ingest_url
Fetches a URL and ingests its main content into a RAG collection, stripping navigation, cookie banners, and footers from documentation pages and articles.
Instructions
Fetches a web page and ingests its main content, stripped of navigation/cookie-banners/footers. Use this for documentation pages, articles, or any URL-addressable content the user wants in the RAG.
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": {
"collection": "<collection>",
"url": "<url>"
},
"name": "ingest_url"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| collection | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| doc_id | Yes | ||
| collection | Yes | ||
| source_path | Yes | ||
| chunks_created | Yes |