E56 | RAGging on Graphs with Philip Rathle | Pondering AI
Philip Rathle traverses from knowledge graphs to LLMs and illustrates how loading the dice with GraphRAG enhances deterministic reasoning, explainability and agency.
Philip explains why knowledge graphs are a natural fit for capturing data about real-world systems. Starting with Kevin Bacon, he identifies many “graphy” problems confronting us today. Philip then describes how interconnected systems benefit from the dynamism and data network effects afforded by knowledge graphs.
Next, Philip provides a primer on how Retrieval Augmented Generation (RAG) loads the dice for large language models (LLMs). He also differentiates between vector- and graph-based RAG. Along the way, we discuss the nature and locus of reasoning (or lack thereof) in LLM systems. Philip articulates the benefits of GraphRAG including deterministic reasoning, fine-grained access control and explainability. He also ruminates on graphs as a bridge to human agency as graphs can be reasoned on by both humans and machines. Lastly, Philip shares what is happening now and next in GraphRAG applications and beyond.
Philip Rathle is the Chief Technology Officer at Neo4j. Philip was a key contributor to the development of the GQL standard (https://www.gqlstandards.org/) and recently authored The GraphRAG Manifesto: Adding Knowledge to GenAI (https://neo4j.com/blog/graphrag-manif...) a go-to resource for all things GraphRAG.
View the transcript of this episode here: https://pondering-ai.transistor.fm/ep...
Listen to all episodes by visiting: https://pondering-ai.transistor.fm/
Episode highlights
00:00 – Welcome
05:22 – Real-World Data and Knowledge Graphs
16:35 – Retrieval Augmented Generation (RAG)
21:21 – GraphRAG as the Locus of Reasoning
30:15 – GraphRAG Applications/Patterns
37:37 – Non-RAG Graph Applications
45:24 – Graph Resources and What’s Next
More about Philip Rathle
◉ Philip Rathle – / prathle
◉ Neo4j – https://www.neo4j.com
◉ GQL Standard – https://www.gqlstandards.org/
◉ The GraphRAG Manifesto – https://neo4j.com/blog/graphrag-manif...
Additional resources
◉ SAS Responsible Innovation – https://www.sas.com/responsible-innov...
◉ SAS AI Solutions – https://www.sas.com/ai
◉ SAS Viya – Data and AI Platform – https://www.sas.com/viya
Disclaimer: All presentations represent the opinions of the presenter and do not represent the position or the opinion of SAS.
SUBSCRIBE TO THE SAS SOFTWARE YOUTUBE CHANNEL
https://www.youtube.com/SASSoftware?s...
ABOUT SAS
SAS is a trusted analytics powerhouse for organizations seeking immediate value from their data. A deep bench of analytics solutions and broad industry knowledge keep our customers coming back and feeling confident. With SAS®, you can discover insights from your data and make sense of it all. Identify what’s working and fix what isn’t. Make more intelligent decisions. And drive relevant change. #SASSoftware #PonderingAI
CONNECT WITH SAS
SAS ► https://www.sas.com
SAS Customer Support ► https://support.sas.com
SAS Communities ► https://communities.sas.com
SAS Analytics Explorers ► https://explorers.sas.com
Facebook ► / sassoftware
X ► / sassoftware
LinkedIn ► / sas
Blogs ► https://blogs.sas.com
RSS ► https://www.sas.com/rss
Смотрите видео E56 | RAGging on Graphs with Philip Rathle | Pondering AI онлайн без регистрации, длительностью часов минут секунд в хорошем качестве. Это видео добавил пользователь SAS Software 28 Август 2024, не забудьте поделиться им ссылкой с друзьями и знакомыми, на нашем сайте его посмотрели 18 раз и оно понравилось людям.