GraphRAG: The Marriage of Knowledge Graphs and RAG: Emil Eifrem

แชร์
ฝัง
  • เผยแพร่เมื่อ 22 พ.ย. 2024

ความคิดเห็น • 65

  • @PrincessKushana
    @PrincessKushana 2 หลายเดือนก่อน +21

    My heart goes out to anyone doing a live tech demo.

  • @Dr_Fat_Ghost
    @Dr_Fat_Ghost 6 วันที่ผ่านมา

    i never commented on any of the tech videos till with my 8 years of experience. I got an interview in few days and i wanted to use graphRAG but i knew about graphDB but this video made me realize few things that its not the number of technical words you use to explain something but its how you make such complicated concept look easy. Kudos Prof Emil Eifrem.
    Please release more videos on different concepts on GraphRAG.

  • @AryanKumarBaghel-cp1jv
    @AryanKumarBaghel-cp1jv หลายเดือนก่อน +2

    Best introductory video for graph rag

  • @babusivaprakasam9846
    @babusivaprakasam9846 หลายเดือนก่อน +1

    Best refresher starter on Graph RAG. Brilliant effort. Respect!

  • @user-pt1kj5uw3b
    @user-pt1kj5uw3b 2 หลายเดือนก่อน +19

    Wish I could have heard more from him

  • @greanbean001
    @greanbean001 2 หลายเดือนก่อน +2

    Clear, concise yet compelling story telling!

  • @mohamedkarim-p7j
    @mohamedkarim-p7j 10 วันที่ผ่านมา +1

    Thank for sharing 👍

  • @IntellectCorner
    @IntellectCorner 2 หลายเดือนก่อน +8

    *𝓣𝓲𝓶𝓮𝓼𝓽𝓪𝓶𝓹𝓼 𝓫𝔂 𝓘𝓷𝓽𝓮𝓵𝓵𝓮𝓬𝓽𝓒𝓸𝓻𝓷𝓮𝓻*
    0:00 - Introduction: Leveraging Data and Relationships
    0:49 - Evolution of Search: From AltaVista to Google
    3:03 - Google’s Knowledge Graph: Concepts and Structure
    4:50 - GraphRAG Era: Integrating LLMs with Knowledge Graphs
    5:28 - What is GraphRAG?
    7:06 - Example: Customer Service Bot with GraphRAG
    8:46 - Benefits of GraphRAG: Accuracy and Development
    10:27 - Easier Development with GraphRAG
    12:00 - Comparing Graph and Vector Representations
    13:40 - Explainability and Governance in GraphRAG
    14:19 - Getting Started with GraphRAG: Data Sources
    15:57 - Demo Introduction: Knowledge Graph Builder Tool
    18:16 - Knowledge Graph Demo: Building and Visualizing Data
    18:48 - Conclusion and QR Code for Resources

  • @animelover5093
    @animelover5093 2 หลายเดือนก่อน +7

    Great stuff now i need to rewrite and migrwte my LLM apps to this for a try

  • @KiranRajendran-d8t
    @KiranRajendran-d8t 2 หลายเดือนก่อน +3

    Great one. Super helpful to understand the usage of graph in RAG

  • @waterislife9
    @waterislife9 16 วันที่ผ่านมา

    Great presentation!

  • @swyxTV
    @swyxTV 2 หลายเดือนก่อน +6

    Amazingly well presented. thank you Emil!

    • @themax2go
      @themax2go 2 หลายเดือนก่อน

      this channel's youtuber's name is "Emil"?

  • @ParitoshLD
    @ParitoshLD 2 หลายเดือนก่อน +3

    knowledge graph as label property , Knowledge graph with owl2 ontologies. Data provenance , uuid creation. There is a good scope in neo4j to have both. Coexistence with ref, owl and label property graph is the one which neo4j should talk

  • @biiiiiimm
    @biiiiiimm 20 วันที่ผ่านมา

    Great présentation thanks !

