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

// Create feature extraction pipeline
const extractor = await pipeline('feature-extraction', 'Xenova/jina-embeddings-v2-small-en',
    { dtype: "fp32" } // Options: "fp32", "fp16", "q8", "q4"
);

// Generate embeddings
const output = await extractor(
    ['How is the weather today?', 'What is the current weather like today?'],
    { pooling: 'mean' }
);

// Compute cosine similarity
console.log(cos_sim(output[0].data, output[1].data));  // 0.9399812684139274 (unquantized) vs. 0.9341121503699659 (quantized)

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).