Re:Show HN: I've built a locally running Perplexity clone
by nemoniac on Thursday April 04, 2024 @03:59AM
(#39927690)
Llocalsearch uses searxng which has a feature to blacklist/whitelist sites for various purposes.
Re:Show HN: I've built a locally running Perplexity clone
by nilsherzig on Thursday April 04, 2024 @05:18AM
(#39928170)
also a great idea to expose this to the frontend. thanks :)
Re:Show HN: I've built a locally running Perplexity clone
by kidintech on Thursday April 04, 2024 @03:32AM
(#39927548)
Seconded. I tried to do this many years ago for my dissertation and failed, but this would be a dream of mine.
Re:Show HN: I've built a locally running Perplexity clone
by robertlagrant on Thursday April 04, 2024 @03:40AM
(#39927588)
Would it not be possible to create a search engine that only crawls certain sites?
Re:Show HN: I've built a locally running Perplexity clone
by kidintech on Thursday April 04, 2024 @03:43AM
(#39927608)
I was most interested in the offline aspect of it, which I wouldn't know where to even start with if I were to fork.
How do you parse and efficiently store large, unstructured information for arbitrary, unstructured queries?
Re:Show HN: I've built a locally running Perplexity clone
by stavros on Thursday April 04, 2024 @05:12AM
(#39928127)
You put it in a search server, like ElasticSearch or Meili.
Re:Show HN: I've built a locally running Perplexity clone
by nilsherzig on Thursday April 04, 2024 @05:18AM
(#39928166)
uhhhh both ideas are great, would you like to turn them into github issues? i will definitely look into both of them :)
is it possible to make it only use a subset of the web? (Only sites that I trust and think are relevant to producing an accurate answer), and are there ways to possibly make it work offline on pre installed websites? (wikipedia, some other wikis and possibly news sites that are archived locally), and how about other forms of documents? (books and research papers as pdfs)