Train Knowledge Graph from Website
lyzr_kg_train_websiteCrawl and ingest website URLs into the v4 knowledge graph to build and expand your RAG knowledge base.
Instructions
Crawl and ingest one or more URLs into the v4 knowledge graph.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"rag_id": "<rag_id>",
"urls": "<urls>"
},
"name": "lyzr_kg_train_website"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | URLs to crawl and ingest | |
| actor | No | Crawler actor | |
| rag_id | Yes | Knowledge base id | |
| source | No | Source label (default website) | |
| chunk_size | No | Chunk size | |
| crawler_type | No | Crawler type | |
| extra_fields | No | Additional body fields merged into the request | |
| chunk_overlap | No | Chunk overlap | |
| max_crawl_depth | No | Max crawl depth | |
| max_crawl_pages | No | Max pages to crawl | |
| dynamic_content_wait_secs | No | Seconds to wait for dynamic content |