Xenova/bge-base-en-v1.5

使用方法 (Transformers.js)

如果还没有安装，可以从 NPM 安装 Transformers.js JavaScript 库：

npm i @huggingface/transformers

然后可以按如下方式使用模型计算嵌入向量：

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

// 创建特征提取管道
const extractor = await pipeline('feature-extraction', 'Xenova/bge-base-en-v1.5');

// 计算句子嵌入向量
const texts = ['Hello world.', 'Example sentence.'];
const embeddings = await extractor(texts, { pooling: 'mean', normalize: true });
console.log(embeddings);
// Tensor {
//   dims: [ 2, 768 ],
//   type: 'float32',
//   data: Float32Array(1536) [ 0.019079938530921936, 0.041718777269124985, ... ],
//   size: 1536
// }

console.log(embeddings.tolist()); // 将嵌入向量转换为 JavaScript 列表
// [
//   [ 0.019079938530921936, 0.041718777269124985, 0.037672195583581924, ... ],
//   [ 0.020936904475092888, 0.020080938935279846, -0.00787576474249363, ... ]
// ]

你也可以使用该模型进行检索。例如：

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

// 创建特征提取管道
const extractor = await pipeline('feature-extraction', 'Xenova/bge-base-en-v1.5');

// 要嵌入的文档列表
const texts = [
    'Hello world.',
    'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.',
    'I love pandas so much!',
];

// 计算句子嵌入向量
const embeddings = await extractor(texts, { pooling: 'mean', normalize: true });

// 预先添加推荐的查询指令用于检索
const query_prefix = 'Represent this sentence for searching relevant passages: '
const query = query_prefix + 'What is a panda?';
const query_embeddings = await extractor(query, { pooling: 'mean', normalize: true });

// 按余弦相似度分数排序
const scores = embeddings.tolist().map(
    (embedding, i) => ({
        id: i,
        score: cos_sim(query_embeddings.data, embedding),
        text: texts[i],
    })
).sort((a, b) => b.score - a.score);
console.log(scores);
// [
//   { id: 1, score: 0.7787772374597298, text: 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.' },
//   { id: 2, score: 0.7071589521880506, text: 'I love pandas so much!' },
//   { id: 0, score: 0.4252782730390429, text: 'Hello world.' }
// ]

注意：为 ONNX 权重创建单独的仓库是一个临时解决方案，直到 WebML 获得更多关注。如果你希望使模型能够支持 Web 端，我们建议使用 🤗 Optimum 转换为 ONNX 格式，并像此仓库这样构建（将 ONNX 权重存放在名为 onnx 的子文件夹中）。