KAG Graph + Multimodal RAG + LLM Agents = Powerful AI Reasoning

Поділитися
Вставка
  • Опубліковано 4 січ 2025

КОМЕНТАРІ • 14

  • @steffenp1113
    @steffenp1113 2 дні тому +2

    Very cool stuff! Is there also a pure English version of the software without Chinese?

    • @GaoDalie_AI
      @GaoDalie_AI  День тому

      Thank you for watching. Unfortunately, I didn’t find any similar projects in pure English. If I do come across one, I will definitely share it with you all

  • @GaoDalie_AI
    @GaoDalie_AI  2 дні тому +3

    Guys if you like the project please consider to hit ⭐
    Paper: arxiv.org/pdf/2409.13731
    Github: github.com/OpenSPG/KAG
    ❣join to my Patreon: www.patreon.com/GaoDalie_AI
    🙏Thank you so much for watching guys! I would highly appreciate it if you
    Book an Appointment with me: topmate.io/gaodalie_ai
    Support the Content (every Dollar goes back into the video): buymeacoffee.com/gaodalie98d
    Subscribe Newsletter for free: substack.com/@gaodalie
    FOLLOW ME :
    join my discord if you have any questions: discord.gg/GENrSVJN
    Follow me on Twitter: x.com/GaoDalie_AI
    Follow me on Linkedin: shorturl.at/dnvEX

  • @조바이든-r6r
    @조바이든-r6r День тому +1

    Isnt it like google deep research?

    • @GaoDalie_AI
      @GaoDalie_AI  День тому

      In my opinion, because OpenKAG is a series of developments, many concepts are involved before they can come up with a final product

  • @AymanHaneen
    @AymanHaneen День тому +1

    The configurations structures pls , Iam a beginner

    • @GaoDalie_AI
      @GaoDalie_AI  День тому

      Please consider joining my substack where you will find all my articles: substack.com/@gaodalie

  • @xXWillyxWonkaXx
    @xXWillyxWonkaXx 2 дні тому

    Great video.

    • @GaoDalie_AI
      @GaoDalie_AI  2 дні тому

      Thank you for taking time to watch the video and i appreciate your input

  • @artur50
    @artur50 2 дні тому +2

    Thx for the video, great idea, pls consider a tutaorial plus test including testing queries on a large document like financial reports from market companies or whole books on a niche topic so that an LLM has (almost) no data on…

    • @GaoDalie_AI
      @GaoDalie_AI  2 дні тому +1

      Thanks for watching! I’ll do my best in the next video and try it out on large documents. KAG is really cool, and their architecture and algorithm design are impressive. I’ve played around with their code, and it looks super promising!

    • @artur50
      @artur50 2 дні тому

      @ superb!

  • @amrohendawi6007
    @amrohendawi6007 День тому +1

    Terrible video on many aspects:
    - the demo doesn't show where this KAG solution replaces RAG
    - the input file and query are too simple and do not need a KAG to solve

    • @GaoDalie_AI
      @GaoDalie_AI  День тому

      Hey, thank you for watching! If you rewatch the video carefully, you’ll notice that at the beginning, I addressed the RAG problem and explained how KAG solves it. I also compared it with GraphRAG, so I have covered everything about KAG. If you’re still not familiar with RAG, I recommend watching my videos, as I’ve covered many topics related to it.