OpenAI + exponential backoff

Wrap chat.completions.create with retries({ max: 3, backoff: "exponential" }) so transient 429s never bubble up to your users.

import { Klaro, retries } from "@klaroshield/sdk";
import OpenAI from "openai";

const openai = new OpenAI();

const klaro = new Klaro().use(
  retries({ max: 3, backoff: "exponential" })
);

const chat = klaro.wrap(
  openai.chat.completions.create.bind(openai.chat.completions)
);

More in Providers