What does it take to run vector search at the scale of 20+ billion vectors? At Vector Space Day, Ol...
TL;DR · AI Summary
文章讨论了如何构建支持200亿向量搜索的基础设施，重点在于自动化Kubernetes操作和大规模检索系统的实践。
Key Takeaways
- 自动化Kubernetes操作可提升向量搜索系统的可靠性与可扩展性。
- HubSpot分享了构建200亿向量检索基础设施的经验。
- 大规模向量搜索需要兼顾生产环境的稳定性和性能。
Outline
Jump quickly between sections.
- §引言
文章介绍了在Vector Space Day上关于构建大规模向量搜索基础设施的讨论。
大规模向量搜索面临部署复杂、手动操作易出错等挑战。
- ·解决方案
通过自动化Kubernetes Operator提升系统的可靠性与可扩展性。
HubSpot分享了在生产环境中构建和管理大规模向量搜索系统的经验。
Mindmap
See how the topics connect at a glance.
查看大纲文本（无障碍 / 无 JS 友好）
- 大规模向量搜索基础设施
- 挑战
- 手动部署复杂
- 易出错
- 解决方案
- 自动化Kubernetes Operator
- 提升可靠性与可扩展性
- 实践
- HubSpot经验分享
- 生产环境应用
Highlights
Key sentences worth saving and sharing.
从手动、易出错的部署转向完全自动化的Kubernetes Operator。
构建支持200亿向量搜索的基础设施需要兼顾可靠性、可扩展性和生产操作。
HubSpot分享了在大规模检索系统中实际应用的实践经验。
Qdrant on X: "What does it take to run vector search at the scale of 20+ billion vectors? At Vector Space Day, Oleg Tereshin and Xin Liu from @HubSpot will share the story behind building the infrastructure that powers retrieval at massive scale. Building the Infra Behind 20 Billion+ Vectors https://t.co/XANTnsHx5v" / X
@qdrant_engine
What does it take to run vector search at the scale of 20+ billion vectors? At Vector Space Day, Oleg Tereshin and Xin Liu from
@
HubSpot
will share the story behind building the infrastructure that powers retrieval at massive scale. Building the Infra Behind 20 Billion+ Vectors
moved from manual, error-prone
qdrant_engine
deployments to a fully automated Kubernetes Operator designed for reliability, scalability, and production operations. If you’re managing vector infrastructure, operating Kubernetes at scale, or building retrieval systems in production, this is the kind of talk packed with practical lessons. 📍 The Midway, San Francisco 🗓️ June 11 RSVP:
luma.com/vsd-sf
3:00 PM · Jun 6, 2026
419
Views
4
1
0
10
Read 4 replies