Live data from Hacker News

Viewing profile — diqi

diqi

HN member
Joined
Thu, Apr 18, 2019, 6:02 AM UTC
HN karma
75
Public activity
26 items

About diqi

Company Website: https://lantern.dev Company Twitter: https://twitter.com/lanterndb Company Github: https://github.com/lanterndata/lantern

Personal(ish) Twitter - https://twitter.com/diqitally

Recent public activity

  1. comment
    Comment #46919161

    What does this even say?

  2. comment
  3. story
  4. comment
    Comment #44118781

    What's so different about auth for B2B?

  5. story
  6. comment
    Comment #41591490

    Thank you! It’s just naively showing the first 20 results at the moment from FTS or vector search. Thanks for the feedback! I’ll make some edits. You can actually search all the ch…

  7. story
    Show HN: View and search Postgres mailing lists

    I built a site to browse the Postgres mailing list archives. It supports search using full text search from Postgres + vector search with the Lantern Postgres extension. I've been …

  8. story
  9. story
  10. story
  11. comment
    Comment #39009342

    Auricle (W21) and AudioFocus (S19) were two YC startups around hearing, I'm not sure what the status of them is though.

  12. comment
    Comment #38873980

    I added an edited note to the bottom of the blog post. The original post and the experiments were created before pgvector 0.5.1 was out, and we had not realized there was significa…

  13. comment
    Comment #38871666

    > Next up: an AI that can watch a deceptive mobile game ad and actually create the game that they're falsely advertising! Would love if it could create Age of Origins, I always lik…

  14. comment
    Comment #38851259

    We used 0.5.0 for these

  15. comment
    Comment #38848731

    Hi, sorry that you didn't have a good experience with Lantern before. We first posted in HN about 3 months ago - Things should be better now, please let us know if you have any iss…

  16. comment
    Comment #38847814

    We haven't benchmarked against 0.5.2 yet so I can't share exact numbers. We will benchmark it once it is released. We think our approach will still significantly outperform pgvecto…

  17. comment
    Comment #38847343

    Ah, thank you for noticing! We actually have typo in the error message. It actually should be the operator instead of . There's some context on the operator here: https://github.co…

  18. comment
    Comment #38847311

    Try YCW24! :)

  19. comment
    Comment #38847013

    Yes it is WAL protected: the advantage of external indexing is that the HNSW graph is being constructed externally on multiple cores instead on a single core inside the Postgres pr…

  20. story
  21. comment
    Comment #37501856

    pgvector is written in C and is supported by Supabase. There's nothing inherent preventing Supabase from supporting Lantern.

  22. comment
    Comment #37501749

    Unless Supabase decides to integrate Lantern (currently they integrate pgvector) you unfortunately cannot use Lantern with Supabase. That said, we will offer Lantern Cloud, our own…

  23. comment
    Comment #37501565

    We don’t do cleanup of the index during VACUUM yet. That said, it’s coming very soon. We’re built on top of Usearch, which supports deletes. We plan to work with the Usearch team t…

  24. comment
    Comment #37501247

    > There's a fourth metric that I'm really interested in: assuming it's possible, how long does it take to update the index with just one or two updated or inserted vectors? Here’s …

  25. comment
    Comment #37501225

    Thanks! I don’t believe pgvector reports performance changes between releases. At the moment, we run the benchmarking on Github CI, but we plan to move this to an external machine,…