Season 2 · Episode 846
Beyond the Vector: Building Long-Standing AI Memory
Stop relying on basic vector search. Discover how Graph RAG and RAPTOR are creating AI systems with true long-standing memory.
My Weird Prompts · Daniel Rosehill
February 25, 202630m 49s
Audio is streamed directly from the publisher (dts.podtrac.com) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
Most AI systems today find information by "shouting into a library" and hoping the right book falls off the shelf, but the industry is rapidly moving toward a more elegant, structured approach to information management. This episode explores the shift from reactive, brute-force vector searches to proactive retrieval architectures like Graph RAG, Hierarchical RAG, and RAPTOR. By moving beyond simple embeddings and embracing knowledge graphs and recursive clustering, developers can build AI systems that possess a truly "holistic" understanding of their data. Learn how these sophisticated methods solve the precision bottleneck and allow for multi-hop reasoning that mimics the associative nature of human memory.