# Extract text from a public PDF for RAG

**Use case:** 

Extract the embedded text of a public, text-based PDF page by page, ready for retrieval-augmented generation (RAG), summarization or indexing. Each page keeps its page number and character counts, with truncation warnings when a limit applies. Replace the example URL with your own PDF. Scanned PDFs need OCR and are not supported. You pay only for documents and pages that were extracted.

## Input

```json
{
  "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
  "format": "markdown",
  "maxChars": 20000
}
```

## Output

```json
{
  "url": {
    "label": "Url",
    "format": "string"
  },
  "status": {
    "label": "Status",
    "format": "string"
  },
  "documentType": {
    "label": "Document type",
    "format": "string"
  },
  "title": {
    "label": "Title",
    "format": "string"
  },
  "outputCharacters": {
    "label": "Output characters",
    "format": "integer"
  },
  "textTruncated": {
    "label": "Text truncated",
    "format": "boolean"
  },
  "pageCount": {
    "label": "Page count",
    "format": "integer"
  },
  "content": {
    "label": "Content",
    "format": "string"
  },
  "warnings": {
    "label": "Warnings",
    "format": "array"
  },
  "error": {
    "label": "Error",
    "format": "string"
  }
}
```

## How it works

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

The PDF to Text & HTML to Markdown for LLMs and RAG Actor is ready to run with the inputs already set for "Extract text from a public PDF for RAG". [Sign up or log in](https://console.apify.com/create-task-from-example/pwNKAzkUztlgALpti) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Extract text from a public PDF for RAG" task

The PDF to Text & HTML to Markdown for LLMs and RAG Actor will start running based on the input automatically. You can also change all the input fields, like single document url, output format, and more, to match your specific use case.

### 3. Receive the "Extract text from a public PDF 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 url, status, document type, 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 "Extract text from a public PDF for RAG" task via API](https://apify.com/textokit/document-to-llm-markdown.md).

## FAQ

### Does it work with scanned PDFs?

No. It reads the embedded text layer only and has no OCR. Pages without embedded text come back empty with a warning, and the document is still charged as an extracted document.

### How much does one PDF cost?

USD 0.005 per successfully extracted document plus USD 0.001 per processed PDF page. A three-page PDF costs USD 0.008 and a ten-page PDF USD 0.015. Failed downloads and failed extractions are not charged.

### Can I extract several PDFs in one run?

Yes. Put up to 50 public HTTPS URLs in the Document URLs field instead of the single URL. Each document gets its own character budget, and PDFs can have up to 200 pages.

## About this Actor

This example demonstrates how to use [PDF to Text & HTML to Markdown for LLMs and RAG](https://apify.com/textokit/document-to-llm-markdown.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/textokit/document-to-llm-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/textokit/document-to-llm-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`).