Skip to main content
Version: 0.10.0

Function: createTokenizer()

createTokenizer(tokenizerPath, runtime?): Promise<{ decode: (...args) => Promise<string>; dispose: () => void; encode: (...args) => Promise<Int32Array<ArrayBufferLike>>; getVocabSize: () => number; idToToken: (id) => string; tokenToId: (token) => number; }>

Defined in: extensions/nlp/tasks/tokenization.ts:19

Loads a tokenizer and exposes its operations with lifetime management for the useTokenizer hook.

Parameters

tokenizerPath

string

Absolute local path to a tokenizer.json file.

runtime?

any

Optional worklet runtime thread to run the tokenizer on.

Returns

Promise<{ decode: (...args) => Promise<string>; dispose: () => void; encode: (...args) => Promise<Int32Array<ArrayBufferLike>>; getVocabSize: () => number; idToToken: (id) => string; tokenToId: (token) => number; }>

A promise resolving to the instantiated tokenizer operations and disposal controls.