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

// Create an image-to-text pipeline
const pipe = await pipeline('image-to-text', 'Xenova/nougat-small');

// Generate markdown
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/nougat_paper.png';
const output = await pipe(url, {
  min_length: 1,
  max_new_tokens: 40,
  bad_words_ids: [[pipe.tokenizer.unk_token_id]],
});
console.log(output);
// [{ generated_text: "# Nougat: Neural Optical Understanding for Academic Documents\n\nLukas Blecher\n\nCorrespondence to: lblecher@meta.com\n\nGuillem Cucur" }]

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).