EnergeticAI Core

EnergeticAI is a distribution of TensorFlow.js optimized for serverless functions:

• small module size (~3 MB vs. 146 MB - 513 MB for stock TensorFlow.js)
• fast cold-start inference (~50 ms vs. 2000+ ms for stock TensorFlow.js)
• incredible ease-of-use (pre-trained models for common cases)

It's intended to be a condensed replacement for TensorFlow.js, so you can use it with much existing code and models.

Install

EnergeticAI is available on NPM.

Install this core package, along with any model libraries you want to use (e.g. embeddings):

npm install @energetic-ai/core @energetic-ai/embeddings @energetic-ai/model-embeddings-en

You can see a full list of packages below.

Usage

Here's an example of using the embeddings model:

import { initModel, distance } from "@energetic-ai/embeddings";
import { modelSource } from "@energetic-ai/model-embeddings-en";
(async () => {
  const model = await initModel(modelSource);
  const embeddings = await model.embed(["hello", "world"]);
  console.log(distance(embeddings[0], embeddings[1])));
})();

Examples

See the examples directory for examples.

Development

This repository uses Lerna to manage packages, and Vitest to run tests.

License

Apache 2.0, except for dependencies.

Acknowledgements

This project is derived from TensorFlow.js which is also Apache 2.0 licensed.