Advanced Embedding Models and Techniques for RAG

Поділитися
Вставка
  • Опубліковано 21 січ 2025

КОМЕНТАРІ • 8

  • @statickzz2021
    @statickzz2021 14 годин тому

    Interesting stuff !

  • @unshadowlabs
    @unshadowlabs 20 годин тому

    Great video! Would be interesting to see how the nomic-embed-text-v1.5 + bm25, from your previous video, performs compared to the newer Nomic ModernBert + bm25 mentioned in this video. Any idea on how much of a speed and accuracy difference between the two?

    • @TrelisResearch
      @TrelisResearch  14 годин тому +2

      Probably 2-3x faster.
      But also scoring maybe 20-30% better

  • @divyagarh
    @divyagarh 3 години тому

    Hi Ronan, Thank you for all your great videos. Super helpful and educational videos.
    Can you please do a video on agents? I mean using a custom LLM to decide which vector DB to retrieve from or if LLM can make the decision to retrieve proper documents or results based on the query?

    • @TrelisResearch
      @TrelisResearch  Годину тому +1

      Oh yeah! It’s coming up soon!

    • @divyagarh
      @divyagarh 56 хвилин тому

      @TrelisResearch great! Thanks a lot!

  • @deathdefier45
    @deathdefier45 19 годин тому

    You hve the best AI content on here.