NEW Knowledge Graph based RAG: SimGRAG (no training)

Поділитися
Вставка
  • Опубліковано 8 лют 2025
  • Excellent new Knowledge Graph based RAG system called SimGraphRAG, or simply SimGRAG.
    Overview of our four classical KG-based RAG systems, and the new SimGRAG, which outperform them. Short technical deep dive into the new methods and algorithms, plus code via GitHub repo.
    All rights w/ authors:
    SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs
    Driven Retrieval-Augmented Generation
    Yuzheng Cai, Zhenyue Guo, Yiwen Pei, Wanrui Bian, Weiguo Zheng
    from Fudan University
    #airesearch
    #knowledgegraph
    #science
    #aiagents
    #graph

КОМЕНТАРІ • 20

  • @code4AI
    @code4AI  Місяць тому

    With the automatic audio dubbing from UA-cam /Google you hear a synthetic voice in your regional language.
    To hear my original voice in English, switch to "Default" or "English" in the settings. Thank you.

    • @raihantayeb
      @raihantayeb Місяць тому

      I liked your video but your voice sound is low compared to other YT videos.

  • @WinonaNagy
    @WinonaNagy Місяць тому +3

    SimGRAG reshapes the landscape of KG-based RAG. The GitHub repo holds the keys to its success. Well done, Fudan team!

  • @Max030994
    @Max030994 Місяць тому +3

    This is awesome! I’m actually working on implementing this solution in the aerospace domain, so this is incredibly useful! Thanks for sharing, I’ll probably go dig into the white-paper so that I can see what they’re doing differently and what I can learn 😊

    • @ayoubfr8660
      @ayoubfr8660 Місяць тому

      Hi man, I am doing the same for another engineering domain, would be nice to discuss and explore!

  • @bhaweshs8461
    @bhaweshs8461 Місяць тому +4

    I used lightRAG with neo4J as gRAG repo and very impressed with its gRAG capabilities.

  • @CharlotteLopez-n3i
    @CharlotteLopez-n3i Місяць тому

    Game changing development in KG-based RAG systems! SimGRAG shows significant improvement. Looking forward to exploring the GitHub repo. #AIResearch #Science

  • @MatthewSanders-l7k
    @MatthewSanders-l7k Місяць тому

    SimGRAG's optimization of KG-based RAG using similar subgraphs is revolutionary. Huge thanks to the Fudan University team. #AIagents

  • @patruff
    @patruff Місяць тому +14

    What about Light RAG?

  • @NaveenReddy-p5j
    @NaveenReddy-p5j Місяць тому

    SimGRAG is a game-changer in KG-based RAG systems. Can't wait to explore its advanced methods and code. #airesearch #knowledgegraph

  • @harisjaved1379
    @harisjaved1379 Місяць тому +6

    Hi my friend! Can you explain how it’s different from neo4j graph rag and lightrag?

  • @thingX1x
    @thingX1x Місяць тому +1

    I love your voice :D

  • @covertassassin1885
    @covertassassin1885 Місяць тому

    Would you say this is similar to HyDE but its more like HyGE where the LLM generates a hypothetical graph to use for retrieval instead of a hypothetical document?

  • @misterloafer5021
    @misterloafer5021 Місяць тому

    Thank you very much for this. Do you have any particular video or reference to recommend to build “small but smart vector spaces” for a particular domain?

    • @code4AI
      @code4AI  Місяць тому

      Depends on your technical terms in your domain and your training of the tokenizer, plus optimal size of vocabulary (I work currently with 75K for physics).

  • @christopherd.winnan8701
    @christopherd.winnan8701 Місяць тому +2

    How does this compare to more well-established KG tools, such as Infranodus?

  • @h.h.c466
    @h.h.c466 Місяць тому

    14:00 the mapped node for a placeholder in the pattern graph (triples) will Not be evaluated concerning distance ... .really? . so we are sort of putting emphasis on the source node and explicitly known relationships ? could not at least the node type be accounted for? I mean we know in the examples that it is a unknown director or movie ? Or is that so encoded in the known parts via embedding, as to Not matter? I find it quite astonishing..

  • @justinnine4940
    @justinnine4940 Місяць тому

    the retrieval mechanism is too naive, it can’t be really useful in practice.
    For example, the system would fail to answer the query “which country is Sacramento located in” because the KG has the structure: Sacramento California United States
    Here the query has 2 nodes while the KG subgraph has 3. They wouldn’t match!

    • @code4AI
      @code4AI  Місяць тому +2

      You comment includes "would " and "wouldn't". Therefore I assume, you have not implemented a real test, but you are just guessing?