extract_youtube_transcript_and_rag
Extracts multi-language YouTube transcripts, timestamped chapters, and metadata, then converts them into token-bounded RAG chunks with timestamp deep-links for retrieval and analysis.
Instructions
Extract full multi-language YouTube transcripts, timestamped chapters, metadata, and token-bounded RAG chunks with deep-links from video URLs or IDs.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "extract_youtube_transcript_and_rag"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| videoUrl | No | Single YouTube video URL, Short URL, or 11-character Video ID. | |
| videoUrls | No | List of YouTube video URLs or IDs for batch extraction. | |
| chunkSizeWords | No | Words per semantic RAG chunk with timestamp deep-links. | |
| targetLanguage | No | Preferred ISO transcript language code (e.g. 'en', 'es', 'fr'). | en |
| includeMetadata | No | Include title, channel metadata, views, and chapters. |