ask
Answer questions about a website using its crawled pages and knowledge graph, then return a cited response grounded in that site’s content.
Instructions
LLM Q&A grounded in the site's pages: keyword retrieval + graph-neighborhood expansion, then embedding rerank and a cited answer. Requires SITE_KG_LLM_BASE and SITE_KG_LLM_KEY in the server environment.
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": {
"site_id": "<site_id>",
"question": "<question>"
},
"name": "ask"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| top_k | No | ||
| site_id | Yes | ||
| question | Yes |