Loading…

线上峰会
12月9-10日
了解更多信息注册参加

Sched 应用程式允许你建立你的日程表,但不能代替你的活动注册。你必须注册 2021年中国 KubeCon + CloudNativeCon + Open Source Summit - 线上峰会 才能参加会议。如果你还没有注册但想加入我们,请到活动注册页面购票注册。

请注意:此日程表自动显示为中国标准时间(UTC +8)。要想看到您选择的时区,请从右侧 「Filter by Date」上方的下拉菜单中选择。日程表可能会有变动。


Virtual
December 9-10
Learn More and Register to Attend

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for KubeCon + CloudNativeCon + Open Source Summit China 2021 - Virtual to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

Please note: This schedule is automatically displayed in China Standard Time (UTC +8). To see the schedule in your preferred timezone, please select from the drop-down menu to the right, above "Filter by Date." The schedule is subject to change.
Back To Schedule
Thursday, December 9 • 13:15 - 13:50
Milvus 2.0:一个云原生向量数据库 | Milvus 2.0: A Vector Database With Cloud-Native Architecture - Xiaomeng Yi, Zilliz

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
矢量数据,即嵌入数据,是各种人工智能应用程序中常见的关键数据类型。矢量数据库出现的原因在于人工智能驱动的应用程序对非结构化数据分析的需求不断增长。Milvus 是一个开源的矢量数据库,也是一个 LF 人工智能和数据修匀项目,自其开源以来已获得了巨大的发展势头。在不到两年的时间里,Milvus 已在全世界获得了 1000 多个企业用户。在开发 Milvus 1.0 之后,我们总结了在服务于各种人工智能应用程序方面获得的经验教训。因此,我们设计了一个新的架构,并将其应用到 Milvus 2.0 中。该新架构实现了读写和计算存储的解耦,具有灵活、易于扩展和云原生的设计。在本演讲中,我们将展示指导开发 Milvus 2.0 的主要设计考虑因素。然后我们会介绍 Milvus 2.0 的系统架构和主要组成部分。最后,我们会讨论我们遇到的挑战。

Vector data, i.e., embedding data, is a common and critical data type in various AI applications. Vector databases were emerging due to the ever-growing demand for unstructured data analytics in AI-powered applications. Milvus, an open-source vector database and an LF AI & DATA graduation project, has gained huge momentum ever since its open-source. It has gained more than 1000 enterprise users worldwide in less than two years. After developing Milvus 1.0, we summarized the experiences and lessons learned from serving various AI applications. Accordingly, we designed a new architecture and applied it to Milvus 2.0. The new architecture achieves read-write and compute-storage decoupling with a flexible, easy-to-scale, and cloud-native design. In this talk, we will show the principal design considerations that guide the development of Milvus 2.0. Then we will introduce its system architecture and major components. Lastly, we will discuss the challenges we encountered.

Speakers
avatar for Xiaomeng Yi

Xiaomeng Yi

Senior Researcher, Zilliz
Xiaomeng Yi, senior researcher and research team leader of Zilliz. He received his Ph.D. degree in computer architecture from Huazhong University of Science and Technology. His research interests include management of high-dimension data, large-scale information retrieval, and resource... Read More →



Thursday December 9, 2021 13:15 - 13:50 CST
Open Source Summit 演讲厅