Hi @YFS

How we can help you today?

I am trying to train the Chatbot with an faq url. https://www.lernwerkstatt.ch/faq

It seems that there is too much content on the url? Is that possible?

Can you please share the error you getting?

Is it possible for you to share a recording or screenshot of the issue.

I have added several IDs (e.g.#q341)

there's no erroe message. The problem is that no all the ID have been recorded. its super random and some are duplicated

any thoughts?

Thank you for sharing these details.

In this case, I recommend using the “Website to FAQ” functionality. This feature is designed to extract question–answer pairs directly from pages.

It will help capture all relevant content more accurately and avoid duplication.

You can find it under the “Others” tab in training section, as shown in the screenshot below.

i have seen and tested it already. I have the same problem - not all FAQ (~10-17 / tested twice) are recorded and shown.

I will share this with our technical team and update you as soon as I have more information.

thanks i see this problem with all pages that I want to index with selectors

Could you please share the links to all the pages where you are experiencing this issue?

https://www.lernwerkstatt.ch/angebot/erwachsenenbildung-einstieg/train-the-trainer/seminar

i've only tested with this one as well

Okay, let me share both the urls with the team.

e.g. i need all inforamtion from this dropdown related to this url

that why i used the div ID

https://www.lernwerkstatt.ch/angebot/sveb-zertifikat-stufe-1/lehrgang

i have also added this URL and the chunks are super random.