Resources can be added to GenAI's knowledge in the Knowledge screen via the web crawler and via files.
Web crawler
You can upload a web page by clicking the + button, choosing resource type 'Add web-crawler' and including the URL(s) from your website.
- If you want to crawl multiple subpages, you can use a wildcard (*). E.g. https://desk.company.com/solutions* will crawl all subpages underneath the solutions page.
- You can also exclude certain web pages from being crawled using the Web Crawler Blacklist on the Profile Settings screen
- Note that the crawler can crawl up to 48 hours in one go
- The best source for high quality answers is naturally written text. That’s why product text like “Color: Black” doesn’t work as well.
Files
You can upload a PDF or JSON file by clicking the + button and choosing resource type ' Upload file'. Note that there is a file size limit of 25MB.
- PDF files can have any format, i.e. they don't have to use a Question/Answer format.
- Text, list and tables can be read in, but pictures are not supported currently.
- To achieve maximum value from you uploaded documents into knowledge, it is best to use blocks of text of no more than 400 words, and to split blocks/topics with 2 white lines/enters.
- JSON
- JSON files should have the following format:
JSON Format
[
{
"trigger": "…",
"content": "…"
}
]
Please note that while it is possible to upload a file that contains multiple languages, this is not recommended, as it may lead to loss of information.
Video
Below you can find a video on the Knowledge and Settings sections within GenAI.