Using the Vercel AI SDK

This example demonstrates how to use the Vercel AI SDK with Trigger.dev.

Overview

The Vercel AI SDK is a simple way to use AI models from many different providers, including OpenAI, Microsoft Azure, Google Generative AI, Anthropic, Amazon Bedrock, Groq, Perplexity and more.

It provides a consistent interface to interact with the different AI models, so you can easily switch between them without needing to change your code.

Generate text using OpenAI

This task shows how to use the Vercel AI SDK to generate text from a prompt with OpenAI.

Task code

trigger/vercel-ai-sdk-openai.ts

import { logger, task } from "@trigger.dev/sdk/v3";
import { generateText } from "ai";
// Install the package of the AI model you want to use, in this case OpenAI
import { openai } from "@ai-sdk/openai"; // Ensure OPENAI_API_KEY environment variable is set

export const openaiTask = task({
  id: "openai-text-generate",

  run: async (payload: { prompt: string }) => {
    const chatCompletion = await generateText({
      model: openai("gpt-4-turbo"),
      // Add a system message which will be included with the prompt
      system: "You are a friendly assistant!",
      // The prompt passed in from the payload
      prompt: payload.prompt,
    });

    // Log the generated text
    logger.log("chatCompletion text:" + chatCompletion.text);

    return chatCompletion;
  },
});

Testing your task

To test this task in the dashboard, you can use the following payload:

{
  "prompt": "What is the meaning of life?"
}