# Chunk a PDF research paper for RAG

**Use case:** 

Converts an arXiv PDF (Attention Is All You Need) to Markdown and splits it into 512-token, section-aware chunks with header paths, stable IDs and exact token counts, ready to embed into Pinecone, Qdrant or pgvector. Swap in any PDF URL.

## Input

```json
{
  "markdown_file": "https://arxiv.org/pdf/1706.03762",
  "headers_to_split_on": [
    "#",
    "##",
    "###"
  ],
  "max_chunk_tokens": 512,
  "tokenizer": "cl100k_base",
  "strip_headers": true,
  "skip_if_unchanged": false,
  "max_input_chars": 2000000,
  "max_chunks": 5000,
  "use_apify_proxy": false
}
```

## Output

```json
{
  "chunk_index": {
    "label": "Chunk index",
    "format": "integer"
  },
  "header_path": {
    "label": "Header path",
    "format": "string"
  },
  "token_count": {
    "label": "Token count",
    "format": "integer"
  },
  "content": {
    "label": "Content",
    "format": "string"
  },
  "chunk_id": {
    "label": "Chunk ID",
    "format": "string"
  },
  "source": {
    "label": "Source",
    "format": "string"
  }
}
```

## How it works

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

The Markdown RAG Chunker: Document Text Splitter Actor is ready to run with the inputs already set for "Chunk a PDF research paper for RAG". [Sign up or log in](https://console.apify.com/create-task-from-example/xx86XwudSdrvdgUAi) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Chunk a PDF research paper for RAG" task

The Markdown RAG Chunker: Document Text Splitter Actor will start running based on the input automatically. You can also change all the input fields, like document url, headers to split on, and more, to match your specific use case.

### 3. Receive the "Chunk a PDF research paper for RAG" 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 chunk index, header path, token count, 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 research paper for RAG" task via API](https://apify.com/codepoetry/markdown-rag-chunker.md).

## About this Actor

This example demonstrates how to use [Markdown RAG Chunker: Document Text Splitter](https://apify.com/codepoetry/markdown-rag-chunker.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/codepoetry/markdown-rag-chunker.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/codepoetry/markdown-rag-chunker.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`).