# PDF to Markdown chunks for RAG and LLMs

**Use case:** 

Turn PDFs into clean Markdown chunks, ready for a vector database or an AI assistant. Headings and lists are kept, headers, footers and page numbers are removed, and every chunk tells you which pages it came from. Pick the chunk size and overlap you need.

## Input

```json
{
  "urls": [
    "https://arxiv.org/pdf/1706.03762v7"
  ],
  "outputFormat": "markdown",
  "splitBy": "chunk",
  "chunkSize": 2000,
  "chunkOverlap": 200,
  "includePages": false,
  "removeHeadersFooters": true,
  "ocr": false,
  "ocrLanguages": [
    "eng"
  ],
  "maxPdfsPerPage": 20,
  "maxFileSizeMb": 100,
  "maxConcurrency": 3
}
```

## Output

```json
{
  "fileName": {
    "label": "File",
    "format": "text"
  },
  "status": {
    "label": "Status",
    "format": "text"
  },
  "title": {
    "label": "Title",
    "format": "text"
  },
  "pageCount": {
    "label": "Pages",
    "format": "number"
  },
  "pageNumber": {
    "label": "Page",
    "format": "number"
  },
  "chunkIndex": {
    "label": "Chunk",
    "format": "number"
  },
  "charCount": {
    "label": "Characters",
    "format": "number"
  },
  "text": {
    "label": "Text",
    "format": "text"
  },
  "errorMessage": {
    "label": "Problem",
    "format": "text"
  },
  "url": {
    "label": "URL",
    "format": "link"
  }
}
```

## About this Actor

This example demonstrates how to use [PDF Text Extractor: PDF and Image to Text, with OCR](https://apify.com/vindr/pdf-text-extractor.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/vindr/pdf-text-extractor.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/vindr/pdf-text-extractor.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`).