Using a finetuned Openai model via Web SDK

Hello, I'm calling the Web SDK to create an assistant. How do I use a finetuned Openai model?

I saw this in the docs but I'm not sure where/when to do the PATCH request, and how it fits in with the current call:

Using Fine-Tuned OpenAI Models
To set up your OpenAI Fine-Tuned model, you need to follow these steps:

Set the custom llm URL to https://api.openai.com/v1.
Assign the custom llm key to the OpenAI key.
Update the model to their model.
Execute a PATCH request to the /assistant endpoint and ensure that model.metadataSendMode is set to off.


This is my current code:
const vapi = new Vapi("x");

const assistantOptions = {
  name: "Vapi’s Pizza Front Desk",
  firstMessage: "Vappy’s Pizzeria speaking, how can I help you?",
  transcriber: {
    provider: "deepgram",
    model: "nova-2",
    language: "en-US",
  },
  voice: {
    provider: "playht",
    voiceId: "jennifer",
  },
  model: {
    provider: "openai",
    model: "gpt-4o",
    messages: [
      {
        role: "system",
        content: `x`,
      },
    ],
  },
};

    const startCallButton = document.getElementById('startCallButton');
    const voiceAnimation = document.getElementById('voiceAnimation');

    let callActive = false; 

    // Add this line to check if the button is found
    console.log('Start/End Call button:', startCallButton);

    // Just before attaching the event listener
    console.log('About to attach event listener');

    startCallButton.addEventListener('click', async () => {
      console.log('Event listener triggered');
      console.log('Button clicked. Call active:', callActive);

      if (!callActive) {
        try {
          startCallButton.disabled = true; 
          startCallButton.innerText = 'Connecting...'; 

          voiceAnimation.classList.add('voice-animation-active');
          await vapi.start(assistantOptions); 
Was this page helpful?