HN user
I know the podcast app Snipd (https://www.snipd.com/) offers some similar things. It will build chapters with AI generated summaries of each chapter.
Not sure if they are leveraging that for search and discovery or not but it looks like they do (https://www.snipd.com/podcasters)
A user can request it for any podcast and it doesn't seem to take that long the times I have tried it.
This seems to be a trendy approach. Intellij Fleet (https://www.jetbrains.com/fleet/) Replit (https://replit.com/) more... (ssh + vim) ;)
They are all a bit different of course. I do worry the MS + GitHub hegemony doesn't have our best interest in mind though.
Another Neeva user here... yeah, the personal document indexing was far cooler than I expected. I held off doing it for it a while but glad I gave it go. Just the GitHub indexing alone is cool. Can do some fun hacks with that too. I think they need to surface these personal results even better in the web results than they do (and I hear that is in the works?? hope it is).
Just a user of Neeva here but a happy one. Also very excited to hear about the work toward an independent stack! Enjoy the spaces and immersive search UIs for various types of searches. Neeva make search fun again. ;)
I think this is part of the issue with Google. They are almost too afraid to innovate in search (for the user) for fear it would impact advertising.
Actually I think Neeva is fully open now for all to try at https://neeva.com/
I don't work for them, but I have gone the paid route with them and I am very pleased with them as my default search now.
Wait.. Dark Castle actually runs?! I can't get the controls to work, can anyone help.. I desperately want to show this to my son so he can see what I used to play. :)
system error: -127
WOW.. it's exactly as I remember it :)
Joke aside, that was a FUN walk down memory lane for me.
Untapped potential. exactly. To me the biggest problem isn't the results (even the ads) it's the lack of innovation. The lack of making search an experience and something that generates a value I can store and share.
I've been looking at several of the options talked about here. My favorite so far is Neeva (https://neeva.com) due to their "spaces" concept and how it provides a simple building block I can explore to address many of the use cases I have for search.
Search needs innovation and people trying new things.
This is just a simple bash script and Apache Tika (https://tika.apache.org/). You could script this together in minutes. Try https://github.com/flameshot-org/flameshot and feed the results through Tika to OCR the results.
what are they.... I would be interested in them as I have been wanting to get time to look at flutter for the web
Yes.. I work on several projects that leverage SPARQL. The article is also remiss in not mentioning the work the W3C is doing along with Neo4J to do its own alignment (https://www.w3.org/Data/events/data-ws-2019/). Indeed, this article seems very self serving in its omissions. There is a follow up meeting planned soon for that too.
Also, much of the work in validation (SHACL, Shex) of graphs leverages SPARQL so it's not going anwhere soon. I would like to see it evolve to allow more vertex based searches without the need for extensions though.