Libraries tagged by tokeniser

A consistent interface to tokenize, analyse and modify any text format. Programming languages, natural languages, markup languages

Go to Download

PHP version of tiktoken

Go to Download

Simple tokenizer that allows you to use .ss template like variables in a dataobjects string.

Go to Download

PHP version of tiktoken

Go to Download

Another class loader using PHP tokenizer

Go to Download

PHP BPE Text Encoder/Decoder for GPT-2 / GPT-3. Based on coderevolutionplugins/gpt-3-encoder-php

Go to Download

Tokenizer-agnostic text preprocessor for trimming and optimising content for LLM context windows.

Go to Download

Turn everything into a unique encrypted JWT.

Go to Download

A collection of fast and easy to use attributed string classes for PHP. Attributed strings can have multiple attributes for each character of the string and are for example used for word processors and natural language processing.

Go to Download

Serialize Closure objects, including their context and binding

Go to Download

nikic/php-parser for HTML — an immutable HTML5 AST with positions, trivia, visitors, and a fidelity printer

Go to Download

Library emulating the PHP internal reflection using just the tokenized source code.

Go to Download

Doing interesting things with closures like serialization.

Go to Download

Turn everything into a token: randomized or predictable.

Go to Download

Implements Iterator interface over a String for extract data with an array of tokens. The name comes from Mage and tokenizer :)

Go to Download