The TokenChunker splits text into chunks based on token count, ensuring each chunk stays within specified token limits. It is ideal for preparing text for models with token limits, or for consistent chunking across different texts.

​
API Reference

To use the TokenChunker via the API, check out the API reference documentation.

​
Initialization

import { TokenChunker } from "chonkie";

// Basic initialization with default parameters (async)
const chunker = await TokenChunker.create({
  tokenizer: "Xenova/gpt2", // Supports string identifiers or Tokenizer instance
  chunkSize: 2048,            // Maximum tokens per chunk
  chunkOverlap: 128          // Overlap between chunks
});

// Using a custom tokenizer
import { Tokenizer } from "@huggingface/transformers";
const customTokenizer = await Tokenizer.from_pretrained("your-tokenizer");
const chunker = await TokenChunker.create({
  tokenizer: customTokenizer,
  chunkSize: 2048,
  chunkOverlap: 128
});

​
Parameters

​
tokenizer
string | Tokenizer
default:"Xenova/gpt2"
Tokenizer to use. Can be a string identifier (model name) or a Tokenizer instance. Defaults to using Xenova/gpt2 tokenizer.
​
chunkSize
number
default:"2048"
Maximum number of tokens per chunk.
​
chunkOverlap
number
default:"0"
Number or percentage of overlapping tokens between chunks. Can be an absolute number (e.g., 16) or a decimal between 0 and 1 (e.g., 0.1 for 10% overlap).
​
returnType
'chunks' | 'texts'
default:"chunks"
Whether to return chunks as Chunk objects (with metadata) or plain text strings.

​
Usage

​
Single Text Chunking

const text = "Some long text that needs to be chunked into smaller pieces...";
const chunks = await chunker.chunk(text);

for (const chunk of chunks) {
  console.log(`Chunk text: ${chunk.text}`);
  console.log(`Token count: ${chunk.tokenCount}`);
  console.log(`Start index: ${chunk.startIndex}`);
  console.log(`End index: ${chunk.endIndex}`);
}

​
Batch Chunking

const texts = [
  "First document to chunk...",
  "Second document to chunk..."
];
const batchChunks = await chunker.chunkBatch(texts);

for (const docChunks of batchChunks) {
  for (const chunk of docChunks) {
    console.log(`Chunk: ${chunk.text}`);
  }
}

​
Using as a Callable

// Single text
const chunks = await chunker("Text to chunk...");

// Multiple texts
const batchChunks = await chunker(["Text 1...", "Text 2..."]);

​
Return Type

TokenChunker returns chunks as Chunk objects by default. Each chunk includes metadata: 
class Chunk {
  text: string;        // The chunk text
  startIndex: number;  // Starting position in original text
  endIndex: number;    // Ending position in original text
  tokenCount: number;  // Number of tokens in chunk
}
If returnType is set to 'texts', only the chunked text strings are returned.
For more details, see the TypeScript API Reference.