# Convert a PDF to Markdown chunks for RAG

**Use case:** 

Convert a PDF (here the 'Attention Is All You Need' paper) into clean Markdown split into chunks by heading, with page numbers and heading paths as metadata, ready to embed into a vector database for RAG. Replace the link with your own PDF, Word, PowerPoint or Excel files, or point it at a whole list of documents.

## Input

```json
{
  "urls": [
    {
      "url": "https://arxiv.org/pdf/1706.03762"
    }
  ],
  "datasetUrlField": "url",
  "outputFormat": "markdown",
  "chunking": "heading",
  "chunkSize": 800,
  "chunkSizeUnit": "tokens",
  "chunkOverlap": 100,
  "includePageNumbers": true,
  "includeSpeakerNotes": true,
  "ocr": false,
  "ocrLanguages": [
    "eng"
  ],
  "maxPagesPerDocument": 0,
  "maxDocuments": 1000,
  "maxFileSizeMb": 100
}
```

## Output

```json
{
  "fileName": {
    "label": "File"
  },
  "fileType": {
    "label": "Type"
  },
  "chunkIndex": {
    "label": "Chunk",
    "format": "number"
  },
  "metadata.pageStart": {
    "label": "Page from",
    "format": "number"
  },
  "metadata.pageEnd": {
    "label": "Page to",
    "format": "number"
  },
  "metadata.headingPath": {
    "label": "Section"
  },
  "tokenCount": {
    "label": "Tokens",
    "format": "number"
  },
  "text": {
    "label": "Text"
  },
  "documentUrl": {
    "label": "Full Markdown",
    "format": "link"
  },
  "status": {
    "label": "Status"
  },
  "error": {
    "label": "Error"
  }
}
```

## About this Actor

This example demonstrates how to use [Document to Markdown for AI & RAG](https://apify.com/egra_van/document-to-markdown.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/egra_van/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/egra_van/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`).