Reliable Graph RAG with Neo4j and Diffbot

Поділитися
Вставка
  • Опубліковано 17 лис 2024

КОМЕНТАРІ • 38

  • @johnkintree763
    @johnkintree763 4 місяці тому +3

    Excellent presentation. Neo4j has done a great job of integrating vector embeddings with knowledge graphs. The neo4j LLM Knowledge Graph Builder for extracting entities and relationships from video transcripts, Wikipedia articles, and pdf format files is impressive. It also merges the extracted knowledge into a graph structure, and then provides an interface to query the LLM about knowledge in the graph.

    • @diffbotai
      @diffbotai  4 місяці тому

      The neo4j graph builder (llm-graph-builder.neo4jlabs.com/) is indeed awesome! try selecting the "Diffbot" option in the generate graph dropdown

  • @kakashisensie100
    @kakashisensie100 4 місяці тому +21

    Amazing video really. and jokes are definitely necessary. 🤓

  • @csmac3144a
    @csmac3144a 3 місяці тому +1

    Very useful info -- just what I was looking for as I'm researching this stuff. Also your delivery is great! Entertaining, yet you explain things very clearly. Subscribed.

  • @Psynapses
    @Psynapses 3 місяці тому

    This is super cool! Thanks for sharing the detailed breakdown, super helpful. WIshing DiffBot the best as well

  • @ronifintech9434
    @ronifintech9434 4 місяці тому +2

    Thanks for the knowledge (graph) sharing :)

  • @BillVoisine
    @BillVoisine 4 місяці тому

    Thank you! This is exactly what I needed!

  • @johannesdeboeck
    @johannesdeboeck 4 місяці тому +1

    Awesome indeed 😍Thank you!

  • @grantdh
    @grantdh 4 місяці тому

    You rock, this was great!

  • @trinityblood5622
    @trinityblood5622 4 місяці тому +2

    Hi it would be great if you could please make longer videos explaining how you did each of these transition for example entity extraction, relationship extraction and so on and then how you did the neo4j integration. Maybe you can make a short video like this out of the original video to attract customers while the long video would still serve as a promising directions for the developer/researcher. I love the output produced from your system, but there’s no way to reproduce what you are doing. Reproducibility is a major concern in KGC.

    • @diffbotai
      @diffbotai  4 місяці тому

      Thanks for the feedback on producing deep dives into those topics. it's too much to cover in an applied video like this, but could be a good topic for a future video. In terms of reproducibility, you should be able to reproduce any of the examples in the video using the linked github project repo in the description.

  • @mshonle
    @mshonle 4 місяці тому +1

    Once the entities are extracted, can the model then be prompted to write a graph query (that could then be executed)? I’m thinking in particular of the “knowing A is B but not B is A” problem, such as when you ask an LLM “who is Mary Pfeiffer’s son?” and it does not say “Tom Cruise” but can answer “who is Tom Cruise’s mother?” just fine?

    • @diffbotai
      @diffbotai  4 місяці тому +1

      Yes! There are many people working on text-to-graph query language and that is a great motivating example for how to overcome language modeling bias

  • @MattJonesYT
    @MattJonesYT 4 місяці тому

    More like this please!

  • @alv9551
    @alv9551 4 місяці тому

    omg I was trying to hold it together at the introduction when I saw the large soup bowl but I broke down when it said "whatever, y'all get replaced by AI in 5 yrs" 😂 Great video overall. I hope I am right about the size of the soup bowl and you are not 3 feet tall.😅

  • @lesptitsoiseaux
    @lesptitsoiseaux 4 місяці тому

    LeanChen, if you had to rate the similiarity of groups of words, how would you do it? A bit like are these two classes similar?

  • @alchemication
    @alchemication 4 місяці тому

    Hey. Thx for the awesome content. Would it be possible to actually show a fully working large scale graph (like proper prod scale thing), and also discuss pros and cons of the approach, and when did you find KGs working well and not so well? The reason I asked is that my own KG experiments worked perfectly for me at smaller scale, but then the speed was so slow, that it was killing my M2 mac all together.

    • @diffbotai
      @diffbotai  4 місяці тому

      Great idea for a future video. For trying out a production version of a 10B node graph built from the entire public web, try out Diffbot!

  • @StephenRayner
    @StephenRayner 2 місяці тому

    I appreciate the meme cup 🎉😂

  • @chillbeach7322
    @chillbeach7322 4 місяці тому

    How does this compare to Graph RAG by Microsoft? What are their differences and similarities?

  • @viky2002
    @viky2002 4 місяці тому

    how does this compare to llamaindex property graph ?

  • @ignaciopincheira23
    @ignaciopincheira23 4 місяці тому

    Hi, could you convert complex PDF documents (with graphics and tables) into an easily readable text format, such as Markdown? The input file would be a PDF and the output file would be a text file (.txt).

    • @joshuajose8598
      @joshuajose8598 4 місяці тому +1

      Maybe the pages have to be turned into images using Poppler and you could use an LLM that allows image inputs like GPT4Vision and Claude3 along with Function Calling to get the entities, objects and relations.

  • @themax2go
    @themax2go Місяць тому

    would it work w/ ollama / local models?

  • @V0v1kkk
    @V0v1kkk 4 місяці тому

    DiffBot - sound not so good for privacy.
    That is the role of the DiffBot? Entities extraction?
    Are there any selfhosted replacements?

    • @diffbotai
      @diffbotai  4 місяці тому

      Unlike OpenAI, Diffbot does not train on your API inputs. Also, we offer on-premises solutions for enterprise customers that are self-hosted. Diffbot's services analyzes text and extracts entities and their relationships (aka a knowledge graph).

  • @tomazbratanic5502
    @tomazbratanic5502 4 місяці тому

    Awesome!

  • @Damon_Sieputovsky
    @Damon_Sieputovsky 4 місяці тому

    fugazi KG- this is only simple LPG (Label Property Graph)

  • @PrincessKushana
    @PrincessKushana 4 місяці тому

    Graphrag is so hot right now.

  • @cagdasucar3932
    @cagdasucar3932 4 місяці тому

    Why is the presenter speaking like a robot?

    • @diffbotai
      @diffbotai  4 місяці тому +1

      Bc she probably is AI-generated

  • @darkmatter9583
    @darkmatter9583 4 місяці тому

    be my teacher,and advisor please connect

  • @chloetete
    @chloetete 3 місяці тому

    She speaks in a very slurred way, I can barely understand her without turning subtitles on.

    • @StephenRayner
      @StephenRayner 2 місяці тому

      I can hear her fine. No issues.

    • @Dom-zy1qy
      @Dom-zy1qy Місяць тому

      She speaks completely fine.

  • @jackbauer322
    @jackbauer322 4 місяці тому +1

    too much information on the screen at once ... really painful to follow ... be more sober and straight to the point. Jokes are not necessary

    • @diffbotai
      @diffbotai  4 місяці тому +1

      Thanks for the feedback!

    • @3stdv93
      @3stdv93 4 місяці тому +1

      Why so serious? 😅