SAN FRANCISCO, Sept. 10, 2024 (GLOBE NEWSWIRE) -- Zilliz, the company behind the open-source vector database Milvus, today announced a major upgrade to Zilliz Cloud, designed to tackle the challenges developers face in scaling generative AI applications from prototype to production. The new release introduces practical tools and performance improvements built to support large-scale AI workloads.
"As Generative AI moves from experimentation to critical deployments, organizations need scalable and reliable vector database solutions," said Charles Xie, CEO at Zilliz. "This release brings features that streamline unstructured data management and boost performance, allowing developers to focus on building, not managing infrastructure."
Zilliz Cloud already sets itself apart with its advanced Cardinal Search Engine, which leverages AI to optimize search strategies. This unique feature includes:
- AI-Powered AutoIndex: Automatically selects optimal search strategies for each dataset, eliminating the need for manual tuning.
- Smart Query Optimizer: Utilizes AI-based algorithm selection to choose the best search approach for optimal performance and accuracy.
- Comprehensive Optimization Suite: Implements optimizations across algorithms, systems, and hardware to enhance speed, accuracy, and efficiency.
- Next-Generation AutoIndex: Combines IVF and graph techniques to deliver unmatched search performance and accuracy for both standard and custom workloads.
Key updates include:
Vector Migration Service: Zilliz Cloud introduces the first vector migration solution in the industry, designed to give developers freedom from vendor lock-in. This service enables efficient transfer of vector data between Milvus 2.x, PGVector, Elasticsearch, and Zilliz Cloud. By offering the freedom to choose or change vector database providers, it addresses a significant challenge in AI infrastructure and promotes data portability.
Data Integration with Fivetran: A new partnership with Fivetran connects Zilliz Cloud to over 500 data sources, streamlining the process of vectorizing, indexing, and querying unstructured data for AI applications.
Performance and Scalability Enhancements: Multi-replica support (public preview) boosts throughput and fault tolerance, while auto-scaling (private preview) adjusts resources based on demand. These features help developers reduce operational overhead while handling growing AI workloads.
Comprehensive Observability: Over 18 core metrics and 39 automated alerts allow developers to monitor system performance in real-time, ensuring smooth operations at scale.
Enterprise-Grade Security: Auth0-based Single Sign-On (private preview) improves access control and simplifies user management, addressing security requirements for enterprise applications.
99.95% Uptime SLA: Zilliz Cloud now guarantees 99.95% uptime, offering developers the reliability needed for production environments.
Zilliz Cloud Expands Global Footprint and Enhances Performance: Zilliz Cloud has significantly expanded its global footprint with the addition of the Tokyo AWS region, bringing its worldwide coverage to 12 regions. This expansion offers developers unprecedented flexibility in data locality and substantially reduces latency for global deployments. Furthermore, Zilliz Cloud now leverages AWS Graviton3-based R7g instances, delivering enhanced performance and cost-effectiveness for vector similarity searches.
These updates underscore Zilliz Cloud's commitment to providing developers with a state-of-the-art, globally accessible vector database solution. By addressing key challenges in data migration, integration, performance, security, and global accessibility, Zilliz Cloud is positioned to accelerate AI development and deployment across industries.
"As the creators of Milvus, we understand the technical challenges developers face when deploying vector databases at scale," added Xie. "These new features give developers the tools they need to build and manage GenAI applications, while keeping control over their unstructured data."
The latest release of Zilliz Cloud is available now. For more information, visit the Zilliz blog.
About Zilliz
Zilliz is a leading vector database company, founded by the engineers who created Milvus, the world's most widely-adopted open source vector database. Zilliz's next-generation database technologies help organizations rapidly create AI/ML applications and unlock the potential of unstructured data. By simplifying complex data infrastructure management, Zilliz is committed to bringing the power of AI to every corporation, organization, and individual.
Headquartered in Redwood Shores, CA, Zilliz is backed by prestigious investors, including Aramco's Prosperity7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others. Zilliz's technologies and products help over 10,000 organizations worldwide easily create AI applications in various use cases. Learn more at zilliz.com or follow @zilliz_universe.
Media Contact:
Chris Churilo
Zilliz Inc
chris.churilo@zilliz.com
A photo accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/d28835ca-9372-4285-bdd9-c04a713ecb36
