Meet KAG: Supercharging RAG Systems with Advanced Reasoning

แชร์
ฝัง
  • เผยแพร่เมื่อ 2 ม.ค. 2025

ความคิดเห็น •

  • @engineerprompt
    @engineerprompt  3 วันที่ผ่านมา +5

    If you are interested in learning more about Advanced RAG systems, checkout my RAG Beyond Basics Course: prompt-s-site.thinkific.com/courses/rag

    • @RohitSharma-uw2eh
      @RohitSharma-uw2eh 2 วันที่ผ่านมา

      Why hindi audio track is not available 😢

  • @kai_s1985
    @kai_s1985 19 ชั่วโมงที่ผ่านมา +1

    nice. wondering if we can use this on groq platform to speed things up?

  • @SullyOrchestration
    @SullyOrchestration 3 วันที่ผ่านมา +8

    I've tried this and unfortunately it's way too slow (30 seconds for a query with a 2 sentence output!) and does not produce its 'logical form solver' transparently enough. We don't know what chunks were retrieved or from where. Unfortunately it's still quite a way from being usable in a practical app.

    • @KoteikiJan
      @KoteikiJan 2 วันที่ผ่านมา

      It depends on the use case! Sometimes it's acceptable to wait a few minutes, or maybe even hours.

  • @u007james
    @u007james 3 วันที่ผ่านมา +5

    how does continual update works with kag

    • @xt3708
      @xt3708 2 วันที่ผ่านมา +3

      Same q!!

  • @IamalwaysOK
    @IamalwaysOK วันที่ผ่านมา

    Is there any way to use "Medical Information Extraction" instead of OpenIE?

  • @ai_handbook
    @ai_handbook 3 วันที่ผ่านมา

    Very nicely explained, congrats mate! 👏👏👏

  • @zhalberd
    @zhalberd 17 ชั่วโมงที่ผ่านมา

    Thank you for this video. Please make a follow up on how to build this. 🙏🏻

  • @RodCoelho
    @RodCoelho 8 ชั่วโมงที่ผ่านมา

    How does it compare with light RAG? Is it Better?

  • @eshandas3645
    @eshandas3645 2 วันที่ผ่านมา

    Can graph rag establish logical connection between them..

  • @abdshomad
    @abdshomad วันที่ผ่านมา

    How is it compared to llm-graph-builder from neo4j?

    • @engineerprompt
      @engineerprompt  วันที่ผ่านมา +1

      wasn't aware of it. Will need to check it out.

  • @donb5521
    @donb5521 2 วันที่ผ่านมา +3

    The premise of Knowledge Augmented Generation is promising, but the current KAG code bases failed to deliver today. The TLDR version is that ultimately I saw no notes or edges created in Neo4j. Even weirder is that in spite of there being no graph it was still giving me results in the UI. (the UI is not open source and appears to be locked down)
    Ultimately the config needs to become more solid and consistent -- and there needs to be agreement between the OpenSPG/openspg and OpenSPG/KAG development teams on whether Ollama is supported.
    An odd mix of Java and Python. Hopefully this gets straightened up soon.
    Prompt Engineering... Normally love your stuff. What would be helpful as a starting point is a Jupyter Notebook from OpenSPG that walks through (and validates) the pipeline step by step. A follow-up would be a reproducible and well documented evaluation against other solutions - LazyGraphRAG, LightRAG / nanorag, etc.

  • @NevilHulspas
    @NevilHulspas 3 วันที่ผ่านมา +9

    Tried it. It's quite slow for answering simple queries. Also indexing about 20 pages in a PDF took about 300k tokens, which is still quite cheap with DeepSeek, but it seems a lot. Indexing also took like an hour or something. User interface is partly chinese, quite a bit of bugs. Seems unfinished.
    Answers that we're outputted were mostly correct though

    • @eshandas3645
      @eshandas3645 วันที่ผ่านมา

      U used openai api key?

  • @patruff
    @patruff 3 วันที่ผ่านมา +10

    Not to be confused with CAG

    • @coom07
      @coom07 2 วันที่ผ่านมา

      I got confused 4 a second. Thanks buddy❤

    • @andydataguy
      @andydataguy 2 วันที่ผ่านมา

      🤣🤣

  • @davidjourno6929
    @davidjourno6929 2 วันที่ผ่านมา

    What about combining KAG and SPARQL ?

  • @RohitSharma-uw2eh
    @RohitSharma-uw2eh 2 วันที่ผ่านมา

    Why hindi audio track is not available

    • @stefanmisic7405
      @stefanmisic7405 วันที่ผ่านมา

      why would we need hindi audio??

    • @RohitSharma-uw2eh
      @RohitSharma-uw2eh วันที่ผ่านมา

      @stefanmisic7405 because youtube add audio track feature is available.may we more enjoy like that mr beast videos

  • @tirushv9681
    @tirushv9681 3 วันที่ผ่านมา +1

    What do you think about Colpali vs KAG? which is the best?

