DEV Community

Olatunji Ayodele Abidemi
Olatunji Ayodele Abidemi

Posted on

1

Building a serverless AI App on Cloudflare Workers

addEventListener('fetch', event => {
event.respondWith(handleRequest(event.request))
})

async function handleRequest(request) {
// Parse the incoming request to get the input data
const data = await request.json();

// Here you would typically call an AI model with the input data
// For example, using Cloudflare's Open Models (replace with actual model endpoint and API key)
const aiModelUrl = 'https://api.cloudflare.com/client/v4/models/YOUR_MODEL_ID';
const aiResponse = await fetch(aiModelUrl, {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({ input: data.input })
});

// Get the AI response and format it as needed
const aiResult = await aiResponse.json();

// Return the AI result as the response from the Worker
return new Response(JSON.stringify(aiResult), {
headers: { 'content-type': 'application/json' },
});
}

Image of Datadog

Master Mobile Monitoring for iOS Apps

Monitor your app’s health with real-time insights into crash-free rates, start times, and more. Optimize performance and prevent user churn by addressing critical issues like app hangs, and ANRs. Learn how to keep your iOS app running smoothly across all devices by downloading this eBook.

Get The eBook

Top comments (1)

A Workflow Copilot. Tailored to You.

Pieces.app image

Our desktop app, with its intelligent copilot, streamlines coding by generating snippets, extracting code from screenshots, and accelerating problem-solving.

Read the docs