Not the author, but at work we've had in the hundreds of millions. Faiss can cer... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		m3at on Dec 14, 2021 \| parent \| context \| favorite \| on: Find anything fast with Google's vector search tec... Not the author, but at work we've had in the hundreds of millions. Faiss can certainly scale. If you do have a tiny index and want to try Google's version of vector search (as an alternative to Faiss), you can easily run ScaNN locally [1] (linked in the article, that's the underlying tech). On small scale I had better perf with ScaNN [1] https://github.com/google-research/google-research/tree/mast...

freediver on Dec 14, 2021 [–]

Thanks for mentioning it. Just tried it and it seems to be faster than Faiss indeed on smaller scale searches.

leobg on Dec 15, 2021 | [–]

There's also hnswlib[1], which has supposedly lower memory requirements and allows for adding new vectors to an existing index.

[1]: https://github.com/nmslib/hnswlib/

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact