Thursday, 16 March 2023

Full-text web scraping and builder bug fixes

New Features

Full-text universal web scraping is back!

Now you can extract full-text content of the targeted web page using URL of the web page as an input:

Full text content in the output

Works best with web search components and knowledge extraction.

Web content that has more than 4,000 characters (around 1000 English words) can't be processed live during the workflow.

To make using longer web page content possible, collect it to the "Documents" section first, and then perform "Internal Search" across it from the workflow.

Bug Fixes

Issue with creating workflows in the workflow builder

Sometimes the servers became out of order when you tried to create a new workflow.

Now this issue is gone.