NODES 2023 - Using LLMs to Convert Unstructured Data to Knowledge Graphs

Discover how Large Language Models (LLMs) can unlock insights within text, social media, and web content. In this session, Noah will demonstrate how LLMs can be used for entity extraction, semantic relationship recognition, and context inference to generate interconnected knowledge graphs. This session will hopefully inspire you to harness LLMs for your uses of unstructured data.

[joshuacunningham]

Thank you very much for this helpful and inspiring presentation!

[capri]

Nice talk. Concise and providing the just the right amount of information. massive thank you for using animations in your slides it helped tremendously with your flow. Trying the github repo as we speak.

[ahmed_hefnawy]

chunking is one of the most steps to build a stable RAG flow, KG will change the RAG Game

[tacticalforesightconsultin]

I've done and presented a project like this with more transparency over 5 years ago, and completed it within a few weeks time. The only concern there was, was with polysemy (word with multiple parts-of-speech).
It really helped to condense the information down and easily see implications across the documents.

[kennethnielsen]

Surprised you didn't use the Matrix movies instead :D

[SaptarshiBasu]

Does anyone develop application for production in this way? What about ontology?

[fensmup]

Quick question let say we are working with maybe 100s of files to create graph, would'nt it be too costly to use llm?

[blvmnvg]

can you provide information regarding seed from URI for azure storage seed provider