tiktoken is a BPE tokeniser for use with OpenAI's models, forked from the original tiktoken library to provide JS/WASM bindings for NodeJS and other JS runtimes.
This repository contains the following packages:
tiktoken
(formally hosted at@dqbd/tiktoken
): WASM bindings for the original Python library, providing full 1-to-1 feature parity.js-tiktoken
: Pure JavaScript port of the original library with the core functionality, suitable for environments where WASM is not well supported or not desired (such as edge runtimes).
Documentation for js-tiktoken
can be found in here. Documentation for the tiktoken
can be found here below.
The WASM version of tiktoken
can be installed from NPM:
npm install tiktoken
Basic usage follows, which includes all the OpenAI encoders and ranks:
import assert from "node:assert";
import { get_encoding, encoding_for_model } from "tiktoken";
const enc = get_encoding("gpt2");
assert(
new TextDecoder().decode(enc.decode(enc.encode("hello world"))) ===
"hello world"
);
// To get the tokeniser corresponding to a specific model in the OpenAI API:
const enc = encoding_for_model("text-davinci-003");
// Extend existing encoding with custom special tokens
const enc = encoding_for_model("gpt2", {
"<|im_start|>": 100264,
"<|im_end|>": 100265,
});
// don't forget to free the encoder after it is not used
enc.free();
In constrained environments (eg. Edge Runtime, Cloudflare Workers), where you don't want to load all the encoders at once, you can use the lightweight WASM binary via tiktoken/lite
.
const { Tiktoken } = require("tiktoken/lite");
const cl100k_base = require("tiktoken/encoders/cl100k_base.json");
const encoding = new Tiktoken(
cl100k_base.bpe_ranks,
cl100k_base.special_tokens,
cl100k_base.pat_str
);
const tokens = encoding.encode("hello world");
encoding.free();
If you want to fetch the latest ranks, use the load
function:
const { Tiktoken } = require("tiktoken/lite");
const { load } = require("tiktoken/load");
const registry = require("tiktoken/registry.json");
const models = require("tiktoken/model_to_encoding.json");
async function main() {
const model = await load(registry[models["gpt-3.5-turbo"]]);
const encoder = new Tiktoken(
model.bpe_ranks,
model.special_tokens,
model.pat_str
);
const tokens = encoder.encode("hello world");
encoder.free();
}
main();
If desired, you can create a Tiktoken instance directly with custom ranks, special tokens and regex pattern:
import { Tiktoken } from "../pkg";
import { readFileSync } from "fs";
const encoder = new Tiktoken(
readFileSync("./ranks/gpt2.tiktoken").toString("utf-8"),
{ "<|endoftext|>": 50256, "<|im_start|>": 100264, "<|im_end|>": 100265 },
"'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)|\\s+"
);
Finally, you can a custom init
function to override the WASM initialization logic for non-Node environments. This is useful if you are using a bundler that does not support WASM ESM integration.
import { get_encoding, init } from "tiktoken/init";
async function main() {
const wasm = "..."; // fetch the WASM binary somehow
await init((imports) => WebAssembly.instantiate(wasm, imports));
const encoding = get_encoding("cl100k_base");
const tokens = encoding.encode("hello world");
encoding.free();
}
main();
As this is a WASM library, there might be some issues with specific runtimes. If you encounter any issues, please open an issue.
Runtime | Status | Notes |
---|---|---|
Node.js | ✅ | |
Bun | ✅ | |
Vite | ✅ | See here for notes |
Next.js | ✅ | See here for notes |
Create React App (via Craco) | ✅ | See here for notes |
Vercel Edge Runtime | ✅ | See here for notes |
Cloudflare Workers | ✅ | See here for notes |
Electron | ✅ | See here for notes |
Deno | ❌ | Currently unsupported (see dqbd/tiktoken#22) |
Svelte + Cloudflare Workers | ❌ | Currently unsupported (see dqbd/tiktoken#37) |
For unsupported runtimes, consider using js-tiktoken
, which is a pure JS implementation of the tokeniser.
