Live data from Hacker News

Viewing profile — gujun720

gujun720

HN member
Joined
Mon, Oct 21, 2019, 8:07 AM UTC
HN karma
5
Public activity
20 items

About gujun720

No profile information was provided.

Recent public activity

  1. comment
    Comment #29561735

    You can check out these demo cases( https://github.com/milvus-io/bootcamp ) to get a better sense of the capability of the vector search/vector database.

  2. comment
    Comment #29561723

    Check my project Milvus vector database ( https://milvus.io ). We've published a bunch of demo cases powered by vector database on GitHub. https://github.com/milvus-io/bootcamp

  3. comment
    Comment #27550573

    I'd like to hear any feedback from who has tried this out.

  4. story
  5. comment
    Comment #23369774

    It will be helpful, if the author could compare the performance of WASM back end. Will it be better than Model runtime with HTTP support?

  6. comment
  7. story
  8. comment
    Comment #22030249

    Good points. I want to add one more. I think the Ann benchmark should pay more attention on 1. The index building speed, as this is very important in some production scenarios. Now…

  9. comment
    Comment #22030161

    It's not about the ML platform. It's about the ML scenarios. If you want to search thru a huge amount of unstructured data after vectorization tech (like deep learning), Milvus wil…

  10. comment
    Comment #22030075

    200 GB is the size of original vectors. When creating index, Milvus supports IVF SQ8 and IVF PQ ADC. Based on our users experience, SQ8 is the most balanced one at this moment. SQ8…

  11. comment
    Comment #22019821

    Milvus could run on arm CPU. We ported it to Nvidia Jetson NANO and Raspberry PI 4 (4GB mem) so far. Most people told us running Milvus on arm looked cool but they were not sure if…

  12. comment
    Comment #22018985

    Correct, new vectors will first be searched thru brute force until the index is created on that file slice.

  13. comment
    Comment #22017554

    Please check https://medium.com/@milvusio/managing-data-in-massive-scale-... It explains how Milvus managing vectors.

  14. comment
    Comment #22017546

    We are working on this feature which allows use to perform hyper search (attributes plus feature vectors). And you can code your scoring rules. Again, hopefully be ready by the end…

  15. comment
    Comment #22017503

    We have some test reports in https://github.com/milvus-io/milvus/tree/master/tests At this moment, the IVF indecies are based on FAISS. So the performance is the same as Faiss. IVF…

  16. comment
    Comment #22017455

    You may check our Medium site. We will post more tech details. https://medium.com/@milvusio

  17. comment
    Comment #22017449

    Milvus allows users to append vectors. Vectors are stored in multiple file slices. When a file slice reaches the threshold, Milvus will build the index for that file slice, and new…

  18. story
  19. story
  20. story