# Extract Corporate Sustainability Reports (ESG) for RAG

**Use case:** 

Fetch and process sustainability and ESG reports directly from corporate websites or public databases. This provides crucial data for RAG models to analyze envi

## Input

```json
{
  "query": "what is retrieval augmented generation",
  "startUrls": [
    {
      "url": "https://www.apple.com/environment/"
    },
    {
      "url": "https://sustainability.about.nike.com/"
    },
    {
      "url": "https://www.patagonia.com/our-purpose/sustainability/"
    }
  ],
  "maxResults": 3,
  "outputFormats": [
    "markdown"
  ],
  "requestTimeoutSecs": 40,
  "scrapingTool": "browser-playwright",
  "removeElementsCssSelector": "nav, footer, aside, script, style, .ad, .advertisement, [aria-hidden='true'], .header",
  "htmlTransformer": "readable-text",
  "desiredConcurrency": 5,
  "maxRequestRetries": 2,
  "dynamicContentWaitSecs": 5,
  "removeCookieWarnings": true,
  "useApifyProxy": true,
  "domainAllowlist": [],
  "domainBlocklist": [],
  "minTextLength": 1000,
  "excludeContentSelectors": [],
  "keywordsAnyOf": [
    "sustainability report",
    "ESG",
    "environmental",
    "social",
    "governance",
    "carbon footprint",
    "circular economy"
  ]
}
```

## Output

```json
{
  "url": {
    "label": "Url"
  },
  "title": {
    "label": "Title"
  },
  "description": {
    "label": "Description"
  },
  "wordCount": {
    "label": "Word count"
  },
  "httpStatusCode": {
    "label": "Http status code"
  },
  "loadedTime": {
    "label": "Loaded time"
  },
  "searchRank": {
    "label": "Search rank"
  }
}
```

## About this Actor

This example demonstrates how to use [RAG Web Browser](https://apify.com/crawlerbros/rag-web-browser) with a specific input configuration. Visit the [Actor detail page](https://apify.com/crawlerbros/rag-web-browser) to learn more, explore other use cases, and run it yourself.