Neo4j's LLM Knowledge Graph Builder - DEMO

In this demonstration of the LLM Knowledge Graph Builder, we show you how to automagically create a graph from your unstructured text and leverage it for Graph-powered Retrieval-Augmented Generation (GraphRAG).
-upload documents, UA-cam videos, and Wikipedia pages.
-configure a graph schema
-extract the lexical and knowledge graph
-visualize the extracted graph
-ask questions and see the details that were used to generate the answers
Try it live: bit.ly/4c4HKyp
Learn more: bit.ly/3KMRrp6
#Neo4j #GRAPHRAG #LLMs #GenAI

[@DeonBands]

Thank you, this has added additional hours to my life, I wrote complete python scripts to do environmental analysis. I will check if the application has api's, as I use google alerts a lot, if it could use rss feeds as a method of automated ingestion this will have exactly what I need to setup graphs / per topic or area I have interest in and have RSS feeds populate the graph etc. etc. etc.

[@tollington9414]

Excellent

[@cd92606]

Very cool. Looks promising!

[@neo4j]

Thank you!

[@drm2005]

Thanks

[@johnkintree763]

Beautiful.

[@neo4j]

Thank you!

[@koushiks2003]

Great content ! If you could add some info about underhood on high level.. it will be much helpful.. thanks ! Also if related contents are existing/separated between UA-cam and also on gcs .. how to have 1 combined knowledge graph as per your setup.. thanks

[@michaelhunger6160]

The high level description is on the docs page (in the description) and also in the architecture description in the repository.
The connection between your nodes should happen based on shared name. Check your graph visualization if you have potentially duplicates that you need to merge (manually in Explore) or via apoc.merge.nodes in Query