> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Chunking • AI Agent SDK

> Chunking: A unified class for text chunking with various chunking strategies.

# Chunking

> Defined in the [**chunking**](https://praison.ai/docs/sdk/reference/praisonaiagents/modules/chunking.md) module.

AI Agent

A unified class for text chunking with various chunking strategies.

## Constructor

**chunker\_type** `str` (default: 'token')

No description available.

**chunk\_size** `int` (default: 512)

No description available.

**chunk\_overlap** `int` (default: 128)

No description available.

**tokenizer\_or\_token\_counter** `str` (default: 'gpt2')

No description available.

**embedding\_model** `Optional`

No description available.

## Methods

> [card] [SUPPORTED\_CHUNKERS()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Chunking-SUPPORTED_CHUNKERS.md)
>
> Lazy load chunker classes.

> [card] [embedding\_model()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Chunking-embedding_model.md)
>
> Lazy load the embedding model.

> [card] [chunker()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Chunking-chunker.md)
>
> Lazy load the chunker instance.

> [card] [chunk()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/Chunking-chunk.md)
>
> Chunk text using the configured chunking strategy.

## Source

> [card] [View on GitHub](https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/knowledge/chunking.py#L30)
>
> `praisonaiagents/knowledge/chunking.py` at line 30


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.