# Chunk a PDF into 800-token pieces for RAG ingestion

**Use case:** 

Converts a research paper PDF to Markdown and splits it into heading-aware chunks of about 800 tokens with an 80-token overlap. Each chunk record carries its index, start and end page, heading path and token estimate, ready to embed into a vector store with page citations.

## Input

```json
{
  "urls": [
    "https://arxiv.org/pdf/1706.03762v7"
  ],
  "chunk": true,
  "chunkTokens": 800,
  "chunkOverlapTokens": 80,
  "ocr": false,
  "saveToKeyValueStore": false,
  "pageBreaks": true,
  "maxFileSizeMb": 25,
  "downloadTimeoutSecs": 20
}
```

## Output

```json
{
  "recordType": {
    "label": "Type",
    "format": "text"
  },
  "filename": {
    "label": "File",
    "format": "text"
  },
  "url": {
    "label": "URL",
    "format": "link"
  },
  "pages": {
    "label": "Pages",
    "format": "number"
  },
  "title": {
    "label": "Title",
    "format": "text"
  },
  "words": {
    "label": "Words",
    "format": "number"
  },
  "tables": {
    "label": "Tables",
    "format": "number"
  },
  "chunkIndex": {
    "label": "Chunk #",
    "format": "number"
  },
  "error": {
    "label": "Error",
    "format": "text"
  }
}
```

## How it works

### 1. Sign up on Apify or log in

The PDF & DOCX to Markdown Converter for AI Agents Actor is ready to run with the inputs already set for "Chunk a PDF into 800-token pieces for RAG ingestion". [Sign up or log in](https://console.apify.com/create-task-from-example/zNcVR8m5duUOAzTlv) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Chunk a PDF into 800-token pieces for RAG ingestion" task

The PDF & DOCX to Markdown Converter for AI Agents Actor will start running based on the input automatically. You can also change all the input fields, like document urls, create rag chunks, and more, to match your specific use case.

### 3. Receive the "Chunk a PDF into 800-token pieces for RAG ingestion" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as type, file, URL, and more.

### 4. Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also [run the "Chunk a PDF into 800-token pieces for RAG ingestion" task via API](https://apify.com/owlabee/pdf-to-markdown.md).

## About this Actor

This example demonstrates how to use [PDF & DOCX to Markdown Converter for AI Agents](https://apify.com/owlabee/pdf-to-markdown.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/owlabee/pdf-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/owlabee/pdf-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`).