Searx is no longer maintained
github.com
github.com
Brave, Quant, Yandex, and Mojeek are other centralized engines that do not rely on Google or Bing TMK.
I also run Yacy.net instance which is decentralized and federated. I crawl the sites I want to include as do the other operators. It is good for non-authoritative searches for topics that might be suppressed in centralized search engines.
The troubles start when you realise you also need to pipe this through a reputable vpn to get any real privacy. Noticeably more lag and unpredictable performance.
Think it had something to do with the vpn connection being up multiple days. Seemed to degrade over time
1. It sits in the "money for AI" fund from me. Ie it competes with ChatGPT. While it uses OpenAI in the background, i have not found it to be as complete and useful as ChatGPT directly. I did cancel ChatGPT for a couple months to try out Phind instead because Phind can search, and i find that missing from ChatGPT of course (at least until they have the module back). I'm on the pro plan of Phind, fwiw.
Hypothetically it could (maybe, i'm assuming) be as valuable for my ChatGPT use cases, but i found that i couldn't just give it the same input i'd give ChatGPT, as Phind would then search for an answer and come back with.. well, things from the internet which wasn't what i was wanting from that ChatGPT interface. I struggle to think of an example, though.. so hopefully this vague description is still of use hah.
2. Where Phind excels of course is digging answers out of the web, finding API solutions, wiring those results up into code, etc. However unfortunately this still seems a complex task. I do not find Phind to be accurate enough. It usually does a decent job at inferring the solution from the results, but it struggles with knowing library versions, context of the search results, etc.
I find myself using Phind primarily as a quick jumping off point for search results.. but i still often need to still search myself to figure out the actual code. So when i feel like i still need to search anyway, and that i feel i gave up ChatGPT for Phind (due to item #1), then it's just a tough position to justify Phind over CGPT for me.
For context usually i'm using and searching about Rust.
Fwiw i've still not decided one way or another. Though i'm definitely on the fence. Hope this vague and off the top of my head post helps a bit.
Off the top of my head i think if the link is correct, Phind is correct.
It's a tough problem though. I suspect the difficulty lies in a lot of search results not containing the appropriate versions/etc at all. So you have to go to secondary/etc steps of looking up library APIs and knowing that the two are incompat.
We see Phind as a superset of ChatGPT. For the problems where search results may not be relevant, it should still function as GPT-4. Do you see it performing worse in your use case?
As for mistaken library versions, we’re working on developing our own index as a long term fix. But in the meantime you should be able to tell it the proper version and it should work.
So our hope is that Phind is a complete ChatGPT replacement for devs. Soon we’ll be rolling out our own models alongside GPT-4 that will bring additional speed and quality improvements.
I’d be happy to chat further with you directly, my email is michael(at)phind.com
I did, but honestly i've not tried it in a while. I'll keep this in mind and try to give it a go again before i cancel/go back to CGPT.
> As for mistaken library versions, we’re working on developing our own index as a long term fix. But in the meantime you should be able to tell it the proper version and it should work.
That is true, i rarely give it my library versions. Though, i feel what's needed is frequently versions are ambiguous in results. In the case of something like Rust, i would take a search result, go to docs.rs/foo and see if those results exist in the lib. Usually that's the mismatched step, something i'm unsure if Phind is doing at all.
I'll try giving it versions more frequently, though.
Unrelated side note: i'd love if Phind had nothing user/pass auth or at the very least much longer valid logins. Using email on multiple devices is a bit annoying for me. For me (i use anonymous emails) it's all the downsides of auth, but plus email validation every time hah. Though this is not making me cancel or anything, i just had to login again and figured i'd vent my small annoyance :)
Does it really kick you out every time you visit? Login sessions should last for at least two weeks. Do you have any privacy settings that might be interfering with our cookie?
> What is the difference between searx and SearxNG?
> TL;DR: SearXNG is for users that want more features and bugs getting fixed quicker. If you prefer a minimalist software and stable experience, use searx.
> SearxNG is a fork of searx, created by a former maintainer of searx. The fork was created because the majority of the maintainers at the time did not find the new proposed features privacy respecting enough. The most significant issue is with engine metrics.
> Searx is built for privacy conscious users. It comes with a unique set of challenges. One of the problems we face is that users rather not report bugs, because they do not want to publicly share what engines they use or what search query triggered a problem. It is a challenge we accepted.
> The new metrics feature collects more information to make engine maintenance easier. We could have had better and more error reports to benefit searx maintainers. However, we believe that the users of searx must come first, not the software. We are willing to compromise on the lack of issue reports to avoid violating the privacy of users.
> Furthermore, SearxNG is under heavy refactoring and dependencies are constantly updated, even if it is unnecessary. It increases the risk of introducing regressions. In searx we strive for stability, rather than moving fast and breaking things.
In other words, marketing BS. If I don't want aggregate stats, I won't collect them. I'm a big person now and can decide that for myself, thanks.
Not reporting the problems in the engines do not benefit to the users, if nothing works why use SearX in the first place then? I would even say it's a major advantage to have the ability to quickly and easily report the issue, this way the users are all getting quick fixes as soon as something break. We rely on unstable API or ways to extract the results from the engines, it doesn't make any sense to not have a system that allow to report the instabilities.
It is true that SearXNG code base change a lot faster than SearX one when it was still actively maintained, but that's because our users want to see the software evolve to new needs, and like I said above relying on unstable ways to extract the data require us to improve the software so that it still works with the engines we rely on. A major feature we added is the new anti bot available on the public instances, it allows having public instances that work with almost all the engines instead of getting errors all over the place because bots were abusing the instance.
The point being.. prescribing language is pointless. People will say what they will.
But I get your point. I say ‘kwebek’ and not ‘kebek’ and ‘MAdrid’ not maDRID.
(You're right though, even if some people are being silly about that one)
Oftentimes though locals are like “just call it Sweden, we know you will butcher Sverige” or “just call it Finland, we know you will mess up Suomi”
It actually often confuses people when you are speaking in English and use the appropriate pronunciation for that language. Like it would throw someone off if I was in Sweden speaking English and said the Swedish way of saying Gothenburg instead (which, depending on where you are from in Sweden, can sound something like “YOT eh boy” with a silent or very soft G at the end)
In your case, it's like pronouncing Rome as Rom-EH, because it sounds cool to you.
Or you can justify your ignorance and inability to literally shift the stress one syllable over with any story you like, if you prefer.
I'm pretty sure people in New York calling it Neuva York soon get corrected, and soon correct themselves. You'd have a hard time living in Britain by being so stubbornly reluctant at learning the correct pronunciation of places.
In any case I’m not in Madrid and the people saying ‘nweva joR’ may not be in New York either.
And despite Erdogan’s pronouncements I’ll keep on saying Turkey.
Postgres-QL rolls off the tongue better than PostgreSequel.
But that makes it sound like something between "sex" "sacks" and "sucks", which is less flattering.