### Answer Based on the available documentation, the Knowledge Base API supports these source types for creating or adding sources: -

knowledge_base_texts

– manually add text [(1) ]() [(2) ]() -

knowledge_base_files

– upload files (limit 25 files, each up to 50MB) -

knowledge_base_urls

– URLs to be scraped -

enable_auto_refresh

– auto-refreshes URL data every 12 hours However, *auto-crawling (sitemap-based crawling) * is not documented as a parameter in the API references. A Discord user attempting to use

auto_crawling_paths

via the API received a

400

error with the message

"auto-crawling domain invalid"

. [(3) ]() So to answer your question: the auto-crawl/sitemap functionality appears to be UI-only based on the current API documentation. The API supports scraping individual URLs with optional auto-refresh, but not sitemap-based crawling. If you need automated KB updates, the documented workaround is to use

knowledge_base_urls

with

enable_auto_refresh: true

, or programmatically add sources via

knowledge_base_texts

or

knowledge_base_files

. [(1) ]() [(2) ]()

​ To learn more, see the sources I considered: [[1] Create Knowledge Base](https://docs.retellai.com/api-references/create-knowledge-base) [[2] Add Knowledge Base Sources](https://docs.retellai.com/api-references/add-knowledge-base-sources) [[3] API/Backend Integration for Knowledge Base Management](https://discord.com/channels/1186424376300679209/1438153573287334000) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.