  • @johnkintree763
    @johnkintree763 2 หลายเดือนก่อน +17

    So, a global digital platform could create a shared graph representation of parts of millions of simultaneous conversations that people around the world select to be merged into a form of collective human and digital intelligence and problem solving.

    • @infraia
      @infraia 2 หลายเดือนก่อน +1

      This is wild

    • @seth.photongraphy2673
      @seth.photongraphy2673 2 หลายเดือนก่อน

      data is the new money

    • @gabrielfraga2303
      @gabrielfraga2303 2 หลายเดือนก่อน

      Now you can do a "meanings" comparison with "users" accounts and learn everything about them! Good for sales with recommendations

    • @mattk6910
      @mattk6910 2 หลายเดือนก่อน +1

      Sounds expensive with unclear value tbh, but cool idea

    • @SteveMayzak
      @SteveMayzak 2 หลายเดือนก่อน

      @@infraiait’s wild if you’re a bot :-)

  • @rohitthum1059
    @rohitthum1059 2 หลายเดือนก่อน +1

    Well presented!!

  • @superbaim
    @superbaim 2 วันที่ผ่านมา

    can it do downstream task like summarization ?

  • @jamesyin3220
    @jamesyin3220 2 หลายเดือนก่อน +2

    You had me at "pagerank"

  • @chriseun0503
    @chriseun0503 หลายเดือนก่อน

    what are the applications of this technology in mapping out professional entworks / relationships? in a way, forming as a basis of a modern, relationship-based CRM?

  • @MJLeeee
    @MJLeeee 2 หลายเดือนก่อน +4

    Where would you think GraphRAG will be "really" needed since higher computation is needed compared to Normal RAGs

    • @hEmZoRz
      @hEmZoRz 2 หลายเดือนก่อน +4

      One thing that comes to mind is any kind of automated research, with a graph of papers, edges representing relations such as citations, shared authors, or topics. Computation or latency would hardly be an issue here.

    • @GoranSkular
      @GoranSkular 2 หลายเดือนก่อน

      Hm, maybe computation can be even lower to yield better results than with vector only RAGs. But the main thing, it's about quality of the 'R' content...

  • @aaen9417
    @aaen9417 หลายเดือนก่อน

    This is amazing.

  • @DJdopeMike
    @DJdopeMike หลายเดือนก่อน

    Wow! this is so cool!

  • @infraia
    @infraia 2 หลายเดือนก่อน +5

    Great company

  • @energyexecs
    @energyexecs หลายเดือนก่อน

    Aha, I like that GraphRag concept. I am augmenting my LLM now with RAG on PDF documents inside my enterprise. But the results were poor and not released for production. Seems like GraphRAG can help.

    • @Zaratch
      @Zaratch หลายเดือนก่อน

      Hi, is it possible for you to share more on this? I would like to know about your experience. lmk if its possible for you to drop your email. Thank you

  • @markvogt70
    @markvogt70 หลายเดือนก่อน

    NOTHING breeds ENTHUSIASM like... ENTHUSIASM.
    "...check this shit out!"
    It's fun when you're a PASSIONATE & SKILLED DATA SCIENTIST and you see a presentation by ANOTHER (better!) PASSIONATE & SKILLED DATA SCIENTIST !
    LOVED the video...

  • @jakubbartczuk3956
    @jakubbartczuk3956 11 วันที่ผ่านมา

    That's pretty cool but the title is a bit misleading as it doesn't touch the actual GraphRAG method (that is, a specific paper and project).

