Powering Billion Scale Vector Search at Milvus with Apache Pulsar

Learn how Milvus vector database utilizes Apache Pulsar to enable high-performance vector search capabilities at billion-scale in this 46-minute technical talk. Discover the architecture behind many modern GenAI applications, including RAG chatbots, image/video search, and recommender systems. Explore how the pub/sub design pattern effectively separates data ingestion from data serving, creating a robust and scalable system that efficiently manages substantial write throughput while maintaining high search traffic performance.