import { pipeline } from '@huggingface/transformers';

// Create an image classification pipeline
const classifier = await pipeline('image-classification', 'Xenova/fastvit_sa24.apple_dist_in1k');

// Classify an image
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg';
const output = await classifier(url, { top_k: 5 });
console.log(output);
// [
//   { label: 'tiger, Panthera tigris', score: 0.6914318203926086 },
//   { label: 'tiger cat', score: 0.051140956580638885 },
//   { label: 'shower curtain', score: 0.04092452675104141 },
//   { label: 'apron', score: 0.004144148901104927 },
//   { label: 'pillow', score: 0.003142605535686016 }
// ]

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).