Building a web search engine from scratch with 3B neural embeddings
Web and SaaS
search engine
SHOW HN2025
Legend
Building a web search engine from scratch with 3B neural embeddings
Building a web search engine from scratch with 3B neural embeddings
blog.wilsonl.in#web search engine#neural embeddings#vector search#semantic search
How HN took it
29 positive, 12 neutral or asking, 2 mixed, 11 critical, out of 54 comments about the project. Thread score +0.41.
Idea: 7 for, 2 againstExecution: 1 for, 8 againstDocs: 7 for, 0 againstPricing: 5 for, 0 againstDesign: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Excellent, detailed write-up
From 3 comments
Thank you for sharing! This is one of the coolest articles I have seen in a while on HN. I did some searches and I think the search results looked very useful so far. I…
de6u99er on HNThis must be the best technical article I read on HN in months!
gbrindisi on HNBrilliant write up - learnt a lot.
siquick on HN
Impressive solo effort producing results that rival major engines
From 3 comments
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…
1gn15 on HNThis wasn't even in the realm of what I thought is possible for a single person to do. Incredible work! It doesn't seem that far in diatance from a commercial search engine?…
dcreater on HNIncredibly cool. What a write-up. What an engineer.
tmelm on HN
Objections
Vector-only search misses exact keyword matches
From 1 comment
A vector-only search engine will fail for a lot of common use cases where the keywords do matter. I tried searching for `garbanzo bean stew` and got totally irrelevant bean…
jvia on HN
Ranking favours meta-pages over specialist sources
From 1 comment
Very cool project! Just out of interest, I sent a query I've had difficulties getting good results for with major engines: "what are some good options for high-resolution…
poly2it on HN
Embeddings are open to SEO and prompt-injection style manipulation
From 1 comment
The author claims "It should be far less susceptible to keyword spam and SEO tactics." however anyone with a cursory knowledge of the limitations of embeddings/LLM's knows the…
zipy124 on HN
Requests
Open source the code
From 2 comments
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…
Imustaskforhelp on HNThank you for sharing! This is one of the coolest articles I have seen in a while on HN. I did some searches and I think the search results looked very useful so far. I…
de6u99er on HN
Add Common Crawl or other open crawl data
From 3 comments
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.…
ccgreg on HNThis 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…
Imustaskforhelp on HNNot sure where you are based, but if you were in the EU and had no commercial intentions, you might want to consider adding the crawls from OpenWebSearch.eu, an EU-funded…
jll29 on HN
Questions
Does the demo still work, given CORS errors and no results reported
From 3 comments
Getting a CORS error from the API - is the demo at https://search.wilsonl.in/ working for anyone else?
Flux159 on HNI couldn't get the search working (there was some cors error) . But what a feat and writeup. Wonder Stuck!
rkunnamp on HNIs search.wilconl.in still up? I do not get any search result.
iamcreasy on HN
How much did it cost
From 1 comment
how much did it cost ?
sciencesama on HN
Alternatives named
Google
From 2 comments
Tried this search: What is an sbert embedding? Google still gave me a better result: https://towardsdatascience.com/sbert-deb3d4aef8a4/ Nevertheless this project looks great and…
rkagerer on HNThis wasn't even in the realm of what I thought is possible for a single person to do. Incredible work! It doesn't seem that far in diatance from a commercial search engine?…
dcreater on HN
Kagi
From 1 comment
please, I want to pay for this. 10x better than Kagi which I stopped paying for
profstasiak on HN
YaCy
From 1 comment
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…
1gn15 on HN