> ## Documentation Index
> Fetch the complete documentation index at: https://trigger-docs-max-duration.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Regular tasks

> The simplest type of task which can be triggered from elsewhere in your code.

They are defined using the `task()` function and can be [triggered](/triggering) from your backend or inside another task.

Like all tasks they don't have timeouts, they should be placed inside a [/trigger folder](/config/config-file), and you [can configure them](/tasks/overview#defining-a-task).

## Example tasks

### A task that does an OpenAI call with retrying

Sometimes OpenAI calls can take a long time to complete, or they can fail. This task will retry if the API call fails completely or if the response is empty.

```ts /trigger/openai.ts
import { task } from "@trigger.dev/sdk/v3";
import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

export const openaiTask = task({
  id: "openai-task",
  //specifying retry options overrides the defaults defined in your trigger.config file
  retry: {
    maxAttempts: 10,
    factor: 1.8,
    minTimeoutInMs: 500,
    maxTimeoutInMs: 30_000,
    randomize: false,
  },
  run: async (payload: { prompt: string }) => {
    //if this fails, it will throw an error and retry
    const chatCompletion = await openai.chat.completions.create({
      messages: [{ role: "user", content: payload.prompt }],
      model: "gpt-3.5-turbo",
    });

    if (chatCompletion.choices[0]?.message.content === undefined) {
      //sometimes OpenAI returns an empty response, let's retry by throwing an error
      throw new Error("OpenAI call failed");
    }

    return chatCompletion.choices[0].message.content;
  },
});
```

### A Task that sends emails in a sequence with delays in between

This example uses Resend to send a sequence of emails over several days.

Each email is wrapped in `retry.onThrow`. This will retry the block of code if an error is thrown. This is useful when you don't want to retry the whole task, but just a part of it. The entire task will use the default retrying, so can also retry.

Additionally this task uses `wait.for` to wait for a certain amount of time before sending the next email. During the waiting time, the task will be paused and will not consume any resources.

```ts /trigger/email-sequence.ts
import { Resend } from "resend";

const resend = new Resend(process.env.RESEND_ASP_KEY);

export const emailSequence = task({
  id: "email-sequence",
  run: async (payload: { userId: string; email: string; name: string }) => {
    console.log(`Start email sequence for user ${payload.userId}`, payload);

    //send the first email immediately
    const firstEmailResult = await retry.onThrow(
      async ({ attempt }) => {
        const { data, error } = await resend.emails.send({
          from: "hello@trigger.dev",
          to: payload.email,
          subject: "Welcome to Trigger.dev",
          html: `<p>Hello ${payload.name},</p><p>Welcome to Trigger.dev</p>`,
        });

        if (error) {
          //throwing an error will trigger a retry of this block
          throw error;
        }

        return data;
      },
      { maxAttempts: 3 }
    );

    //then wait 3 days
    await wait.for({ days: 3 });

    //send the second email
    const secondEmailResult = await retry.onThrow(
      async ({ attempt }) => {
        const { data, error } = await resend.emails.send({
          from: "hello@trigger.dev",
          to: payload.email,
          subject: "Some tips for you",
          html: `<p>Hello ${payload.name},</p><p>Here are some tips for you…</p>`,
        });

        if (error) {
          //throwing an error will trigger a retry of this block
          throw error;
        }

        return data;
      },
      { maxAttempts: 3 }
    );

    //etc...
  },
});
```