利用 Kubernetes 部署 Milvus 分布式集群

Milvus 作为一款针对海量特征向量的相似度搜索引擎,在单台服务器上就可以处理十亿级数据规模。而对于百亿或者千亿级数据,则需要具有水平扩展能力的 Milvus 集群来满足对海量向量数据的高性能检索需求。

我们使用了 Mishards 中间件来搭建 Milvus 集群。Mishards 是一个用 Python 开发的 Milvus 集群分片中间件,其内部处理请求转发、读写分离和水平扩展,为用户提供内存和算力可以扩容的 Milvus 实例。详情请参阅 Mishards。 https://milvus.io/cn/docs/v0.10.0/mishards.md

看完本次直播你将能了解如何利用 Helm & kubectl 两种方式部署 Milvus,也欢迎配合文档学习:

🚀 https://github.com/milvus-io/milvus-helm

🚀 https://github.com/milvus-io/bootcamp/tree/0.10.0/solutions/Kubernetes

展开查看详情

1. Milvus 利用 Kubernetes 搭建 Milvus 分布式集群 Mia Li

2.Unlock the treasure of unstructured data AI algorithms transform image, video, voice, natural language into vectors, and enables understanding and utilization of unstructured data at scale. Unstructured data Deep learning models Vectors Knowledge, insight, $ © 2020 Zilliz. All rights reserved.

3.Philosophy of vector search engine Ballast of an unstructured database. Unstructured Data image, video, voice, natural language store input Information Extraction Object output Result AI Models Storage Milvus Search Index query insert Knowledge Base Feature Vectors © 2020 Zilliz. All rights reserved.

4.Milvus: The journey 2018.10 2019.04 2019.06 The most active AI projects 1st The Milvus in Linux foundation seed idea 0.1 user Open Joined Source LF AI 2019.10 2020.03 © 2020 Zilliz. All rights reserved.

5.Progress Unstoppable momentum since its debut. 5.8K 3.9K 117 Commits GitHub stars Contributors 25K 300+ 19 DockerHub downloads Users Patents filed © 2020 Zilliz. All rights reserved.

6.Users 300+ community users in initial 6 months, and rapid growing. © 2020 Zilliz. All rights reserved.

7.Useful Links Live demo https://milvus.io/scenarios https://milvus.io https://github.com/milvus-io/milvus • Content-based image retrieval system (以图搜图) • Q&A chatbot powered by NLP (智能客服机器人) https://milvusio.slack.com • Molecular analysis (化合物分析) https://twitter.com/milvusio https://www.facebook.com/io.milvus.5 https://zhuanlan.zhihu.com/ai-search https://medium.com/@milvusio Follow our WeChat account © 2020 Zilliz. All rights reserved.

8.欢迎加入 Milvus 技术交流群 © 2020 Zilliz. All rights reserved.

9.Speaker Intro Data Engineer at Zilliz - Data preprocessing - AI model application - Docker deployment Mia Li © 2020 Zilliz. All rights reserved.

10.Logistics - Mishards intro - Live coding: Deploy Milvus with Helm & kubectl - Q&A session © 2020 Zilliz. All rights reserved.

11.Mishards Mishards handles request forwarding, read-write separation, horizontal and dynamic scaling, providing you with additional capabilities in terms of expanded memory and computing power. https://milvus.io/cn/docs/v0.10.2/mishards.md © 2020 Zilliz. All rights reserved.

12.Mishards-based cluster solution • Mishards node: A stateless and scalable node. • Milvus write node: An unscalable node. • Milvus read node: A stateful and scalable node. • Shared storage service: Milvus read and write nodes share data through the shared storage service. • Metadata service: MySQL © 2020 Zilliz. All rights reserved.

13.Deploy Milvus cluster • Build from Source code • Docker • Kubernetes https://github.com/milvus-io/milvus/blob/0.10.1/shards/README_CN.md © 2020 Zilliz. All rights reserved.

14.Deploy Milvus cluster with Kubernetes Preparation •Kubernetes 1.10+ •Helm >= 2.12.0 •Shared storage Set Deploy Milvus Test StorageClass Cluster https://github.com/milvus-io/bootcamp/tree/0.10.0/solutions/Kubernetes © 2020 Zilliz. All rights reserved.

15.Application Smarter Housing Search and Recommendation Powered by Milvus Music Recommendation System Powered by Milvus(I2I) © 2020 Zilliz. All rights reserved.

16.欢迎加入 Milvus 技术交流群 © 2020 Zilliz. All rights reserved.