# Split a PDF into RAG chunks (Bitcoin whitepaper example)

**Use case:** 

Convert the Bitcoin whitepaper PDF into 28 Markdown chunks of about 1,000 characters with 100 characters of overlap. Each chunk is one dataset row with its heading path and index, ready to embed in a vector database. You pay once per document, not per chunk.

## Input

```json
{
  "urls": [
    "https://bitcoin.org/bitcoin.pdf"
  ],
  "base64Documents": [
    {
      "fileName": "hello.csv",
      "data": "bmFtZSxjaXR5CkFkYSxMb25kb24K"
    }
  ],
  "chunkSize": 1000,
  "chunkOverlap": 100,
  "outputMode": "chunks",
  "maxConcurrency": 10,
  "httpVia": "auto",
  "pdfCleanup": true,
  "ocr": false,
  "ocrMaxPages": 20
}
```

## Output

```json
{
  "url": {
    "label": "URL",
    "format": "link"
  },
  "input": {
    "label": "Input"
  },
  "fileName": {
    "label": "File name"
  },
  "success": {
    "label": "Success"
  },
  "status": {
    "label": "Status"
  },
  "charged": {
    "label": "Charged"
  },
  "contentType": {
    "label": "Content type"
  },
  "bytes": {
    "label": "Bytes"
  },
  "wordCount": {
    "label": "Word count"
  },
  "characters": {
    "label": "Characters"
  },
  "markdown": {
    "label": "Markdown"
  },
  "error": {
    "label": "Error"
  }
}
```

## About this Actor

This example demonstrates how to use [PDF Text Extractor & PDF to Markdown - OCR, Word, Excel](https://apify.com/tidytools/document-to-markdown.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/tidytools/document-to-markdown.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/tidytools/document-to-markdown.md

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).