RAG with a Neo4j Knowledge Graph: How it Works and How to Set It Up

Поділитися
Вставка
  • Опубліковано 22 гру 2024

КОМЕНТАРІ •

  • @AAL3087
    @AAL3087 10 місяців тому +2

    Great whirlwind tour to present a concrete understading of RAG with knowledge graphs in Neo4j. Thanks. Looking forward to exploring this channel more to learn more about RAG/KGs/GenAIStack etc.

    • @neo4j
      @neo4j  10 місяців тому

      Thank you very much!

  • @aaen9417
    @aaen9417 Рік тому +3

    Thank you for publishing this type of content. This is absolutely amazing!

  • @deepbayes6808
    @deepbayes6808 Рік тому +11

    This was really useful., also the presentor did an amazing job. But it was too short. I wish to see a longer more tutorial like version of it too. Or to have links to relevant knowledge and tutorials.

    • @neo4j
      @neo4j  11 місяців тому +1

      Thank you very much! we have some more in-depth material on our blog. Check the links in the video description

  • @mtprovasti
    @mtprovasti Місяць тому +1

    Def. Interested seeing variations of this. Seems super easy.

  • @kenchang3456
    @kenchang3456 11 місяців тому +4

    Thanks for this robust example.

    • @neo4j
      @neo4j  11 місяців тому

      Thank you!

  • @NelsLindahl
    @NelsLindahl Рік тому +2

    Loved this video and the pace!

    • @neo4j
      @neo4j  Рік тому

      Thank you very much!

  • @leonh-kd3cm
    @leonh-kd3cm 9 місяців тому +1

    It is still not clear whether at the final stage what input do you provide to LLM to get the final question:
    - Original Question text
    - Text extracted from the KG nodes/edges
    - SO, you do not provide text associated with the best K answers resulted form initial generation of embeddings from the user prompt?
    ...and how to you compose the text extracted from the nodes? What is the technique?

  • @RajendraKadam725
    @RajendraKadam725 10 місяців тому +1

    Thanks for sharing the video @neo4j.
    By the way, both responses provided in the video were inaccurate.
    Why wasn't the correct answer generated? 🤔

    • @neo4j
      @neo4j  10 місяців тому

      sorry - can you share the timestamp where you think the answers were wrong?

  • @tecnopadre
    @tecnopadre 8 місяців тому +2

    It would be really useful to do this video adding how to convert the unstructured data to KG and the use it on a RAG.
    Step by step it's what makes people use Neo4j more. Thank you!

    • @neo4j
      @neo4j  8 місяців тому +1

      Thank you for the suggestion!

  • @roy.awderby
    @roy.awderby Рік тому +1

    Thank you for the deep explanation

    • @neo4j
      @neo4j  Рік тому

      Thank you!

  • @joshuacunningham7912
    @joshuacunningham7912 10 місяців тому +1

    Excellent video. Thank you.

    • @neo4j
      @neo4j  10 місяців тому

      Thank you!

  • @poisson12376
    @poisson12376 4 місяці тому +1

    Does the node embedding include information of node/relations? or just the text of the answer/question.

  • @jacobschuster5261
    @jacobschuster5261 Рік тому +1

    Brilliant, thank you!

    • @neo4j
      @neo4j  Рік тому

      Thanks! Glad you like it

  • @googleyoutubechannel8554
    @googleyoutubechannel8554 7 місяців тому +1

    How does this compare to what MS is doing in the GraphRAG paper, it seems like MS was really jazzed on using the LLM, GPT4, (in some way it wasn't clear) to create the relationships, the edges/weights etc, and this was the secret sauce, I assume this is different from what Neo4j is doing, but could you expand?

    • @neo4j
      @neo4j  7 місяців тому

      this was a bit before GraphRAG become a term - check out the latest episodes from GoingMeta ( neo4j.com/video/going-meta-a-series-on-graphs-semantics-and-knowledge/ ) where go into GraphRAG a bit more as well

  • @firebaugh73
    @firebaugh73 4 місяці тому +1

    Trying to run this on Linux in my home lab and it's erroring out on the genai-stack-database when I run docer compose --profile linux-gpu up.

