#NODES2025 countdown
summary
A fireside chat lays out concrete pipelines for combining large models with graph databases, showing a GraphRAG pattern that attaches node-level provenance to answers, an AgenticAI controller that issues graph queries and updates, and glue code using Deeplearning.AI tooling plus a graph backend. Demos show live retrieval of facts from a knowledge graph, discuss latency and consistency tradeoffs, and explain when graph grounding measurably reduces hallucination.
AI-written summary · about
related talks
27mLies, Damn Lies, and AIs
23mConnecting the Dots With Context Graphs
51mMemory Masterclass: Make Your AI Agents Remember What They Do!
01h 26mThinking in Graphs: The Cognitive Foundations of Agentic AI
56mConnecting the Dots with Context Graphs
06mCloud-Native GraphRAG: AI’s Logical Edge
42mMaking OSS AI Real with Knowledge Graphs
53mPractical GraphRAG - Making LLMs smarter with Knowledge Graphs