This guide will help you integrate OpenAI's GPT models with Metorial to give your AI agents access to 600+ integrations.

Prerequisites

Before you begin, make sure you have:

• A Metorial API key
• An OpenAI API key
• Node.js installed on your machine

Installation

Install the required packages:

npm install metorial @metorial/openai openai

Basic Setup

Here's a simple example to get you started:

import { Metorial } from 'metorial';
import { metorialOpenAI } from '@metorial/openai';
import OpenAI from 'openai';

// Initialize Metorial
const metorial = new Metorial({
  apiKey: 'your-metorial-api-key'
});

// Initialize OpenAI
const openai = new OpenAI({
  apiKey: 'your-openai-api-key'
});

// Use them together
await metorial.withProviderSession(
  metorialOpenAI.chatCompletions,
  { serverDeployments: ['your-server-deployment-id'] },
  async session => {
    const messages = [{ role: 'user', content: 'Hello!' }];

    const response = await openai.chat.completions.create({
      model: 'gpt-4o',
      messages,
      tools: session.tools
    });

    console.log(response.choices[0]?.message.content);
  }
);

Next Steps

• Learn how to handle tool calls in the "Handling Tool Calls" guide
• Explore available integrations in your Metorial dashboard
• Check out the OpenAI API documentation for advanced features