/chat", body, ct);
        res.EnsureSuccessStatusCode();
        return await res.Content.ReadAsStringAsync(ct);
    }
}

What happened?

• AiChatService wraps Ollama.
• Model name comes from config.
• PostAsJsonAsync sends the chat payload.

Practice next

1. Read the example and rewrite it in your own repo.
2. Run it against local Ollama (or finish the Ollama module first).
3. Change one prompt constraint and compare output.
4. Tighten the prompt to 3 bullets max.
5. Log duration of the model call.

Remember

You can explain Streaming Tokens to the Browser simply. You have a runnable local sketch. You know one risk to watch.

Streaming Tokens to the Browser in LocalAIDesk

Your team applies streaming tokens to the browser while building a private agent desk.

Outcome: A concrete next step exists in code or checklist form.