Live data from Hacker News

Viewing profile — txtai

txtai

HN member
Joined
Fri, Feb 25, 2022, 9:58 PM UTC
HN karma
243
Public activity
198 items

About txtai

No profile information was provided.

Recent public activity

  1. story
  2. story
  3. story
  4. story
  5. comment
  6. comment
  7. comment
    Comment #35645985

    Excellent work! Hope to see a version that has a friendlier commercial license in the future (current version is CC-BY 4.0 NC).

  8. comment
    Comment #35645915

    If you want something similar to this that is fully downloadable and open source, check this out - https://huggingface.co/NeuML/txtai-wikipedia It's an embeddings database of Wikip…

  9. comment
    Comment #35631128

    [flagged]

  10. story
  11. comment
    Comment #35503773

    SetFit is a great framework for building a text classifier. This is a pretty straight forward problem and a good fit for a standard text classifier as well. Here is an example of f…

  12. story
  13. comment
    Comment #35385133

    [flagged]

  14. comment
    Comment #35381703

    txtai combines Faiss and SQLite to support similarity search with SQL. For example: SELECT id, text, date FROM txtai WHERE similar('machine learning') AND date >= '2023-03-30' GitH…

  15. comment
    Comment #35314801

    txtai combines SQLite and Faiss to enable vector search. It also does a lot more than that. https://github.com/neuml/txtai

  16. story
  17. story
  18. story
  19. story
  20. story
  21. story
  22. story
  23. comment
    Comment #34710387

    The first comment in that article has details on the new model. Not the original author but per their testing they said they paid $70 to encode 1M records. The embeddings are 1536 …

  24. comment
    Comment #34709890

    That's up to you. Many don't want to open an account and pay in order to explore what's possible. There are LLMs available on the HF Hub, such as google/flan-t5-xl.

  25. comment
    Comment #34708301

    Starting with HF models and moving to a large model like GPT3 when the task calls for it is a good approach to take with almost all tasks.