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

# Chunking

> Prepare extracted content for RAG, search, agents, embeddings, and review queues.

Use chunking when the extraction output will feed retrieval, embeddings, agent context, search indexing, or review queues. Pick the chunking strategy based on how humans naturally use the document.

[Platform sample: Attention Is All You Need](https://platform.runpulse.com/dashboard/examples/3be15d23-d622-4f27-9843-ec2929140eec)

<img src="https://mintcdn.com/pulseai/OJ897TEZf8bV6lk8/images/platform/chunking-config.png?fit=max&auto=format&n=OJ897TEZf8bV6lk8&q=85&s=79aa35c60c606b22a4aeef06d488d6fd" alt="Chunking configuration in the Platform" width="690" height="318" data-path="images/platform/chunking-config.png" />

| Strategy    | Best for                                                              |
| ----------- | --------------------------------------------------------------------- |
| `semantic`  | Narrative documents where topics matter more than page boundaries.    |
| `header`    | Reports, policies, filings, and manuals with useful headings.         |
| `page`      | Legal, regulatory, and audit workflows where page provenance matters. |
| `recursive` | Strict size windows for embedding models or downstream systems.       |

```json theme={null}
{
  "file_url": "https://platform.runpulse.com/api/examples/3be15d23-d622-4f27-9843-ec2929140eec/pdf",
  "extensions": {
    "chunking": {
      "chunk_types": ["semantic", "page"],
      "chunk_size": 1200
    }
  }
}
```

Chunk results are returned under `extensions.chunking`. Keep page chunking on when auditors or users must be able to reconcile an answer back to exact page boundaries.

<CardGroup cols={2}>
  <Card title="Chunking For RAG" icon="scissors" href="/cookbooks/chunking-strategy-rag">
    Choose a retrieval-friendly chunking strategy.
  </Card>

  <Card title="LangChain Vector Store" icon="database" href="/cookbooks/rag-langchain-vector-store">
    Embed chunks with source metadata.
  </Card>
</CardGroup>