# Build RAG Knowledge Base from Product Documentation

**Use case:** 

Extract structured text from your product documentation website for RAG pipelines. This enables accurate, up-to-date responses for customer service chatbots and

## Input

```json
{
  "startUrls": [
    {
      "url": "https://docs.apify.com/"
    }
  ],
  "crawlerType": "playwright:chromium",
  "maxCrawlDepth": 5,
  "maxCrawlPages": 100,
  "maxConcurrency": 5,
  "includeUrlGlobs": [
    "https://docs.apify.com/**"
  ],
  "excludeUrlGlobs": [
    "*/login*",
    "*/search*",
    "*/contact-us*"
  ],
  "outputFormat": "markdown"
}
```

## Output

```json
{
  "url": {
    "label": "URL",
    "format": "text"
  },
  "title": {
    "label": "Title",
    "format": "text"
  },
  "depth": {
    "label": "Depth",
    "format": "number"
  },
  "httpStatusCode": {
    "label": "Status",
    "format": "number"
  }
}
```

## About this Actor

This example demonstrates how to use [Website Content Crawler](https://apify.com/crawlerbros/website-content-crawler) with a specific input configuration. Visit the [Actor detail page](https://apify.com/crawlerbros/website-content-crawler) to learn more, explore other use cases, and run it yourself.