Skip to main content
What this builds. A KB that ingests web content two ways — one URL with AI enhancement, and a recursive crawl bounded by url_limit. You’ll end up with. A KB holding both ingestion results, with the recursive crawl scheduled to refresh weekly.

Expected output

rescrape_frequency lives on the URL config, not the KB — different URLs in the same KB can refresh on different schedules.

See also

Add files

Ingest local files into a KB.

Advanced query

Query with filters, hybrid, rerank, and QA.

KB reference

Every public method.