  • @twoplustwo5
    @twoplustwo5 2 หลายเดือนก่อน +1

    🎯 Key points for quick navigation:
    00:00:00 *📊 Introduction and Background*
    - Emil Eifrem introduces his dedication to helping developers build better applications by leveraging relationships between data points,
    - Overview of the lecture's focus on the combination of LLMs and knowledge graphs.
    00:00:45 *🔍 Evolution of Search Technology*
    - Discussion on the history and evolution of web search engines from AltaVista to Google,
    - Explanation of the challenges with keyword-based search and how Google's PageRank algorithm, a graph-based algorithm, revolutionized search.
    00:02:48 *📚 Introduction of Knowledge Graphs*
    - Google's shift from PageRank to Knowledge Graphs, emphasizing the difference between "things" and "strings,"
    - Description of the visual structure of Knowledge Graphs, combining structured and unstructured data.
    00:04:24 *🧠 The Advent of Gen and AI in Search*
    - Google's recent advancements in AI-powered search, integrating LLMs and Knowledge Graphs,
    - Explanation of "GraphRAG" and how it combines retrieval-based Knowledge Graphs with Gen technologies.
    00:06:01 *🤖 Implementing GraphRAG in Applications*
    - Detailed example of building a customer service bot using GraphRAG,
    - Explanation of how GraphRAG enhances typical RAG-based applications by leveraging knowledge graphs for better retrieval and context.
    00:08:20 *🌟 Benefits of GraphRAG*
    - Higher accuracy of responses in AI applications using GraphRAG compared to traditional RAG,
    - Easier development of applications once a Knowledge Graph is established, with examples from high-profile companies.
    00:10:09 *🛠 Advantages in Development and Governance*
    - Clarity and transparency in application development using graphs versus vectors,
    - Improved explainability, auditability, and governance for business IT.
    00:12:54 *🚀 Getting Started with GraphRAG*
    - Steps and considerations in creating a Knowledge Graph,
    - Demonstration of the Knowledge Graph Builder tool, showing the process of uploading and visualizing data.
    00:18:01 *🎉 Conclusion and Final Thoughts*
    - Final insights and practical example using the Knowledge Graph Builder,
    - Encouragement to try out the tool and further explore the benefits of GraphRAG in applications.
    Made with HARPA AI

  • @johannesdeboeck
    @johannesdeboeck 2 หลายเดือนก่อน +3

    How is this useful if there is still hallucination happening and the accuracy is only 70%?
    LLMs have a preference for their internal knowledge over external knowledge coming from RAG or knowledge graphs.
    Anyone has tips to solve this?

    • @hEmZoRz
      @hEmZoRz 2 หลายเดือนก่อน +3

      I mean... if "traditional RAG", if you will, has proven immensely useful in various contexts, then surely a method reporting significantly higher performance will be useful, too.

    • @johannesdeboeck
      @johannesdeboeck 2 หลายเดือนก่อน

      ​@@hEmZoRz I would think so, but I do not understand how, if you can not trust it 100% when using LLMs.
      I asked this question once to Philip Rathle (CTO @ Neo4j) and he kindly replied:
      “It comes back to what GraphRAG pattern you are using, and “Locus of Reasoning”. I’m planning a follow-up post that will cover this.”

    • @johannesdeboeck
      @johannesdeboeck 2 หลายเดือนก่อน +1

      While waiting for his post I asked ChatGPT to clarify..
      Locus of Reasoning:
      refers to the place where most of the reasoning or decision-making happens: inside the LLM (internal) or within the external knowledge source (external).
      External Locus of Reasoning:
      The LLM is designed to pull in external knowledge (like a knowledge graph) first and treat it as the primary source for generating its response, making it more likely to use the external knowledge over its own.
      Different GraphRAG patterns can influence where the “Locus of Reasoning” is placed:
      In Post-Retrieval or Iterative patterns, the LLM is more likely to be influenced by the external data.
      Post-Retrieval: The LLM first retrieves relevant information from the knowledge graph and then integrates it with its internal knowledge to generate a response. In this pattern, the external knowledge is directly presented to the LLM before it starts generating.
      Iterative: A dynamic, back-and-forth pattern where the LLM may ask for more information from the knowledge graph during the generation process. This pattern tends to have more active integration of external knowledge throughout the reasoning.

