# Convert a PDF with tables to Markdown and RAG chunks

**Use case:** 

Convert a PDF with a table into clean Markdown with the table kept inline as a Markdown table, plus heading-aware RAG chunks with page numbers for citations. The example uses a public W3C sample PDF; replace it with links to your own PDF, Word (DOCX), PowerPoint (PPTX) or Excel (XLSX) files. One row per document shows pages, tables, words and chunk count.

## Input

```json
{
  "documentUrls": [
    "https://www.w3.org/WAI/WCAG21/working-examples/pdf-table/table.pdf"
  ],
  "outputMode": "documents-and-chunks",
  "chunkSize": 1500,
  "chunkOverlap": 150,
  "pageMarkers": true,
  "removeHeadersFooters": true,
  "includeSlideNotes": true,
  "maxRowsPerSheet": 1000,
  "maxDocuments": 100,
  "maxPagesPerDocument": 500,
  "maxFileSizeMb": 30,
  "maxConcurrency": 2,
  "requestTimeoutSecs": 60,
  "documentTimeoutSecs": 300
}
```

## Output

```json
{
  "source": {
    "label": "Source",
    "format": "string"
  },
  "format": {
    "label": "Format",
    "format": "string"
  },
  "status": {
    "label": "Status",
    "format": "string"
  },
  "title": {
    "label": "Title",
    "format": "string"
  },
  "pageCount": {
    "label": "Pages",
    "format": "integer"
  },
  "pagesConverted": {
    "label": "Charged pages",
    "format": "integer"
  },
  "pagesWithoutText": {
    "label": "No text on pages",
    "format": "array"
  },
  "tableCount": {
    "label": "Tables",
    "format": "integer"
  },
  "wordCount": {
    "label": "Words",
    "format": "integer"
  },
  "chunkCount": {
    "label": "Chunks",
    "format": "integer"
  },
  "chargedEvents": {
    "label": "Charged",
    "format": "object"
  },
  "statusNote": {
    "label": "Note",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [PDF to Markdown & RAG Chunks: Document Parser (DOCX/PPTX/XLSX)](https://apify.com/lindenwerk/pdf-to-markdown-rag.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/lindenwerk/pdf-to-markdown-rag.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/lindenwerk/pdf-to-markdown-rag.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`).