​
Changes from v2 to v3

The main difference is that things in v3 are far simpler. That’s because in v3 your code is deployed to our servers (unless you self-host) which are long-running.
  1. No timeouts.
  2. No io.runTask() (and no cacheKeys).
  3. Just use official SDKs, not integrations.
  4. tasks are the new primitive, not jobs.

​
Convert your v2 job using an AI prompt

The prompt in the accordion below gives good results when using Anthropic Claude 3.5 Sonnet. You’ll need a relatively large token limit.
Don’t forget to paste your own v2 code in a markdown codeblock at the bottom of the prompt before running it.

​
OpenAI example comparison

This is a (very contrived) example that does a long OpenAI API call (>10s), stores the result in a database, waits for 5 mins, and then returns the result.

​
v2

First, the old v2 code, which uses the OpenAI integration. Comments inline:
v2 OpenAI task
import { client } from "~/trigger";
import { eventTrigger } from "@trigger.dev/sdk";

//1. A Trigger.dev integration for OpenAI
import { OpenAI } from "@trigger.dev/openai";
const openai = new OpenAI({
  id: "openai",
  apiKey: process.env["OPENAI_API_KEY"]!,
});

//2. Use the client to define a "Job"
client.defineJob({
  id: "openai-tasks",
  name: "OpenAI Tasks",
  version: "0.0.1",
  trigger: eventTrigger({
    name: "openai.tasks",
    schema: z.object({
      prompt: z.string(),
    }),
  }),
  //3. integrations are added and come through to `io` in the run fn
  integrations: {
    openai,
  },
  run: async (payload, io, ctx) => {
    //4. You use `io` to get the integration
    //5. Also note that "backgroundCreate" was needed for OpenAI
    //   to do work that lasted longer than your serverless timeout
    const chatCompletion = await io.openai.chat.completions.backgroundCreate(
      //6. You needed to add "cacheKeys" to any "task"
      "background-chat-completion",
      {
        messages: [{ role: "user", content: payload.prompt }],
        model: "gpt-3.5-turbo",
      }
    );

    const result = chatCompletion.choices[0]?.message.content;
    if (!result) {
      //7. throwing an error at the top-level in v2 failed the task immediately
      throw new Error("No result from OpenAI");
    }

    //8. io.runTask needed to be used to prevent work from happening twice
    const dbRow = await io.runTask("store-in-db", async (task) => {
      //9. Custom logic can be put here
      //   Anything returned must be JSON-serializable, so no Date objects etc.
      return saveToDb(result);
    });

    //10. Wait for 5 minutes.
    //    You need a cacheKey and the 2nd param is a number
    await io.wait("wait some time", 60 * 5);

    //11. Anything returned must be JSON-serializable, so no Date objects etc.
    return result;
  },
});

​
v3

In v3 we eliminate a lot of code mainly because we don’t need tricks to try avoid timeouts. Here’s the equivalent v3 code:
v3 OpenAI task
import { logger, task, wait } from "@trigger.dev/sdk/v3";

//1. Official OpenAI SDK
import OpenAI from "openai";
const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

//2. Jobs don't exist now, use "task"
export const openaiTask = task({
  id: "openai-task",
  //3. Retries happen if a task throws an error that isn't caught
  //   The default settings are in your trigger.config.ts (used if not overriden here)
  retry: {
    maxAttempts: 3,
  },
  run: async (payload: { prompt: string }) => {
    //4. Use the official SDK
    //5. No timeouts, so this can take a long time
    const chatCompletion = await openai.chat.completions.create({
      messages: [{ role: "user", content: payload.prompt }],
      model: "gpt-3.5-turbo",
    });

    const result = chatCompletion.choices[0]?.message.content;
    if (!result) {
      //6. throwing an error at the top-level will retry the task (if retries are enabled)
      throw new Error("No result from OpenAI");
    }

    //7. No need to use runTask, just call the function
    const dbRow = await saveToDb(result);

    //8. You can provide seconds, minutes, hours etc.
    //   You don't need cacheKeys in v3
    await wait.for({ minutes: 5 });

    //9. You can return anything that's serializable using SuperJSON
    //   That includes undefined, Date, bigint, RegExp, Set, Map, Error and URL.
    return result;
  },
});

​
Triggering tasks comparison

​
v2

In v2 there were different trigger types and triggering each type was slightly different.
v2 triggering
async function yourBackendFunction() {
  //1. for `eventTrigger` you use `client.sendEvent`
  const event = await client.sendEvent({
    name: "openai.tasks",
    payload: { prompt: "Create a good programming joke about background jobs" },
  });

  //2. for `invokeTrigger` you'd call `invoke` on the job
  const { id } = await invocableJob.invoke({
    prompt: "What is the meaning of life?",
  });
}

​
v3

We’ve unified triggering in v3. You use trigger() or batchTrigger() which you can do on any type of task. Including scheduled, webhooks, etc if you want.
v3 triggering
async function yourBackendFunction() {
  //call `trigger()` on any task
  const handle = await openaiTask.trigger({
    prompt: "Tell me a programming joke",
  });
}

​
Upgrading your project

  1. Make sure to upgrade all of your trigger.dev packages to v3 first.
npx @trigger.dev/cli@latest update --to 3.0.0
  1. Follow the v3 quick start to get started with v3. Our new CLI will take care of the rest.

​
Using v2 together with v3

You can use v2 and v3 in the same codebase. This can be useful where you already have v2 jobs or where we don’t support features you need (yet).
We do not support calling v3 tasks from v2 jobs or vice versa.