> ## 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**](../modules/chunking) module.

<Badge color="blue">AI Agent</Badge>

A unified class for text chunking with various chunking strategies.

## Constructor

<ParamField query="chunker_type" type="str" required={false} default="'token'">
  No description available.
</ParamField>

<ParamField query="chunk_size" type="int" required={false} default="512">
  No description available.
</ParamField>

<ParamField query="chunk_overlap" type="int" required={false} default="128">
  No description available.
</ParamField>

<ParamField query="tokenizer_or_token_counter" type="str" required={false} default="'gpt2'">
  No description available.
</ParamField>

<ParamField query="embedding_model" type="Optional" required={false}>
  No description available.
</ParamField>

## Methods

<CardGroup cols={2}>
  <Card title="SUPPORTED_CHUNKERS()" icon="function" href="../functions/Chunking-SUPPORTED_CHUNKERS">
    Lazy load chunker classes.
  </Card>

  <Card title="embedding_model()" icon="function" href="../functions/Chunking-embedding_model">
    Lazy load the embedding model.
  </Card>

  <Card title="chunker()" icon="function" href="../functions/Chunking-chunker">
    Lazy load the chunker instance.
  </Card>

  <Card title="chunk()" icon="function" href="../functions/Chunking-chunk">
    Chunk text using the configured chunking strategy.
  </Card>
</CardGroup>

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/knowledge/chunking.py#L5">
  `praisonaiagents/knowledge/chunking.py` at line 5
</Card>