Frank Liu on recent updates to Milvus, and why vector databases are hot.
Subscribe: Apple • Spotify • Stitcher • Google • AntennaPod • Podcast Addict • Amazon • RSS.
Frank Liu is Director of Operations & ML Architect at Zilliz, the company behind Milvus, an open source vector database. We discuss their recent VLDB paper (“A Cloud Native Vector Database Management System”) that describes recent updates to Milvus, as well as vector databases and vector search in general.
Highlights in the video version:
- How is Milvus being used?
Querying and interacting with vector databases
Tunable performance-consistency trade-off
Largest known Milvus cluster
ANN models in Milvus
Data catalogs in the context of vector databases
Will improvements in other data management systems reduce the need for vector databases?
Features and embeddings: difference between feature stores and vector databases
Use cases beyond search
Milvus roadmap
Related content:
- A video version of this conversation is available on our YouTube channel.
- The Vector Database Index
- Bob van Luijt of Weaviate: An open source, production grade vector search engine
- Ram Sriharsha of Pinecone: A new storage engine for vectors
- Summer of Orchestration: conversations with co-creators of Prefect, Dagster, Flyte, and Orchest.
- New open source tools to unlock speech and audio data
- fastdup: Introducing a new free tool for curating image datasets at scale
- A Guide to Data Annotation and Synthetic Data Generation Tools
If you enjoyed this episode, please support our work by encouraging your friends and colleagues to subscribe to our newsletter:
[Image: Embeddings from Zilliz, used with permission.]