# Convert a Documentation Site to Markdown for RAG

**Use case:** 

Crawl a documentation site and get every page as clean Markdown, ready for a RAG pipeline, a vector database or an AI agent. Main content only: menus and footers are removed, links are kept. This example converts 20 pages of the Apify docs; put the link of your own docs instead. No browser, so it is fast and cheap: $1 per 1,000 pages.

## Input

```json
{
  "urls": [
    "https://docs.apify.com/platform/actors"
  ],
  "maxPagesPerUrl": 20,
  "onlyMainContent": true,
  "includeLinks": true,
  "includeImages": false
}
```

## Output

```json
{
  "url": {
    "label": "Page",
    "format": "link"
  },
  "title": {
    "label": "Title",
    "format": "text"
  },
  "wordCount": {
    "label": "Words",
    "format": "number"
  },
  "markdown": {
    "label": "Markdown",
    "format": "text"
  },
  "depth": {
    "label": "Depth",
    "format": "number"
  },
  "status": {
    "label": "Status",
    "format": "text"
  },
  "errorMessage": {
    "label": "Error",
    "format": "text"
  }
}
```

## How it works

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

The Website to Markdown: Fast Crawler for LLM & RAG (No Browser) Actor is ready to run with the inputs already set for "Convert a Documentation Site to Markdown for RAG". [Sign up or log in](https://console.apify.com/create-task-from-example/3csQwrR1PzLtiWLWM) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Convert a Documentation Site to Markdown for RAG" task

The Website to Markdown: Fast Crawler for LLM & RAG (No Browser) Actor will start running based on the input automatically. You can also change all the input fields, like pages, pages per link, and more, to match your specific use case.

### 3. Receive the "Convert a Documentation Site to Markdown 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 page, title, words, 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 "Convert a Documentation Site to Markdown for RAG" task via API](https://apify.com/arnaud437/website-to-markdown.md).

## FAQ

### What does the documentation to Markdown task return?

The documentation to Markdown task returns one row per page: its link, its title and its main content as clean Markdown, without menus or footers, ready to split into chunks for a RAG pipeline or a vector database.

### How do I convert my own documentation site?

To convert your own documentation site to Markdown, replace the start link with the first page of your docs and choose how many pages to follow from it. The crawler respects robots.txt.

### How much does converting a documentation site to Markdown cost?

Converting a documentation site to Markdown with this task costs $1 per 1,000 pages on the free plan and less on paid Apify plans; error pages are free. The 20 pages of this example cost about 2 cents.

## About this Actor

This example demonstrates how to use [Website to Markdown: Fast Crawler for LLM & RAG (No Browser)](https://apify.com/arnaud437/website-to-markdown.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/arnaud437/website-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/arnaud437/website-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`).
