Adding Agentic Layers to RAG

แชร์
ฝัง
  • เผยแพร่เมื่อ 24 ธ.ค. 2024

ความคิดเห็น •

  • @RobertFitz-r8r
    @RobertFitz-r8r 8 หลายเดือนก่อน +5

    Awesome presentation. Clear, well-structured, and easy-to-follow. Love the term "Dynamic QA System" rather than bucketing all internal knowledge query use-cases into RAG. Adding agents at different locations of a vanilla RAG workflow seems to be a powerful system architecture for solving a large set of QA use cases. Lots of food for thought!

    • @VolodymyrLisivka
      @VolodymyrLisivka 3 หลายเดือนก่อน

      The best presentation about simple for loop.

  • @johnwallis1626
    @johnwallis1626 8 หลายเดือนก่อน +6

    good presentation, my issue is using langchain/llama in production, they just add another unnecessary and buggy layer, maybe things will change moving forward, also adding layers of agents can ramp up costs quite significantly, which is where need for good open source llms comes in.

  • @burnt1ce85
    @burnt1ce85 5 หลายเดือนก่อน

    15:39 what is ReAct’s performance like when it loops many times? I assume it can be costly and slow if it loops 10+ times.

    • @rajbiswas776
      @rajbiswas776 4 หลายเดือนก่อน

      It is but the output is much more clarified that what you would have in one loop

  • @nexuslux
    @nexuslux 8 หลายเดือนก่อน +1

    Nice presentation. Just didn’t see enough from llama index… but very well spoken and interesting.