Cloud-native service for Milvus
Zilliz simplifies the process of deploying and scaling vector search applications by eliminating the need to create and maintain complex data infrastructure.
- Get $100 with your 30-day trial
Powerful, flexible support for embeddings generated by multiple Machine Learning algorithms- Lightning-fast queries on any size data set
- Cost-effective storage of vectors
- Zero ops overhead with serverless architecture
Why Zilliz Cloud?
Built on Milvus and optimized for performance
Zilliz Cloud is built on the popular open-source vector database, Milvus. The same creators of Milvus have used their experience with over a thousand enterprise Milvus users across various industries to create state-of-the-art vector database services.
Elastic and Scalable
Cost-effectively scale with serverless clusters that instantly provision and scale to match your budget and needs. Scale your compute and storage resources as far as you need to support vector search to tens of billions of vectors.
Pay-as-you-go
Scale up or down when needed and pay only for what you use to lower the cost of storing your embeddings with the most budget-friendly vector database. New sign-ups receive $100 to spend during their first 30 days. Access scaled discounts for high-volume workloads with committed usage.
Multi-Cloud (AWS, GCP)
Zilliz Cloud offers consistent management, security, and governance experience across all clouds. You don’t need to invest in reinventing processes for every cloud platform you use to support your data and AI efforts. Instead, your teams can focus on putting all your data to work to build new similarity search capabilities.
Cloud Native Resiliency
Zilliz Cloud is always on the latest version, secure with the latest patches, and supported by a world-class operations team. Build on the Milvus strength with reliability & resiliency built-in, 99.9% uptime SLA, and zero data corruption.
Enterprise Security & Governance
Zilliz Cloud provides full data encryption in transit, complies with the SOC 2 standards, and will support Role-Based Access Control (RBAC) soon.
Key features
Vector database features
Where can vector databases help?
LLM Augmentation
Expand LLMs' knowledge by incorporating external data sources into LLMs and your AI applications.
Recommender System
Recommend information or products to users based on their past behaviors and preferences.
Text/Semantic Search
Search for semantically similar texts across vast amounts of natural language documents.
Image Similarity Search
Search for visually similar images from a vast collection of image libraries.
Audio Similarity Search
Find similar audio results from massive amounts of audio data such as music, sound effects, and speeches.
Video Similarity Search
Search for similar videos from extensive collections of video libraries.
Question Answering System
Interactive QA chatbot that automatically answers user questions.
Molecular Similarity Search
Search for similar substructures, superstructures, and other structures for a specified molecule.
Multimodal Similarity Search
Query across different modalities such as texts, videos, audio, and images.
Zilliz Cloud is available across cloud service providers.
- AWS Web Service
- Google Cloud
Frequently asked questions
A CU is a group of hardware resources for serving your indexes and search requests. You can simply consider a CU as a fully-managed physical node for deploying search service.
The "Performance-optimized CU" suits low latency or high throughput similarity searches. This option works best for high-search performance scenarios.
The "Capacity-optimized CU" suits data volumes that are five times larger than the performance-optimized CU option but at the cost of higher search latency. This option works best for increased storage capacity scenarios.
The "Cost-optimized CU" provides the same large capacity as the "Capacity-optimized" option, but at a lower cost with reduced search performance. This option is ideal for budget-conscious projects that need ample storage without high-performance demands.
A Performance-optimized CU can serve 5 million 128-dimensional vectors or 1 million 768-dimensional vectors.
A Capacity-optimized CU can serve 25 million 128-dimensional vectors or 5 million 768-dimensional vectors.
A Cost-optimized CU can serve 25 million 128-dimensional vectors or 5 million 768-dimensional vectors.
No. Currently, Zilliz Cloud only supports deploying a serverless cluster on GCP. If you need to deploy a cluster on AWS, choose the Standard or Enterprise plan to deploy a dedicated cluster on AWS.
Please submit a request at https://support.zilliz.com/hc/en-us.
In short, cloud service prices often vary between providers and regions. Several factors contribute to these differences, such as the costs of the underlying physical resources that cloud database services rely on.
To request a new cloud service provider region for Zilliz Cloud, please submit a Cloud Region Request.