承接 rahul900day/tiktoken-php 相关项目开发

从需求分析到上线部署,全程专人跟进,保证项目质量与交付效率

邮箱:yvsm@zunyunkeji.com | QQ:316430983 | 微信:yvsm316

rahul900day/tiktoken-php

最新稳定版本:1.0.0

Composer 安装命令:

composer require rahul900day/tiktoken-php

包简介

README 文档

README

Most compatible PHP implementation of OpenAI's original Tiktoken.

Get Started

Requires PHP 8.1+

Install Tiktoken via Composer package manager.

composer require rahul900day/tiktoken-php

Supported Models

Model Supported
GPT-3
GPT-3.5 & 4
GPT-4o

Usage

Basic Usage

use Rahul900day\Tiktoken\Tiktoken;

$encoder = Tiktoken::getEncodingForModel('gpt-4');
$encoder->encode("hello world aaaaaaaaaaaa");
$encoder->decode([9906, 4435]);

Special Tokens

use Rahul900day\Tiktoken\Tiktoken;

$encoder = Tiktoken::getEncodingForModel('gpt-4');
$encoder->encode('<|endoftext|>', allowedSpecial: 'all');

Caching

Tiktoken always cache the server's responses when downloading them.

By default it uses the system's default temporary directory to cache a response but you can still overwrite the cache location by setting TIKTOKEN_CACHE_DIR environment variable.

Registering Custom Encoding

use Rahul900day\Tiktoken\Encodings\OpenAiPublic\Cl100KBaseEncoding;

class Cl100KIm extends Cl100KBaseEncoding 
{
    protected function getName(): string
    {
        return 'cl100k_im';
    }
    
    protected function getSpecialTokens(): array
    {
        return [
            ...parent::getSpecialTokens(),
            "<|im_start|>" => 100264,
            "<|im_end|>" => 100265,
        ];
    }
}

use Rahul900day\Tiktoken\Registry;
use Rahul900day\Tiktoken\Tiktoken;

Registry::registerCustomEncoding('cl100k_im', new Cl100KIm);
$encoding = Tiktoken::getEncoding('cl100k_im');

// Expect: 100264
$encoding->encode("<|im_start|>", allowedSpecial: 'all');

Changelog

Please see CHANGELOG for more information on what has changed recently.

Security Vulnerabilities

Please review our security policy on how to report security vulnerabilities.

Credits

License

This package is released under the MIT License.

统计信息

  • 总下载量: 6.02k
  • 月度下载量: 0
  • 日度下载量: 0
  • 收藏数: 7
  • 点击次数: 1
  • 依赖项目数: 0
  • 推荐数: 0

GitHub 信息

  • Stars: 7
  • Watchers: 1
  • Forks: 0
  • 开发语言: PHP

其他信息

  • 授权协议: MIT
  • 更新时间: 2024-06-16