-----------------------------------------------------------------------------------
Scraping, also known as web scraping, is an automated method for the massive and systematic extraction of information from web pages using computer programs or tools, without manual intervention.-----------------------------------------------------------------------------------
Once you’ve added content to the Autogenerated section of Virtual Assistant, whether from links or PDF documents, and enabled the option to use that Autogenerated Knowledge, when one of your customers types a query into the virtual assistant, the process will first search for the information in the Personalized knowledge base; if it doesn’t find what’s being asked, it will then search the Autogenerated knowledge base.
-----------------------------------------------------------------------------------
Key Details:-
Enter a complete URL to search the content of the main site and all associated links.
- For example, for (https://es.aivo.co/), the sites could be: https://es.aivo.co/customers; https://es.aivo.co/chatgpt; https://es.aivo.co/cx-station/webinars, etc.
- Domains and links ending in .php, .html, or .aspx are supported.
- The site must be public and accessible. Links that require authentication or are protected by security measures such as IP filters or CAPTCHAs cannot be processed.
- You can include a single link by checking the “Search only this URL” checkbox. Otherwise, the system will search for all links that begin with the entered URL.
- Once you've added the links, you'll need to process the content before enabling Auto-Generated Knowledge.
- If a PDF file is found during the search, it will appear in the Documents tab.
- From the list of links, you can:
- Search for specific links in the list of results using the URL or a keyword included in the title.
- Preview the extracted text.
- Open in a new tab.
- Download the extracted text.
- Delete links: you can do this individually or in bulk.
- To add new links, start a new search; existing links will not be replaced.
- After adding new links or deleting any, click Process again for the changes to take effect.
- The change history will be displayed. There, you’ll see the modifications made in this section, who made them, and when.
This makes it more efficient to manage content collaboratively and simultaneously detect any adjustments made that impact the virtual assistant’s knowledge. - Once the virtual assistant begins responding with the Autogenerated knowledge, you can incorporate those responses into Custom Knowledge from the Autogenerated Training section.
You may also be interested in:> Best practices for managing your Generative AI content.
> Autogenerated knowledge functionality and the use of prompts
-----------------------------------------------------------------------------------
In the video below, discover a step-by-step guide on how to implement link embedding and what actions you can take on the list of found links.
For details about the PDF upload option, see: Incorporate the content of PDF files into auto-generated knowledge with Gen AI