npm install @huggingface/transformers

<script type="module">
  import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/transformers';
</script>

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

// Create a pipeline for a specific task
const pipe = await pipeline('sentiment-analysis');

// Use the pipeline
const result = await pipe('I love transformers!');
// Output: [{ label: 'POSITIVE', score: 0.999817686 }]

// IMPORTANT: Always dispose when done to free memory
await classifier.dispose();

const pipe = await pipeline(
  'sentiment-analysis',
  'Xenova/bert-base-multilingual-uncased-sentiment'
);

// Run on CPU (default for WASM)
const pipe = await pipeline('sentiment-analysis', 'model-id');

// Run on GPU (WebGPU - experimental)
const pipe = await pipeline('sentiment-analysis', 'model-id', {
  device: 'webgpu',
});

// Use quantized model (faster, smaller)
const pipe = await pipeline('sentiment-analysis', 'model-id', {
  dtype: 'q4',  // Options: 'fp32', 'fp16', 'q8', 'q4'
});

const classifier = await pipeline('text-classification');
const result = await classifier('This movie was amazing!');

const ner = await pipeline('token-classification');
const entities = await ner('My name is John and I live in New York.');

const qa = await pipeline('question-answering');
const answer = await qa({
  question: 'What is the capital of France?',
  context: 'Paris is the capital and largest city of France.'
});

const generator = await pipeline('text-generation', 'onnx-community/gemma-3-270m-it-ONNX');
const text = await generator('Once upon a time', {
  max_new_tokens: 100,
  temperature: 0.7
});

const translator = await pipeline('translation', 'Xenova/nllb-200-distilled-600M');
const output = await translator('Hello, how are you?', {
  src_lang: 'eng_Latn',
  tgt_lang: 'fra_Latn'
});

const summarizer = await pipeline('summarization');
const summary = await summarizer(longText, {
  max_length: 100,
  min_length: 30
});

const classifier = await pipeline('zero-shot-classification');
const result = await classifier('This is a story about sports.', ['politics', 'sports', 'technology']);

const classifier = await pipeline('image-classification');
const result = await classifier('https://example.com/image.jpg');
// Or with local file
const result = await classifier(imageUrl);

const detector = await pipeline('object-detection');
const objects = await detector('https://example.com/image.jpg');
// Returns: [{ label: 'person', score: 0.95, box: { xmin, ymin, xmax, ymax } }, ...]

const segmenter = await pipeline('image-segmentation');
const segments = await segmenter('https://example.com/image.jpg');

const depthEstimator = await pipeline('depth-estimation');
const depth = await depthEstimator('https://example.com/image.jpg');

const classifier = await pipeline('zero-shot-image-classification');
const result = await classifier('image.jpg', ['cat', 'dog', 'bird']);

const transcriber = await pipeline('automatic-speech-recognition');
const result = await transcriber('audio.wav');
// Returns: { text: 'transcribed text here' }

const classifier = await pipeline('audio-classification');
const result = await classifier('audio.wav');

const synthesizer = await pipeline('text-to-speech', 'Xenova/speecht5_tts');
const audio = await synthesizer('Hello, this is a test.', {
  speaker_embeddings: speakerEmbeddings
});

const captioner = await pipeline('image-to-text');
const caption = await captioner('image.jpg');

const docQA = await pipeline('document-question-answering');
const answer = await docQA('document-image.jpg', 'What is the total amount?');

const detector = await pipeline('zero-shot-object-detection');
const objects = await detector('image.jpg', ['person', 'car', 'tree']);

const extractor = await pipeline('feature-extraction');
const embeddings = await extractor('This is a sentence to embed.');
// Returns: tensor of shape [1, sequence_length, hidden_size]

// For sentence embeddings (mean pooling)
const extractor = await pipeline('feature-extraction', 'onnx-community/all-MiniLM-L6-v2-ONNX');
const embeddings = await extractor('Text to embed', { pooling: 'mean', normalize: true });

https://huggingface.co/models?library=transformers.js&sort=trending

// 1. Visit: https://huggingface.co/models?pipeline_tag=text-generation&library=transformers.js&sort=trending

