⏳ tiktoken

tiktoken is a BPE tokeniser for use with OpenAI's models, forked from the original tiktoken library to provide NPM bindings for Node and other JS runtimes.

The open source version of tiktoken can be installed from NPM:

npm install @dqbd/tiktoken

Usage

Basic usage follows:

import assert from "node:assert";
import { get_encoding, encoding_for_model } from "@dqbd/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,
});

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+"
);

Compatibility

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 caveats | | Vercel Edge Runtime | 🚧 | Work in progress | | Cloudflare Workers | 🚧 | Untested | | Deno | ❌ | Currently unsupported |

Vite

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()],
});

Next.js

Both API routes and /pages are supported with some caveats. To overcome issues with importing /node variant and incorrect __dirname resolution, you can import the package from @dqbd/tiktoken/bundler instead.

import { get_encoding } from "@dqbd/tiktoken/bundler";
import { NextApiRequest, NextApiResponse } from "next";

export default function handler(req: NextApiRequest, res: NextApiResponse) {
  return res.status(200).json({
    // eslint-disable-next-line @typescript-eslint/no-unsafe-assignment
    message: get_encoding("gpt2").encode(`Hello World ${Math.random()}`),
  });
}

Additional Webpack configuration is also required, see https://github.com/vercel/next.js/issues/29362.

class WasmChunksFixPlugin {
  apply(compiler) {
    compiler.hooks.thisCompilation.tap("WasmChunksFixPlugin", (compilation) => {
      compilation.hooks.processAssets.tap(
        { name: "WasmChunksFixPlugin" },
        (assets) =>
          Object.entries(assets).forEach(([pathname, source]) => {
            if (!pathname.match(/\.wasm$/)) return;
            compilation.deleteAsset(pathname);

            const name = pathname.split("/")[1];
            const info = compilation.assetsInfo.get(pathname);
            compilation.emitAsset(name, source, info);
          })
      );
    });
  }
}

const config = {
  webpack(config, { isServer, dev }) {
    config.experiments = {
      asyncWebAssembly: true,
      layers: true,
    };

    if (!dev && isServer) {
      config.output.webassemblyModuleFilename = "chunks/[id].wasm";
      config.plugins.push(new WasmChunksFixPlugin());
    }

    return config;
  },
};

To properly resolve tsconfig.json, use either moduleResolution: "node16" or moduleResolution: "nodenext":

{
  "compilerOptions": {
    "moduleResolution": "node16"
  }
}

Acknowledgements

• https://github.com/zurawiki/tiktoken-rs