    • @tirushv9681
      @tirushv9681 3 วันที่ผ่านมา

      I feel Colpali performs well with accuracy and cost effective. Because image retrieval is from Colpali and we host it. Thoughts?

    • @MrAhsan99
      @MrAhsan99 3 วันที่ผ่านมา

      @@tirushv9681 Is there anyone providing the api for colpali usage? I want to use this in my app. Want to give access via api to limited users/

  • @Alex-rg1rz
    @Alex-rg1rz 3 วันที่ผ่านมา

    very interesting! thanks

  • @DocRekd-fi2zk
    @DocRekd-fi2zk วันที่ผ่านมา

    Is this based on rdf?

  • @sanjaybhatikar
    @sanjaybhatikar 3 วันที่ผ่านมา

    It is the ReAct prompting with graph backend

  • @rishavranaut7651
    @rishavranaut7651 2 วันที่ผ่านมา +1

    All these things still in infancy stage to be used in real use cases, ..will take time to match up with traditional RAG

    • @engineerprompt
      @engineerprompt  2 วันที่ผ่านมา

      I agree! I am happy to see the progress and the research in retrieval. Retrieval is still one of the most useful applications of the LLMs.

  • @matiasm.3124
    @matiasm.3124 3 วันที่ผ่านมา +1

    Nice can you do the one in python using all local services/llm please.

  • @surajjaiswal1371
    @surajjaiswal1371 2 วันที่ผ่านมา +1

    What is better KAG or Agentic RAG?

    • @engineerprompt
      @engineerprompt  2 วันที่ผ่านมา +1

      You can use KAG as a tool for an agent to do retrieval.

    • @surajjaiswal1371
      @surajjaiswal1371 2 วันที่ผ่านมา

      @@engineerprompt Like the agent part in the Agentic RAG?

    • @engineerprompt
      @engineerprompt  2 วันที่ผ่านมา

      @@surajjaiswal1371 exactly. RAG is just a tool that will be available to your agent.

    • @surajjaiswal1371
      @surajjaiswal1371 2 วันที่ผ่านมา

      @@engineerprompt Okay, thanks!

  • @maniecronje
    @maniecronje วันที่ผ่านมา

    Thank you for sharing great tutorial …reading from others comments it looks like the model is slow with responses which prevented me trying it but nevertheless informative nonetheless thanks 🙏

  • @beppemerlino
    @beppemerlino 3 วันที่ผ่านมา

    amazing!

  • @qadeer.ahmad123
    @qadeer.ahmad123 3 วันที่ผ่านมา +1

    There is also CAG (Cache-Augmented Generation) much more faster.

  • @ankitgadhvi
    @ankitgadhvi วันที่ผ่านมา

    Very helpful tutorial for setup and good explanation on KAG systems however I used it and did not like the answers. it takes too long to give the answers and the answer are not good. also too much time needed to make embeddings from the chunks.

  • @sanjaybhatikar
    @sanjaybhatikar 3 วันที่ผ่านมา +1

    Another day, another -ag 😂

  • @Sri_Harsha_Electronics_Guthik
    @Sri_Harsha_Electronics_Guthik 2 วันที่ผ่านมา

    need python version

  • @JoeCryptola-b1m
    @JoeCryptola-b1m 15 ชั่วโมงที่ผ่านมา

    No FAG? Fetched Augmented Generartion relax everyone. Uses internet fetch over docs that's why it's FAG not RAG

  • @JNET_Reloaded
    @JNET_Reloaded 3 วันที่ผ่านมา

    i notice it tries to use mysql i already have mysql and that default port ofc is in use this is bs! use sql lite or something like a file thats separate from a server and dont require ports ffs!

  • @JNET_Reloaded
    @JNET_Reloaded 3 วันที่ผ่านมา +1

    I would NOT reccomend this bs at all! terrable!

    • @matiasm.3124
      @matiasm.3124 3 วันที่ผ่านมา

      @@JNET_Reloaded why ??? Explain

    • @iftekharshaikh7222
      @iftekharshaikh7222 3 วันที่ผ่านมา +1

      @@matiasm.3124 they have basically being using SQL in the backend and the biggest problem with the Graph based approach is that it adds an LLM in between that increases cost and decreases speed in the indexing process and on top of that they are using 2 LLMs for indexing so double the cost and slower the speed also in the retrieval process they have query decomposition using NLP and stuff the chunk retrieval process is slower than usual as they are also using an LLM in the middle so this approach might get you the best results and relevance uptill now but it will come with high costs and slower speed as another person said that yiu have to wait 30 seconds for a single answer that too was not complicated so there is no practical use for this

  • @SonGoku-pc7jl
    @SonGoku-pc7jl 2 วันที่ผ่านมา

    kag waw! i try project with mypufd4llm, is posible combination with this?