Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Building a web search engine from scratch with 3B neural embeddings

blog.wilsonl.in

Post reply on HN
Print view View original

11–20 of 124 posts

Re: Show HN: Building a web search engine from scratch with 3B neural embeddings

#11

Post by yorwba »

giancarlostoro wrote: post #3

This then begs the question for me, without an LLM what is the approach to build a search engine? Google search used to be razor sharp, then it degraded in the late 2000s and early 2010s and now its meh. They filter out so much content for a billion different reasons and the results are just not what they used to be. I've found better results from some LLMs like Grok (surprisingly) but I can't seem to understand why…

When I encounter the "cannot find verbatim quote I remember" problem and then later find what I was looking for in some other way, I usually discover that I misremembered and the actual quote was different. I do prefer getting zero results in that case, though.

Re: Show HN: Building a web search engine from scratch with 3B neural embeddings

#12

Post by ASalazarMX »

andai wrote: post #5
giancarlostoro wrote: post #3

This then begs the question for me, without an LLM what is the approach to build a search engine? Google search used to be razor sharp, then it degraded in the late 2000s and early 2010s and now its meh. They filter out so much content for a billion different reasons and the results are just not what they used to be. I've found better results from some LLMs like Grok (surprisingly) but I can't seem to understand why…

My understanding was that every few months Google was forced to adjust their algorithms because the search results would get flooded by people using black hat SEO techniques. At least that's the excuse I heard for why it got so much worse over time. Not sure if that's related to it ignoring quotes and operators though. I'd imagine that to be a cost saving measure (and very rarely used, considering it keeps accusing m…

This is my take as well. When websites were few, directories were awesome. When websites multiplied, Google was awesome. When websites became SEO trash, social networks were awesome. When social networks are become trash, I'm hoping the Fediverse becomes the next awesome.

I don't see AI in any form becoming the next awesome.

Re: Show HN: Building a web search engine from scratch with 3B neural embeddings

#13

Post by ccgreg »

At the end, the author thinks about adding Common Crawl data. Our ranking information, generated from our web graph, would probably be a big help in picking which pages to crawl.

I love seeing the worked out example at scale -- I'm surprised at how cost effective the vector database was.

Re: Show HN: Building a web search engine from scratch with 3B neural embeddings

#14

Post by jobswithgptcom »

I been doing a smaller version of the same idea for just domain of job listings. Initially I looked at HNSW but couldn't reason on how to scale it with predictable compute time cost. I ended up using IVF because I am a bit memory starved. I will have to take at look at coreNN.

Re: Show HN: Building a web search engine from scratch with 3B neural embeddings

#15

Post by Imustaskforhelp »

This is really really cool. I had earlier wanted to entirely run my searches on it and though that seems possible, I feel like it would be sadly a little bit more waste of time in terms of searches but still I'll maybe try to run some of my searches against this too and give me thoughts on this after doing something like this if I could, like, it is a big hit or miss but it will almost land you to the right spot, like not exactly.

For example, I searched lemmy hoping to find the fediverse and it gave me their liberapay page though.

Please, actually follow up on that common crawl promise and maybe even archive.org or other websites too and I hope that people are spending billions in this AI industry, I just hope that you can whether even through funding or just community crowdwork, actually succeed in creating such an alternative. People are honestly fed up with the current search engine almost monopoly.

Wasn't Ecosia trying to roll out their own search engine, They should definitely take your help or have you in their team..

I just want a decentralized search engine man, I understand that you want to make it sustaianable and that's why you haven't open sourced but please, there is honestly so much money going into potholes doing nothing but make our society worse and this project almost works good enough and has insane potential...

Please open source it and lets hope that the community tries to figure out a way around some ways of monetization/crowd funding to actually make it sustainable

But still, I haven't read the blog post in its entirety since I was so excited that I just started using the search engine.., But I feel like the article feels super indepth and that this idea can definitely help others to create their own proof of concepts or actually create some open source search engine that's decent once and for all.

Not going to lie, But this feels like a little magic and I am all for it. I have never been this excited the more I think about it of such projects in actual months!

I know open source is tough and I come from a third country but this is actually so cool that I will donate ya as much as I can / have for my own right now. Not much around 50$ but this is coming from a guy who has not spent a single penny online and wanting to donate to ya, please I beg ya to open source and use that common crawl, but I just wish you all the best wishes in your life and career man.