If you are using Vite, you will need to add both the vite-plugin-wasm
and vite-plugin-top-level-await
. Add the following to your vite.config.js
:
import wasm from "vite-plugin-wasm";
import topLevelAwait from "vite-plugin-top-level-await";
import { defineConfig } from "vite";
export default defineConfig({
plugins: [wasm(), topLevelAwait()],
});
Both API routes and /pages
are supported with the following next.config.js
configuration.
// next.config.json
const config = {
webpack(config, { isServer, dev }) {
config.experiments = {
asyncWebAssembly: true,
layers: true,
};
return config;
},
};
Usage in pages:
import { get_encoding } from "tiktoken";
import { useState } from "react";
const encoding = get_encoding("cl100k_base");
export default function Home() {
const [input, setInput] = useState("hello world");
const tokens = encoding.encode(input);
return (
<div>
<input
type="text"
value={input}
onChange={(e) => setInput(e.target.value)}
/>
<div>{tokens.toString()}</div>
</div>
);
}
Usage in API routes:
import { get_encoding } from "tiktoken";
import { NextApiRequest, NextApiResponse } from "next";
export default function handler(req: NextApiRequest, res: NextApiResponse) {
const encoding = get_encoding("cl100k_base");
const tokens = encoding.encode("hello world");
encoding.free();
return res.status(200).json({ tokens });
}
By default, the Webpack configugration found in Create React App does not support WASM ESM modules. To add support, please do the following:
- Swap
react-scripts
withcraco
, using the guide found here: https://craco.js.org/docs/getting-started/. - Add the following to
craco.config.js
:
module.exports = {
webpack: {
configure: (config) => {
config.experiments = {
asyncWebAssembly: true,
layers: true,
};
// turn off static file serving of WASM files
// we need to let Webpack handle WASM import
config.module.rules
.find((i) => "oneOf" in i)
.oneOf.find((i) => i.type === "asset/resource")
.exclude.push(/\.wasm$/);
return config;
},
},
};
Vercel Edge Runtime does support WASM modules by adding a ?module
suffix. Initialize the encoder with the following snippet:
// @ts-expect-error
import wasm from "tiktoken/lite/tiktoken_bg.wasm?module";
import model from "tiktoken/encoders/cl100k_base.json";
import { init, Tiktoken } from "tiktoken/lite/init";
export const config = { runtime: "edge" };
export default async function (req: Request) {
await init((imports) => WebAssembly.instantiate(wasm, imports));
const encoding = new Tiktoken(
model.bpe_ranks,
model.special_tokens,
model.pat_str
);
const tokens = encoding.encode("hello world");
encoding.free();
return new Response(`${tokens}`);
}
Similar to Vercel Edge Runtime, Cloudflare Workers must import the WASM binary file manually and use the tiktoken/lite
version to fit the 1 MB limit. However, users need to point directly at the WASM binary via a relative path (including ./node_modules/
).
Add the following rule to the wrangler.toml
to upload WASM during build:
[[rules]]
globs = ["**/*.wasm"]
type = "CompiledWasm"
Initialize the encoder with the following snippet:
import { init, Tiktoken } from "tiktoken/lite/init";
import wasm from "./node_modules/tiktoken/lite/tiktoken_bg.wasm";
import model from "tiktoken/encoders/cl100k_base.json";
export default {
async fetch() {
await init((imports) => WebAssembly.instantiate(wasm, imports));
const encoder = new Tiktoken(
model.bpe_ranks,
model.special_tokens,
model.pat_str
);
const tokens = encoder.encode("test");
encoder.free();
return new Response(`${tokens}`);
},
};
To use tiktoken in your Electron main process, you need to make sure the WASM binary gets copied into your application package.
Assuming a setup with Electron Forge and @electron-forge/plugin-webpack
, add the following to your webpack.main.config.js
:
const CopyPlugin = require("copy-webpack-plugin");
module.exports = {
// ...
plugins: [
new CopyPlugin({
patterns: [
{ from: "./node_modules/tiktoken/tiktoken_bg.wasm" },
],
}),
],
};
To build the tiktoken
library, make sure to have:
- Rust and
wasm-pack
installed. - Node.js 18+ is required to build the JS bindings and fetch the latest encoder ranks via
fetch
.
Install all the dev-dependencies with yarn install
and build both WASM binary and JS bindings with yarn build
.