Milvus: Scaling Vector Data Solutions with Gen AI
summary
Milvus is an open source, cloud‑native vector database that runs stateless on Kubernetes using built on MinIO and Kafka for storage and change capture, offers Milvus Lite/Standalone/Distributed and claims horizontal scale up to 100 billion vectors, shards data into segments with hot/cold placement, supports HNSW in‑memory, DISKANN on disk and GPU indexes, adds metadata filtering to cut search space, and demonstrates a live 35 million vector demo using Cohere embeddings plus Ollama Llama 3.1 with observed P99 ~5 ms for batch searches.
AI-written summary · about
chapters (11)
- 0:00Milvus and vector databases
- 2:28Vector databases in GenAI
- 4:54Traditional databases vs vector search
- 7:24Generating vectors from data
- 9:11Vector search in practice
- 10:13Scaling Milvus on Kubernetes
- 14:53Index strategies for search
- 18:20Filtering and search reduction
- 19:44Retrieval Augmented Generation with Milvus
- 22:54Live demo: 35M vectors
- 33:27Q&A
related talks
37mMilvus: Scaling Vector Data Solutions with Gen AI
36mMilvus: Scaling Vector Data Solutions with Gen AI
30mMilvus Vector Database: Unlocking the Future of Open Source Vector Databases
35mMilvus 2.0: Building the World's Most Advanced Open-source Vector Database
29mThe Evolution of Milvus: A Cloud-Native Vector Database
51mUnleashing the Potential of Cloud-Native Vector Databases
31mMilvus 2.0: A Vector Database With Cloud-Native Architecture
26mThe Rise of Vector Databases - Lessons from the Milvus Community