Hoory Knowledge Base (KB) is a unique application designed to crawl the content of any website where the widget is embedded.
The information from the website is collected into a knowledge database, used to send relevant answers to a user’s requests if there are no suitable Trainings available.
KB in the Workspace
To create a unique knowledge database for your assistant, simply let Hoory start the very first crawl!
Just click Start crawling and let Hoory handle the progress. Meanwhile, you can continue easily navigating through the workspace. You will be notified once the crawl is complete.
Note: The time of crawling can vary due to the volume of your website’s content.
After crawling the widget-embedded website, Hoory provides a list of crawled pages based on which the workspace’s Knowledge Base is built. Relevant content from these pages is sent as answers to your users’ questions.
Take into account that you can Hide from Index the pages you don’t want the users to receive. If a page appears with a No Index badge, it has blocking mechanisms that prevent Hoory from crawling it.
In the list of crawled pages, you can view the number of questions matched with one page. This means you’ll see how many times a page has been matched as relevant and sent to users. You can also view the date and time a page was last matched with a question in the Last matched column.
In the nested view of the list, you can also view the given subpages and select multiple pages to perform an action.
There’s also an option to preview the crawled pages and the HTML codes directly from the list.
Start a new crawl
You can always ask Hoory to recrawl your updated website by clicking Start a new crawl. This way, Hoory will rewrite the Knowledge Base by crawling the website from scratch. This process can be stopped at any time, after which Hoory will provide the list of pages successfully crawled up until that moment.
Once the KB is enabled, your assistant will send relevant pages to users’ requests with a badge saying Retrieved from Index. Hoory will highlight a part of the page where it found the relevant content to the question in the page preview. Your users can then open the page and see the corresponding paragraph.
Note that your assistant will try to retrieve answers from the trainings first. If it doesn’t find a relevant trained response, it will switch to the Knowledge Base to find the correct answers. So, when the widget users ask a question that has no trained answer, Hoory sends the already crawled pages relevant to that question.
For any questions you may have, please contact our Support via [email protected].