  • @monkeyli-nl5ms
    @monkeyli-nl5ms 5 місяців тому +1

    the pull mode is not in the hub anymore... what happened?

  • @podunkman2709
    @podunkman2709 10 місяців тому +1

    Is there any loader ready to insert own data (csv or else - not pdf) instead of stackOverflow?

    • @neo4j
      @neo4j  10 місяців тому

      not as such, but the repo is available and you can modify the loader to take on other data: github.com/docker/genai-stack

  • @drm2005
    @drm2005 Місяць тому

    How many users can interact simultaneously ?

  • @allminhuman2602
    @allminhuman2602 Рік тому +1

    Great video! What would be the minimum recommended system specs for this to work?

    • @neo4j
      @neo4j  Рік тому

      Thank you! Any relatively modern laptop should work to give it a go and do a test-run.

  • @MatanItah
    @MatanItah 8 місяців тому

    About how long can we expect the StackOverflow loader to import using the settings in the video to run?

  • @henkhbit5748
    @henkhbit5748 Рік тому

    Great video, I have Windows and ollama is not for windows yet. Can I run the docker under wsl2?

    • @nbbhaskar3294
      @nbbhaskar3294 9 місяців тому

      I have wsl2 docker setup in my windows and I am able to run ollama successfully.

  • @podunkman2709
    @podunkman2709 Рік тому

    This is only demo of some commercial product?
    Can I use it within company to build some service?

    • @neo4j
      @neo4j  Рік тому

      the stack is based on open-source components which you can use to build your own product/servcice

  • @alimahmans9681
    @alimahmans9681 Рік тому +1

    Thank you so much

    • @neo4j
      @neo4j  Рік тому +1

      Glad it is helpful!

  • @Aristocle
    @Aristocle 8 місяців тому

    How can I load PDF, markdown, into Neo4j?

    • @neo4j
      @neo4j  8 місяців тому +1

      not directly, see this community post for a few pointers: community.neo4j.com/t/loading-pdf-or-doc-content-into-neo4j/8967
      this doesnt cover AI assisted tools which you can use these days for similar results

  • @armelhyacinthe6173
    @armelhyacinthe6173 Рік тому +1

    Thank you ❤

    • @neo4j
      @neo4j  Рік тому

      You're welcome! Glad it is helpful

  • @davidecacozza392
    @davidecacozza392 9 місяців тому

    Hi! It is possible to use an own neo4j graph?

    • @neo4j
      @neo4j  9 місяців тому

      yeah, totally - check out our recent Going Meta Episodes ( neo4j.com/video/going-meta-a-series-on-graphs-semantics-and-knowledge/ ) or our Courses on GraphAcademy ( graphacademy.neo4j.com/ )

    • @samreenkhan4994
      @samreenkhan4994 8 місяців тому

      did u try? if yes, then how

  • @D1zZit
    @D1zZit 11 місяців тому

    Amazing! Planning on integrating this with my neo4j db which has 1 billion relationships, might be pushing the limits a bit 🤣🤣

    • @neo4j
      @neo4j  11 місяців тому

      let us know how it goes :)

    • @samreenkhan4994
      @samreenkhan4994 8 місяців тому

      did it work ?

    • @D1zZit
      @D1zZit 8 місяців тому

      @@samreenkhan4994 Querying and using RAG on the database itself worked. Generating embeddings with FAST-RP did not despite the powerful specs of hardware. Instead had to generate embeddings on a condensed data form with many missing properties. Still working it out.

  • @Sri_Harsha_Electronics_Guthik
    @Sri_Harsha_Electronics_Guthik 6 місяців тому

    what is up with the page...? looks weird!

    • @neo4j
      @neo4j  6 місяців тому

      which one?

    • @Sri_Harsha_Electronics_Guthik
      @Sri_Harsha_Electronics_Guthik 6 місяців тому

      @@neo4j sry... That was a UA-cam issue. They have been rolling out new layout for UA-cam desktop and it is disgusting. I thought it was you guys having a specific layout for your videos.
      I have new question... Can we not use docker? And still use neo4j

  • @christopherhartline1863
    @christopherhartline1863 9 днів тому

    Like the guy below @mtprovasti I'd love to see variations. Maybe a ... part two with additional technical detail w/ an eye towards permanence (i.e., development and deployment)