legacyphpdoctor/tiktoken-php-7-4

PHP version of tiktoken

dev-master 2025-08-06 21:00 UTC

Requires

• php: ^7.4 || 8.1
• symfony/service-contracts: ^2.5 || ^3.0

Requires (Dev)

• doctrine/coding-standard: ^13
• mikey179/vfsstream: ^1.6.11
• phpbench/phpbench: ^1.2
• phpunit/phpunit: ^9
• psalm/plugin-phpunit: ^0.18
• vimeo/psalm: 5.26

Suggests

• ext-ffi: To allow use LibEncoder

MIT

• tokenizer
• encode
• decode
• bpe
• openai
• tiktoken

README

⚠️ This repository is a PHP 7.4 compatible fork of yethee/tiktoken-php.

Installation

$ composer require legacyphpdoctor/tiktoken-php-7-4

tiktoken-php

This is a port of the tiktoken.

Installation

$ composer require yethee/tiktoken

Usage

use Yethee\Tiktoken\EncoderProvider;

$provider = new EncoderProvider();

$encoder = $provider->getForModel('gpt-3.5-turbo-0301');
$tokens = $encoder->encode('Hello world!');
print_r($tokens);
// OUT: [9906, 1917, 0]

$encoder = $provider->get('p50k_base');
$tokens = $encoder->encode('Hello world!');
print_r($tokens);
// OUT: [15496, 995, 0]

Cache

The encoder uses an external vocabularies, so caching is used by default to avoid performance issues.

By default, the directory for temporary files is used. You can override the directory for cache via environment variable TIKTOKEN_CACHE_DIR or use EncoderProvider::setVocabCache():

use Yethee\Tiktoken\EncoderProvider;

$encProvider = new EncoderProvider();
$encProvider->setVocabCache('/path/to/cache');

// Using the provider

Lib mode

Experimental

You can use tiktoken-rs library via FFI binding. This can improve performance when need to encode medium or large texts. However, the overhead of data marshalling can lead to poor performance for small texts.

use Yethee\Tiktoken\Encoder\LibEncoder;
use Yethee\Tiktoken\EncoderProvider;

// LibEncoder::init('/path/to/lib');

$encProvider = new EncoderProvider(true); // Force using the lib encoder

You need to provide path to the lib before using the provider. There are several ways to do this:

• Use Yethee\Tiktoken\Encoder\LibEncoder::init() method.
• Use Yethee\Tiktoken\Encoder\LibEncoder::preload() method, inside opcache preload script.
• Use environment variable TIKTOKEN_LIB_PATH or LD_LIBRARY_PATH

Build lib

Requirements

• Rust >= 1.85

git clone [e-mail]:yethee/tiktoken-php.git
cd tiktoken-php
cargo build --release

Copy binary from target/release:

• libtiktoken_php.so for linux
• libtiktoken_php.dylib for MacOS
• tiktoken_php.dll for Windows

NOTE: You can see .docker/Dockefile for an example.

Benchmark

You can see benchmark result in #27 or run it locally:

composer bench

TODO

• Add implementation for Yethee\Tiktoken\Encoder\LibEncoder::encodeInChunks() method

Limitations

• Encoding for GPT-2 is not supported.
• Special tokens (like <|endofprompt|>) are not supported.

License

MIT