Released: November 6, 2025
We’ve introduced advanced filtering capabilities for website sources in the Knowledge Hub, giving you greater control over which pages are ingested from your sitemap and during new page detection.
New “Include” and “Exclude” operators let you refine sitemap URLs more effectively.
“Include” operator: Finds URLs that contain specified text (match any).
“Exclude” operator: Removes URLs that contain specified text.
Combine both: For targeted results—e.g., include "academics" and exclude "science" to view only academic pages without "science" in the URL.
Also available in “New Page Filters” when “Detect New Pages” is enabled, allowing automatic filtering of newly added website pages.
In addition, when creating a website source, you’ll now be presented with a confirmation dialogue with a summary of how many URLs will be added before ingestion begins.
This enhancement helps you quickly zero in on the most relevant content, streamlining your ingestion process and ensuring only the pages you want are included in your Knowledge Hub.
