Topic
Qdrant
4 episodes
-
Memory OS — Hermes Agent Memory Operating System
Two friends debate Memory OS, a seven-layer local memory stack for Hermes Agent. Justy is excited about the promise of a finally-sane agent memory layer; Cody pokes at the stack of SQLite, Qdrant, and 16 plugins, and whether it's solving a problem that already has solutions.
-
Vector Databases Explained in 3 Levels of Difficulty MachineLearningMastery
Izzo and Boone decode vector databases from basic similarity search to production-scale indexing algorithms like HNSW and IVF, explaining how they solve the core problem of searching unstructured data at scale.
-
Agents need vector search more than RAG ever did
Why agents are driving a massive spike in vector search complexity, making purpose-built retrieval infrastructure more critical than ever. We dig into Qdrant's latest release, real production stories from companies handling millions of documents, and the three signals it's time to upgrade your vector setup.
-
How to Build Your Own Custom LLM Memory Layer from Scratch | Towards Data Science
In this episode, we explore innovative ways to enhance large language models (LLMs) with custom memory layers that improve user interactions. By enabling LLMs to remember past user interactions, we can drive personalization and efficiency in AI applications. Join us as we unpack how to build these memory systems from scratch and what this means for the future of conversational agents.