Re: Show HN: Building a web search engine from scratch with 3B neural embeddings

#16

Post by msgodel »

giancarlostoro wrote: post #3

This then begs the question for me, without an LLM what is the approach to build a search engine? Google search used to be razor sharp, then it degraded in the late 2000s and early 2010s and now its meh. They filter out so much content for a billion different reasons and the results are just not what they used to be. I've found better results from some LLMs like Grok (surprisingly) but I can't seem to understand why…

I wish there was an old fashioned n-gram + page rank search engine for those of us who don't mind the issues the older Google had. I've thought about making my own a few times.

Re: Show HN: Building a web search engine from scratch with 3B neural embeddings

#17

Post by Imustaskforhelp »

ASalazarMX wrote: post #12
andai wrote: post #5

Earlier quoted context omitted.

My understanding was that every few months Google was forced to adjust their algorithms because the search results would get flooded by people using black hat SEO techniques. At least that's the excuse I heard for why it got so much worse over time. Not sure if that's related to it ignoring quotes and operators though. I'd imagine that to be a cost saving measure (and very rarely used, considering it keeps accusing m…

This is my take as well. When websites were few, directories were awesome. When websites multiplied, Google was awesome. When websites became SEO trash, social networks were awesome. When social networks are become trash, I'm hoping the Fediverse becomes the next awesome. I don't see AI in any form becoming the next awesome.

I wish all the best wishes to fediverse too. I'd like to take this one step too that communities have gone a similar transition too from forums to mostly now discord and I wish them to move to something like matrix which is federated (yes I know it has issues, but trust me sacrifices must be made)

What are your thoughts on things like bluesky/nostr and (matrix) too.

Bluesky does seem centralized in its current stage but its idea of (pds?) makes it fundamentally hack proof in the sense that if you are on a server which gets hacked, then your account is still safe or atleast that's the plan, not sure about its current implementation.

I also agree with AI not being the next awesome. Maybe for coding sure, but not in general yeah. But even in coding man, I feel like its good enough and its hard to catch more progress from now on and its just not worth it but honestly that's just me.

Re: Show HN: Building a web search engine from scratch with 3B neural embeddings

#18

Post by ASalazarMX »

Imustaskforhelp wrote: post #17
ASalazarMX wrote: post #12

Earlier quoted context omitted.

This is my take as well. When websites were few, directories were awesome. When websites multiplied, Google was awesome. When websites became SEO trash, social networks were awesome. When social networks are become trash, I'm hoping the Fediverse becomes the next awesome. I don't see AI in any form becoming the next awesome.

I wish all the best wishes to fediverse too. I'd like to take this one step too that communities have gone a similar transition too from forums to mostly now discord and I wish them to move to something like matrix which is federated (yes I know it has issues, but trust me sacrifices must be made) What are your thoughts on things like bluesky/nostr and (matrix) too. Bluesky does seem centralized in its current stage…

I think BlueSky still needs to prove itself. It is what Twitter/X was a decade ago, before the enshittification, and I enjoy the content a lot, with my reservations.

The weakness of Mastodon (and the Fediverse IMO), is that you can join one of many instances, and it becomes easier to form an echo chamber. Your feed will the the Fediverse hose (lots of irrelevant content), your local instance (an echo chamber), or your subscriptions (curating them takes effort). Nevertheless, that might be as well a strength I'm not truly appreciating.

Re: Show HN: Building a web search engine from scratch with 3B neural embeddings

#19

Post by 1gn15 »

This is incredibly, incredibly cool. Creating a search engine that beats Google in quality in just 2 months and less than a thousand dollars.

Really great idea about the federated search index too! YaCy has it but it's really heavy and never really gave good results for me.

Re: Show HN: Building a web search engine from scratch with 3B neural embeddings

#20

Post by reactordev »

andai wrote: post #5
giancarlostoro wrote: post #3

This then begs the question for me, without an LLM what is the approach to build a search engine? Google search used to be razor sharp, then it degraded in the late 2000s and early 2010s and now its meh. They filter out so much content for a billion different reasons and the results are just not what they used to be. I've found better results from some LLMs like Grok (surprisingly) but I can't seem to understand why…

My understanding was that every few months Google was forced to adjust their algorithms because the search results would get flooded by people using black hat SEO techniques. At least that's the excuse I heard for why it got so much worse over time. Not sure if that's related to it ignoring quotes and operators though. I'd imagine that to be a cost saving measure (and very rarely used, considering it keeps accusing m…

This is correct. Marketing and Advertising manipulated pages to gain higher rankings because they figured out the algorithm behind it. Forcing Google to change the algorithm. Originally, prior to the flood of garbage and hidden ’s it was very good at linking content together. Now, it’s a weighted database.
Post reply on HN