bge m3 EU AI Act Compliance Profile

https://huggingface.co/BAAI/bge-m3 with ONNX weights to be compatible with Transformers.js.

Usage (Transformers.js)

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

You can then use the model to compute embeddings, as follows:

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

// Create a feature-extraction pipeline
const extractor = await pipeline('feature-extraction', 'Xenova/bge-m3');

// Compute sentence embeddings
const texts = ["What is BGE M3?", "Defination of BM25"]
const embeddings = await extractor(texts, { pooling: 'cls', normalize: true });
console.log(embeddings);
// Tensor {
//   dims: [ 2, 1024 ],
//   type: 'float32',
//   data: Float32Array(2048) [ -0.0340719036757946, -0.04478546231985092, ... ],
//   size: 2048
// }

console.log(embeddings.tolist()); // Convert embeddings to a JavaScript list
// [
//   [ -0.0340719036757946, -0.04478546231985092, -0.004497686866670847, ... ],
//   [ -0.015383965335786343, -0.041989751160144806, -0.025820579379796982, ... ]
// ]

You can also use the model for retrieval. For example:

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

// Create a feature-extraction pipeline
const extractor = await pipeline('feature-extraction', 'Xenova/bge-m3');

// Define query to use for retrieval
const query = 'What is BGE M3?';

// List of documents you want to embed
const texts = [
  'BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.',
  'BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document',
];

// Compute sentence embeddings
const embeddings = await extractor(texts, { pooling: 'cls', normalize: true });

// Compute query embeddings
const query_embeddings = await extractor

Your obligations as a bge m3 deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Library

Base Model