Knowledge bases
Sitemap knowledge sources
A sitemap source uses a sitemap’s listed page URLs as the ingestion set instead of discovering pages through link crawling. Manual re-ingest processes the full supported list, while Business can use reliable page-level last-modified dates for incremental nightly updates.
- Availability
- Pro and Business
- Configured in
- Dashboard → Stand-ins → Knowledge bases → expand a knowledge base → Website sources → Sitemap → Ingest sitemap
- Category
- Knowledge bases
- Reference status
- Current
Before you begin
Plan availability: Pro and Business; automatic nightly refresh is Business-only.
Prerequisite: A reachable sitemap that lists supported public pages; automatic refresh additionally requires Business and usable page-level `lastmod` values.
Key boundary: A sitemap entry is a discovery hint, not proof that its page is readable. Manual refresh fails as a whole when a listed page cannot be read, and automatic refresh cannot infer changes reliably without usable `lastmod` values.
Add and ingest a sitemap
- Enter the sitemap URL in an owned knowledge base and begin ingestion.
- Stand reads the listed page URLs and fetches those pages rather than following arbitrary page links to determine scope.
- One sitemap source accepts up to 5,000 listed pages as a customer-visible platform guardrail.
- Successfully indexed web pages and extracted text consume the organization’s normal plan allowances.
Manual re-ingest behavior
A manual sitemap refresh is a complete re-ingest of the supported listed pages. It includes entries that omit lastmod, because the customer explicitly requested a full refresh rather than an incremental comparison.
Stand builds a replacement while the prior successful source remains active. If any listed page required for the refresh cannot be read, the refresh fails and the previous successful content remains available.
Automatic updates
After you enable automatic updates, checks run on a rolling 24-hour schedule, subject to processing availability.
| Sitemap state | Nightly behavior |
|---|---|
New URL with usable lastmod | The page is eligible for processing as new content. |
Existing URL with a newer usable lastmod | The page is eligible for replacement. |
Missing current or stored lastmod | Entries without a usable current date are skipped. An existing indexed page whose stored date is missing is also skipped, even if the sitemap later adds a date; manually re-ingest to establish that baseline. |
| Page removed from the sitemap | Incremental refresh does not remove its previously indexed content. Use a full manual re-ingest to reconcile the source with the current list. |
| Individual page cannot be read | That page can be skipped while other eligible pages update. Its prior indexed version stays available. |
| Ingestion task fails | Uncommitted replacement work is not activated; the prior successful content remains available. |
Enable automatic refresh
- Open the sitemap source details after its initial successful ingestion.
- Enable the nightly sitemap update control on Business.
- Confirm that the sitemap publishes page-level
lastmodvalues that change when page content changes. - Disable the control to stop future nightly processing without deleting the source or its last successful content.
Plan and ownership boundaries
- Sitemap sources require Pro or Business; Base supports website crawling instead.
- Nightly automatic updates require Business. Pro can manually refresh its supported sitemap sources.
- Only the owning rep can change, refresh, or delete the source; organization members can see shared knowledge.
- The 5,000-entry guardrail does not increase the organization’s plan page or indexed-content allowance.
Example
The screen below shows the feature in its normal Stand context. Labels and surrounding controls may vary with account state and plan.
