LlamaIndex Webinar: Advanced RAG with Knowledge Graphs (with Tomaz from Neo4j)

Поделиться
HTML-код
  • Опубликовано: 28 янв 2025

Комментарии • 25

  • @ramanshrivastava5916
    @ramanshrivastava5916 6 месяцев назад +17

    feels like he never slept and started giving this presentation

    • @myrzikslife156
      @myrzikslife156 6 месяцев назад +2

      maybe totally different time zone

  • @jackrorystaunton4557
    @jackrorystaunton4557 Месяц назад

    Tomaz, thank you for sharing!

  • @FlannelCamel
    @FlannelCamel 7 месяцев назад +4

    Fantastic webinar, very useful.
    On a long and only very slightly related tangent, protip:
    Before (and during!) long presentations drink tea with honey and a lemon slice. When we're nervous our throat tenses up and it's very easy to start coughing when talking constanly. The hot tea with honey helps with that, and the acidity from the lemon prevents your mouth from drying out. I used to have a terrible time doing these 50-minute presentations + Q&A. My throat would be shot even though I wasn't yelling or anything. Eventually I took a couple of vocal training lessons and it practically solved the issue in a week.

  • @курв-ь4ь
    @курв-ь4ь 7 месяцев назад +4

    This call was great, we used the LlamaIndex+Neo4j implementation as a basis for automatic knowledge graph generation in R2R

  • @nicklesseos
    @nicklesseos 7 месяцев назад +2

    Jerry was a great moderator asking killer question to Tomaz

  • @adegboyegaajenifuja1274
    @adegboyegaajenifuja1274 3 месяца назад

    Very useful workshop. Really enjoyed watching. I'd like to know if text chunking is automated as part of the KG building phase. If not, what techniques can be used around chunking particularly in instances of large bodies of text.

  • @bmm8213
    @bmm8213 7 месяцев назад +7

    How can I constrain the graph construction with .owl and RDF?

    • @0000000854
      @0000000854 7 месяцев назад +1

      This also I want to ask, if RDF/OWL necessary for LLM augmentation performance

  • @mabecina1
    @mabecina1 3 месяца назад

    Thanks for this - using this now with a small project. One question - once the index is upserted into Neo4j, how do you load it? I assume you don't have to rebuild it every time

  • @santiagomarroquin9525
    @santiagomarroquin9525 6 месяцев назад +1

    Great content, very useful. Where can we find the notebooks used here?

  • @ayeshaamjad3777
    @ayeshaamjad3777 7 месяцев назад

    While defining the schema, the node labels and relationships were defined. In addition to that, is there a way to define properties associated with each node label?

  • @TestModel-y7p
    @TestModel-y7p 7 месяцев назад +3

    where can we find the notebook used in the video? Please share!

    • @nymphofpan
      @nymphofpan 6 месяцев назад

      He actually shows the notebook he used late in the video check after 45:25

  • @killerdrama5521
    @killerdrama5521 7 месяцев назад

    Its good learning stuff. I have an grpah db which i created. It has different nodes with different lables and relationships between them with properties. Those nodes and relationships and properties and lables generated with help of LLM propmpt and loaded into neo4j. I want to built RAG on top of it. What will be feasible solution as i have very random node lables and relationships.? Suggest some reference please reference

  • @0000000854
    @0000000854 7 месяцев назад

    Hi sir ! I’m also LLM/KG enthusiasm, based on your expertise Is Ontology schema like RDF/OWL necessary when building Graph data base as RAG material for LLM output augmentation ?

  • @chloetete
    @chloetete 6 месяцев назад

    Watch the lecture with at least 1.5x speed to prevent yourself from sleeping...

  • @AdamKingson
    @AdamKingson 7 месяцев назад +10

    great content but presentation skills....needs some work and energy!

  • @sherlockho4613
    @sherlockho4613 6 месяцев назад

    the tune is reallyy dozy,however the code is easy to understand

  •  7 месяцев назад +2

    Hangover recovery?😂

  • @theuser810
    @theuser810 7 месяцев назад +4

    Not a fan of the way this was presented ... I was expecting a tutorial

  • @project-asgard
    @project-asgard 6 месяцев назад

    🥱

  • @sanjaybhatikar
    @sanjaybhatikar 4 месяца назад

    Dude, you're slurring over words making it very hard to follow along