Skip to content
Graph Chat: Multimodal GraphRAG and Agentic Observability with David Hughes episode artwork

Feb 5, 2026 9 min

Graph Chat: Multimodal GraphRAG and Agentic Observability with David Hughes

from GraphGeeks Podcast Hosted by Amy Hodler

Bryce Merkl Sasaki of G.V() sits down with David Hughes, Solutions Architect for Graph and AI at Enterprise Knowledge, during the Open Data Science Conference (ODSC) in San Francisco. The conversation dives into the cutting edge of connected data, moving beyond the initial hype of Retrieval-Augmented Generation (RAG) to explore how graphs are essential for the next generation of AI. Key Points: Multimodal GraphRAG: David explains the shift from simple associative search to a more robust approach that captures signals from images and audio by integrating knowledge management into the graph. Agentic Solutions & Observability: A look into the need for engineering rigor in AI agents, focusing on computation graphs, memory inspection, and moving toward deterministic returns using tools like BAML and DSPy. The Future of Graph Tech: David discusses the "uncomfortable but exciting" migration from native graph databases to graph-based modeling and querying within vector databases (like LanceDB).

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

Graph Chat: Multimodal GraphRAG and Agentic Observability with David Hughes

0:00 9:24

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of GraphGeeks Podcast?

This episode is 9 minutes long.

When was this GraphGeeks Podcast episode published?

This episode was published on February 5, 2026.

Can I download this GraphGeeks Podcast episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.