    • @hEmZoRz
      @hEmZoRz 2 หลายเดือนก่อน

      @@johannesdeboeck Admittedly, I'm not an expert in the RAG field and don't know exactly what goes into rigorous validation of these systems, but I would imagine that the benchmarks are very difficult (after all, a benchmark where current models would score >95% regularly wouldn't be particularly useful), hence the seemingly low accuracy scores. If that's the case, the accuracy in simpler tasks is likely to be significantly higher, even close to 100%.
      Now, clearly real-life tasks also come in many flavours and difficulties. I'm sure there's a whole host of applications that are simple enough in nature that RAG performs sufficiently close to 100%, where it's not mission critical to achieve absolute perfect 100% reliability on the RAG system (after all, humans aren't perfect either).
      edit: for what it's worth, I've played around with vector RAG in personal projects, involving straightforward tasks, and while I haven't performed any thorough validations, I'd guesstimate these systems perform somewhere in the territory of 90-95% accuracy.

    • @johannesdeboeck
      @johannesdeboeck 2 หลายเดือนก่อน +2

      ​@@hEmZoRz Thanks for your input.
      There is a good video that explains what the exact issue is with using external knowledge such as RAG systems or knowledge graphs. It is on the Diffbot TH-cam channel and is called "Trying to make LLMs less stubborn in RAG"
      I am not affiliated with Diffbot. It just shows very good how the LLM can be stubborn and refuse to use external knowledge.

  • @__m__e__
    @__m__e__ 2 หลายเดือนก่อน +1

    Give that man another minute!

    • @emileifrem7726
      @emileifrem7726 2 หลายเดือนก่อน +3

      Oh man, I had a few more things I did want to show in that demo. Maybe I'll try record another version of just the (full) demo!

    • @smithj
      @smithj 2 หลายเดือนก่อน

      I would really appreciate that and I assume others too!

    • @BlackkTiger
      @BlackkTiger 2 หลายเดือนก่อน

      @@emileifrem7726 If you have time, please do!

    • @RyanJohnson818
      @RyanJohnson818 2 หลายเดือนก่อน

      I would love a full version! We in the company are the "graph/ontology" people, and explaining the benefits and process of GraphRAG can be challenging

  • @jbond5834
    @jbond5834 2 หลายเดือนก่อน

    cool!

  • @mickelodiansurname9578
    @mickelodiansurname9578 2 หลายเดือนก่อน

    i certainly shall indeed be trying said QR code for a least an hour goofing off on graphs of utterly unrelated topics... why thank you...

    • @emileifrem7726
      @emileifrem7726 2 หลายเดือนก่อน

      Oh no, was the QR code wrong? Which one?

  • @adilgun2775
    @adilgun2775 2 หลายเดือนก่อน

    would easily be mess in PROD.. my experience; keep it simple and make it work

    • @emileifrem7726
      @emileifrem7726 2 หลายเดือนก่อน +4

      That's part of the rationale. Because graph space is explicit and visible, it can actually be EASIER in production. Vector space is opaque. You have no idea *why* two things are cosine-ish proximate. If you have a green apple and a tennis ball, they're probably close in vector space. But why? Is it the roundness of the things? Is it the green-ness? You have no idea. It's 0.738475 near in some euclidean space. In graph space, you know they're related because of their color, or an apple and orange are similar because they're both fruits etc. That visible and explicit nature of the graph frequently makes it easier in production, because you understand what's going on. On your higher order comment though, I *completely* agree: keep it simple, make it work, iterate from there.

  • @themax2go
    @themax2go 2 หลายเดือนก่อน +2

    graphrag is outdated, it's way too computationally expensive, there's a much more efficient solution

    • @akramarts4228
      @akramarts4228 2 หลายเดือนก่อน +13

      Can you share details of the better method?

  • @cardiderek
    @cardiderek 2 หลายเดือนก่อน

    GraphRag isn't a fitting name.

  • @GarryGolden
    @GarryGolden 2 หลายเดือนก่อน +1

    ALways enjoy Emil's framings. Graph is still real deal. Soon maybe we'll talk about Experience Graphs -- KG _ xG _ AI/LLMs