Live data from Hacker News

Show HN: WordFor – a free, open, private reverse dictionary running on browser

wordfor.xyz

1–6 of 6 posts

Show HN: WordFor – a free, open, private reverse dictionary running on browser

#1
We all know the feeling: can’t remember the word but we know what it means. That’s why I built:

WordFor - a reverse dictionary where you describe a concept and it suggests the word you’re looking for.

- Runs entirely in the browser (no server calls) - No ads, tracking, or accounts - Low latency (results show up immediately as you type)

Curious how well it works for other people, and happy to answer questions about the approach or tradeoffs.

Technical Blog explaining the workings: https://zshn25.github.io/wordfor-reverse-dictionary/

Show HN: WordFor – a free, open, private reverse dictionary running on browser
wordfor.xyz

Re: Show HN: WordFor – a free, open, private reverse dictionary running on browser

#4
post #3

[flagged]

I first compute the embeddings to the dictionaries and store these. At query-time, when the user inputs the description, its embeddings are again computed by a lighter model. Then comparison happens between this and the stored ones

Re: Show HN: WordFor – a free, open, private reverse dictionary running on browser

#5
It is very well done congratulations! I am building an installable web app catalog, and I am happy to see other apps using offline content download instead of server-client roundups for search queries. It works very well and this is comforting me in keeping the same strategy!

Your app being a PWA, I will list it at https://korru.app :)

Re: Show HN: WordFor – a free, open, private reverse dictionary running on browser

#6

It is very well done congratulations! I am building an installable web app catalog, and I am happy to see other apps using offline content download instead of server-client roundups for search queries. It works very well and this is comforting me in keeping the same strategy! Your app being a PWA, I will list it at https://korru.app :)

Thank you for your kind words. Great catalog. I found WordFor already.