# Convert PDF reports to Markdown for LLMs and RAG

**Use case:** 

Turn long PDF reports, papers and manuals into clean Markdown that keeps headings, reading order and tables, ready for ChatGPT, Claude or a RAG pipeline. Tables also come out as JSON. Digital pages are read without OCR; scanned pages get OCR automatically. The example converts the 9-page Docling technical report from arXiv.

## Input

```json
{
  "documentUrls": [
    "https://arxiv.org/pdf/2408.09869"
  ],
  "ocrMode": "auto",
  "extractTablesAsJson": true,
  "maxPages": 20,
  "maxFileSizeMb": 50,
  "maxDocuments": 100,
  "documentTimeoutSecs": 300
}
```

## Output

```json
{
  "source_url": {
    "label": "Source URL",
    "format": "string"
  },
  "full_markdown": {
    "label": "Full Markdown",
    "format": "string"
  }
}
```

## How it works

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

The Invoice, Receipt & PDF Table to JSON/Markdown OCR Actor is ready to run with the inputs already set for "Convert PDF reports to Markdown for LLMs and RAG". [Sign up or log in](https://console.apify.com/create-task-from-example/doUZuZLw38hyNibsM) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Convert PDF reports to Markdown for LLMs and RAG" task

The Invoice, Receipt & PDF Table to JSON/Markdown OCR Actor will start running based on the input automatically. You can also change all the input fields, like document urls, OCR mode, and more, to match your specific use case.

### 3. Receive the "Convert PDF reports to Markdown for LLMs and 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 source url and full markdown.

### 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 "Convert PDF reports to Markdown for LLMs and RAG" task via API](https://apify.com/panix/invoice-table-json-extractor.md).

## FAQ

### Why convert PDFs to Markdown for an LLM?

Markdown keeps headings, lists and tables as plain text, so an LLM or an embedding model sees the document's structure. The PDF to Markdown task drops page clutter and keeps the reading order of multi-column pages.

### How long can the PDFs be?

The PDF to Markdown task reads up to 2,000 pages per document; set Max pages per document to limit the cost. Very large results are saved to the key-value store and linked from markdown_url.

### Are my documents sent to an AI service?

The PDF to Markdown task runs IBM Docling and its OCR models inside your Apify run. No document is sent to OpenAI or any other outside service, and no API key is needed.

### How much does the PDF to Markdown task cost?

The PDF to Markdown task costs $0.005 per digital page on the Apify Free plan and $0.0045 on Starter, less on bigger plans, plus $0.004 per run. Scanned pages cost more because they need OCR.

## About this Actor

This example demonstrates how to use [Invoice, Receipt & PDF Table to JSON/Markdown OCR](https://apify.com/panix/invoice-table-json-extractor.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/panix/invoice-table-json-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/panix/invoice-table-json-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`).
