Ever wonder what it's REALLY like inside the world of tech startups? Join Daniel Davis and Brennan Woodruff, the COO of GoCharlie (a generative AI startup), for a brutally honest conversation about the realities of creating an AI startup versus the usual Silicon Valley tech hype.

knowledge graphs with linear algebra and how it will impact RAG and explainability with LLMs. Is matrix multiplication the most effective way to query knowledge? Is Cypher or GQL the future of query languages?

Topics:

00:00 Intros

07:03 A different way of storing knowledge with FalkorDB

11:15 GraphBLAS

13:10 Sparse Matrices and Zeroes

17:35 Connecting linear algebra to Cypher

21:32 Semantic search and HNSW

26:04 Latency and knowledge graph queries

30:20 "The lack of explainability is disturbing"

34:18 Hybrid RAG systems

37:46 The focus will be on GraphRAG

➡️ Bluesky: https://bsky.app/profile/trustgraph.bsky.social

The Co-founder and CTO of Memgraph, Marko Budiselić, joins us to talk all things knowledge graphs, evaluation metrics for AI, and whether or not AI can be considered AGI if it's not a cyber-physical system.

➡️ GitHub: https://github.com/memgraph/memgraph

➡️ Discord: https://discord.gg/memgraph

➡️ LinkedIn: https://www.linkedin.com/company/memgraph

Taking a break from data engineering and RAG, Daniel spoke with Rick Borden, an attorney from Frankfurt Kurnit Klein & Selz, on the state of AI regulations in 2024. Is it really the wild west in enterprise contracts around AI now? How do AI innovators navigate through these chaotic times? Which sci-fi book most accurately described the current state of AI? And will quantum computers make everything we just said irrelevant?

🔗 Rick's Links:

The founders of TrustGraph, Daniel Davis and Mark Adams, discuss their journeys with big data, knowledge graphs, and data engineering. Knowledge graphs are hard to learn - no matter what Mark says, and he gives everyone a crash course on them, why querying graphs is tricky, and what makes for reliable data services. The conversation ends with a discussion of what makes for "explainable AI" and the future of AI security.

Daniel Davis of TrustGraph and Kirk Marple from Graphlit discuss the 2024 state of RAG. Whether it's RAG, GraphRAG, or HybridRAG, a lot has changed since the term has become ubiquitous in AI. Where are we, where are we going, and where should be going are all answered in this discussion.