I followed the Knowledge Extraction given in the Documentation. When I extract from the URL which is Yes Bank FAQ, that is given in the documentation, I am getting **Extraction Failed. Encountered an unexpected error during extraction. Please review the supported formats. **. I could not find any help to rectify this from the Samples too. Do revert back on the steps to extract the FAQ (Knowledge Extraction). I am extracting using Public API
Hello @thenaveenm ,
The URL being used does not have the supported format, and thus extraction fails. You can verify with Citi bank FAQ’s, it works fine.
Hi @sameera.tumuluri ,
Can you please provide a walkthrough on how to extract from the Webpage?. I want to create a webpage as a repository holding the FAQs. I am able to extract into the Bot using Public API, but Extraction fails.
I cannot find a How To example for Extraction from Webpage. It would be great help if you guide on how to frame the Question Answer Pairs for the FAQs.
If you try FAQs | Advice | Careers | JPMorgan Chase & Co. it should work. I just tested it. You may follow similar indentations etc. on your page.
One reason for FAQ extraction failing could be if the page is not allowing traffic from bots.kore.ai (for example, HDFC Bank FAQ extraction may not work as traffic from bots.kore.ai which is hosted in the US may be blocked). I am not too sure if that is the case with you but this is certainly one of the factors.