# RAG Dataset from Apify Actor Documentation

**Use case:** 

Convert Apify Actor publishing docs into clean Markdown chunks. Gain structured, retrieval-ready data for AI assistants and vector databases.

## Input

```json
{
  "urls": [
    "https://docs.apify.com/actors/publishing",
    "https://docs.apify.com/actors/publishing/actor-rating",
    "https://docs.apify.com/actors/publishing/actor-status",
    "https://docs.apify.com/actors/publishing/monetize",
    "https://docs.apify.com/actors/publishing/monetize/monthly-payouts",
    "https://docs.apify.com/actors/publishing/monetize/pay-per-event",
    "https://docs.apify.com/actors/publishing/monetize/pricing-and-costs",
    "https://docs.apify.com/actors/publishing/monetize/rental",
    "https://docs.apify.com/actors/publishing/publish",
    "https://docs.apify.com/actors/publishing/publish-task",
    "https://docs.apify.com/actors/publishing/quality-score",
    "https://docs.apify.com/actors/publishing/status-badge",
    "https://docs.apify.com/actors/publishing/test"
  ],
  "maxPages": 20,
  "sameDomainOnly": true,
  "respectRobotsTxt": true,
  "outputMode": "pages_and_chunks",
  "includeMarkdown": true,
  "includeSchema": true,
  "includeFreshnessSignals": true,
  "includeLinks": false,
  "includeHtml": false,
  "chunkSize": 800,
  "chunkOverlap": 100,
  "minContentChars": 250,
  "maxConcurrency": 3,
  "requestTimeoutSecs": 20,
  "maxSitemaps": 10,
  "userAgent": "WebsiteToRagDatasetBot/1.0 (+https://apify.com)",
  "urlAllowlistPatterns": [],
  "urlBlocklistPatterns": [],
  "removeSelectors": [
    "nav",
    "footer",
    "header",
    "aside",
    "script",
    "style",
    "noscript",
    "iframe",
    "form",
    "[class*='llmMenu_']"
  ],
  "onlySelectors": [
    ".theme-doc-markdown"
  ],
  "dedupeByCanonical": true,
  "saveRunSummaryToKeyValueStore": true
}
```

## Output

```json
{
  "url": {
    "label": "URL",
    "format": "string"
  },
  "title": {
    "label": "Title",
    "format": "string"
  },
  "status": {
    "label": "Status",
    "format": "string"
  },
  "markdown": {
    "label": "Markdown",
    "format": "string"
  },
  "estimatedTokens": {
    "label": "Estimated tokens",
    "format": "integer"
  },
  "chunkCount": {
    "label": "Chunk count",
    "format": "integer"
  },
  "schemaTypes": {
    "label": "Schema types",
    "format": "array"
  },
  "processedAt": {
    "label": "Processed at",
    "format": "string"
  },
  "error": {
    "label": "Error",
    "format": "object"
  }
}
```

## About this Actor

This example demonstrates how to use [Website to RAG Dataset](https://apify.com/sebastian-actors/website-to-rag-dataset) with a specific input configuration. Visit the [Actor detail page](https://apify.com/sebastian-actors/website-to-rag-dataset) to learn more, explore other use cases, and run it yourself.