# Build a RAG Dataset from Y Combinator YouTube Videos

**Use case:** 

Pulls transcripts of the 20 newest Y Combinator videos as clean text plus timestamped segments you can chunk and cite, with title, publish date, views and word count for each. The run also saves one combined markdown file of every transcript. Use it to seed a startup-advice knowledge base, or paste your own channel link.

## Input

```json
{
  "startUrls": [
    {
      "url": "https://www.youtube.com/@ycombinator"
    }
  ],
  "language": "en",
  "maxVideosPerSource": 20,
  "includeTimestamps": true,
  "includeChapters": true,
  "includeMetadata": true,
  "subtitleFormats": [],
  "includeFailedVideos": true,
  "preferAutoGenerated": false,
  "fallbackToAnyLanguage": true,
  "maxConcurrency": 5,
  "proxyConfiguration": {
    "useApifyProxy": true,
    "apifyProxyGroups": [
      "RESIDENTIAL"
    ]
  }
}
```

## Output

```json
{
  "title": {
    "label": "Video",
    "format": "text"
  },
  "channelName": {
    "label": "Channel",
    "format": "text"
  },
  "duration": {
    "label": "Length",
    "format": "text"
  },
  "language": {
    "label": "Lang",
    "format": "text"
  },
  "isAutoGenerated": {
    "label": "Auto-generated",
    "format": "boolean"
  },
  "wordCount": {
    "label": "Words",
    "format": "number"
  },
  "publishedAt": {
    "label": "Published",
    "format": "text"
  },
  "viewCount": {
    "label": "Views",
    "format": "number"
  },
  "status": {
    "label": "Status",
    "format": "text"
  },
  "url": {
    "label": "URL",
    "format": "link"
  },
  "text": {
    "label": "Transcript",
    "format": "text"
  }
}
```

## About this Actor

This example demonstrates how to use [YouTube Transcript Scraper – Subtitles to Text for LLM & RAG](https://apify.com/inovaflow/youtube-transcript-scraper.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/inovaflow/youtube-transcript-scraper.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/inovaflow/youtube-transcript-scraper.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`).