### Answer This issue with "Untitled" entries appearing in knowledge bases has been reported by other users. [(1) ]() Possible causes for URL processing failures: - The URL may have redirects, bot-blocking, or unsupported page formats that prevent proper parsing [(2) ]() - Some URLs may not be accessible without login or cookies Recommendations: 1. Verify URL accessibility - Ensure the URLs are public and accessible without authentication 2. Use more granular paths for auto-crawling instead of broad paths with many exclusion URLs, as this improves crawl performance and helps avoid hitting exclusion URL limits [(3) ]() 3. Consider file format - If you're having persistent issues with URLs, you might try downloading the content and uploading as

.md

(Markdown) files instead, which are chunked and retrieved more accurately Regarding the "Untitled" entries: Unfortunately, the sources indicate these entries without proper

source_id

values cannot be deleted through the UI or API. [(1) ]() For the unresponsive "Ignore" button and persistent processing errors, I'd recommend reaching out to Retell support directly: - [Contact Sales]() - [GitHub]() Would you like me to provide a general answer on troubleshooting knowledge base URL issues?

​ To learn more, see the sources I considered: [[1] Knowledge base 'Untitled' entries](https://discord.com/channels/1186424376300679209/1442676739179413515) [[2] Discord message from @colin_43491 on 2025-11-04](https://discord.com/channels/1186424376300679209/1294891368505937952/1435219186719653920) [[3] Knowledge Base](https://docs.retellai.com/build/knowledge-base) ​

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