Crawler vs LinkContentFetcher #6538
Replies: 1 comment
-
That's correct! If you already have a list of URLs, LinkContentFetcher is what you need.
It's not yet ported, but this doesn't mean we won't add it later. It's just not very high on the priority list right now but sooner or later we will probably add it again. |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
I have a set of URLs that I want to extract the text from. I am trying to understand what is the difference between the
Crawler
and theLinkContentFetcher
and if there are any advantages to using one versus the other.To my understanding the
Crawler
will start from a link, extract the text and then move on to other "neighboring" URLs and extract those as well. While theLinkContentFetcher
will only extract the text from the URLs provided. Is there any benefit to using theCrawler
when I am only interested in specific URLs?I was also reading through the Haystack 2.0 docs and I was not able to find any mention of
Crawler
. Does that mean that it will not be in the new version of Haystack?Thank you for your amazing work I really love what you have done so far!
Beta Was this translation helpful? Give feedback.
All reactions