README.md

October 18, 2023 · View on GitHub

FastEmbed-js ⚡️

Typescript/NodeJS implementation of @Qdrant/fastembed

🍕 Features

Supports CommonJS and ESM.
Uses @anush008/tokenizers multi-arch native bindings for @huggingface/tokenizers.
Supports batch embedddings with generators.

The default model is Flag Embedding, which is top of the MTEB leaderboard.

🔍 Not looking for Javascript?

Python 🐍: fastembed
Rust 🦀: fastembed-rs
Go 🐳: fastembed-go

🤖 Models

🚀 Installation

To install the FastEmbed library, npm works:

npm install fastembed

📖 Usage

import { EmbeddingModel, FlagEmbedding } from "fastembed";
// For CommonJS
// const { EmbeddingModel, FlagEmbedding } = require("fastembed)

const embeddingModel = await FlagEmbedding.init({
    model: EmbeddingModel.BGEBaseEN
});

let documents = [
    "passage: Hello, World!",
    "query: Hello, World!",
    "passage: This is an example passage.",
    // You can leave out the prefix but it's recommended
    "fastembed-js is licensed under MIT" 
];

const embeddings = embeddingModel.embed(documents, 2); //Optional batch size. Defaults to 256

for await (const batch of embeddings) {
    // batch is list of Float32 embeddings(number[][]) with length 2
    console.log(batch);
}

Supports passage and query embeddings for more accurate results

const embeddings = embeddingModel.passageEmbed(listOfLongTexts, 10); //Optional batch size. Defaults to 256

for await (const batch of embeddings) {
    // batch is list of Float32 passage embeddings(number[][]) with length 10
    console.log(batch);
}

const queryEmbeddings: number[] = await embeddingModel.queryEmbed(userQuery);
console.log(queryEmbeddings)

🚒 Under the hood

Why fast?

It's important we justify the "fast" in FastEmbed. FastEmbed is fast because:

Quantized model weights
ONNX Runtime which allows for inference on CPU, GPU, and other dedicated runtimes