The focus on the top 10 in vector search is a product of wanting to prove value over keyword search. Keyword search is going to miss some conceptual matches. You can try to work around that with tokenization and complex queries with all variations but it's not easy. Vector search isn't all that new a concept. For example, the annoy library (https://github.com/spotify/annoy), an open source embeddings database. - Source: Hacker News / 10 months ago

If you want to go larger you could still use some simple setup in conjunction with faiss, annoy or hnsw. Source: 12 months ago

I then use annoy to compare them. Annoy can use different measures for distance, like cosine, euclidean and more. Source: about 1 year ago

Yes you can do this for equality predicates if your row groups are sorted . This blog post (that I didn't write) might add more color. You can't do this for any kind of text searching. If you need to do this with file based storage I'd recommend using a vector based text search and utilize a ANN index library like Annoy. Source: about 1 year ago

If you need large scale (1000+ dimension, millions+ source points, >1000 queries per second) and accept imperfect results / approximate nearest neighbors, then other people have already mentioned some of the best libraries (FAISS, Annoy). Source: about 1 year ago

This has lead to a delightful variety of custom clients like https://phanpy.social/ - https://elk.zone/ is another example that I really like. It's the complete opposite of the Twitter API situation, where they locked their API down and killed the entire ecosystem of third-party clients. - Source: Hacker News / 2 months ago

And there are tons of third party clients. I think Tusky is the best one I’ve seen for Android, and there’s an interesting web-based one called Elk that’s very nice. You load up https://elk.zone and then use it as a front-end to sign in to your server. - Source: Hacker News / 10 months ago

The answer to that is https://elk.zone atm, a fun and chef's kiss interface (built with nuxt). You can insert elk.zone/ before any Mastodon url. https://phanpy.social is also great, with multi columns even for lists. A browser plugin (like "Mastodon – Simplified Federation") to follow, favorite, etc. Directly on any server has also improved my experience a lot. - Source: Hacker News / 11 months ago

Quick! Tell Obama and Taylor Swift about https://elk.zone! They're going to be so excited! - Source: Hacker News / 12 months ago

Try https://elk.zone with your exisitng mastodon account, which is precisely that. - Source: Hacker News / 12 months ago