# Prepare Web Content for RAG in Markdown

**Use case:** 

Batch-convert public webpages into clean Markdown capped for downstream LLM token budgets and knowledge-base ingestion.

## Input

```json
{
  "urls": [
    "https://en.wikipedia.org/wiki/Retrieval-augmented_generation",
    "https://en.wikipedia.org/wiki/Large_language_model"
  ],
  "includeImages": false,
  "includeLinks": true,
  "maxContentLength": 12000,
  "requestTimeout": 45,
  "maxRetries": 2
}
```

## Output

```json
{
  "url": {
    "label": "URL",
    "format": "link"
  },
  "title": {
    "label": "Title"
  },
  "wordCount": {
    "label": "Words"
  },
  "charCount": {
    "label": "Characters",
    "format": "number"
  },
  "tokenEstimate": {
    "label": "Est. tokens",
    "format": "number"
  },
  "success": {
    "label": "Success",
    "format": "boolean"
  },
  "extractedAt": {
    "label": "Extracted At"
  }
}
```

## About this Actor

This example demonstrates how to use [Webpage to Markdown Converter](https://apify.com/automation-lab/webpage-to-markdown-converter) with a specific input configuration. Visit the [Actor detail page](https://apify.com/automation-lab/webpage-to-markdown-converter) to learn more, explore other use cases, and run it yourself.