// 2. Browse and select a model (e.g., onnx-community/gemma-3-270m-it-ONNX)

// 3. Check model card for:
//    - Model size: ~270M parameters
//    - Quantization: q4 available
//    - Language: English
//    - Use case: Instruction-following chat

// 4. Use the model:
import { pipeline } from '@huggingface/transformers';

const generator = await pipeline(
  'text-generation',
  'onnx-community/gemma-3-270m-it-ONNX',
  { dtype: 'q4' } // Use quantized version for faster inference
);

const output = await generator('Explain quantum computing in simple terms.', {
  max_new_tokens: 100
});

await generator.dispose();

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

// View version
console.log(env.version); // e.g., '3.8.1'

// Common settings
env.allowRemoteModels = true;  // Load from Hugging Face Hub
env.allowLocalModels = false;  // Load from file system
env.localModelPath = '/models/'; // Local model directory
env.useFSCache = true;         // Cache models on disk (Node.js)
env.useBrowserCache = true;    // Cache models in browser
env.cacheDir = './.cache';     // Cache directory location

// Development: Fast iteration with remote models
env.allowRemoteModels = true;
env.useFSCache = true;

// Production: Local models only
env.allowRemoteModels = false;
env.allowLocalModels = true;
env.localModelPath = '/app/models/';

// Custom CDN
env.remoteHost = 'https://cdn.example.com/models';

// Disable caching (testing)
env.useFSCache = false;
env.useBrowserCache = false;

import { AutoTokenizer, AutoModel } from '@huggingface/transformers';

// Load tokenizer and model separately for more control
const tokenizer = await AutoTokenizer.from_pretrained('bert-base-uncased');
const model = await AutoModel.from_pretrained('bert-base-uncased');

// Tokenize input
const inputs = await tokenizer('Hello world!');

// Run model
const outputs = await model(inputs);

const classifier = await pipeline('sentiment-analysis');

// Process multiple texts
const results = await classifier([
  'I love this!',
  'This is terrible.',
  'It was okay.'
]);

const pipe = await pipeline('text-generation', 'onnx-community/gemma-3-270m-it-ONNX', {
  device: 'webgpu',
  dtype: 'fp32'
});

// Optimized for browsers with quantization
const pipe = await pipeline('sentiment-analysis', 'model-id', {
  dtype: 'q8'  // or 'q4' for even smaller size
});

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

// Track progress for each file
const fileProgress = {};

function onProgress(info) {
  console.log(`${info.status}: ${info.file}`);
  
  if (info.status === 'progress') {
    fileProgress[info.file] = info.progress;
    console.log(`${info.file}: ${info.progress.toFixed(1)}%`);
  }
  
  if (info.status === 'done') {
    console.log(`✓ ${info.file} complete`);
  }
}

// Pass callback to pipeline
const classifier = await pipeline('sentiment-analysis', null, {
  progress_callback: onProgress
});

interface ProgressInfo {
  status: 'initiate' | 'download' | 'progress' | 'done' | 'ready';
  name: string;      // Model id or path
  file: string;      // File being processed
  progress?: number; // Percentage (0-100, only for 'progress' status)
  loaded?: number;   // Bytes downloaded (only for 'progress' status)
  total?: number;    // Total bytes (only for 'progress' status)
}

try {
  const pipe = await pipeline('sentiment-analysis', 'model-id');
  const result = await pipe('text to analyze');
} catch (error) {
  if (error.message.includes('fetch')) {
    console.error('Model download failed. Check internet connection.');
  } else if (error.message.includes('ONNX')) {
    console.error('Model execution failed. Check model compatibility.');
  } else {
    console.error('Unknown error:', error);
  }
}

const pipe = await pipeline('sentiment-analysis');
const result = await pipe('Great product!');
await pipe.dispose();  // ✓ Free memory (100MB - several GB per model)