Cardinal Vector Search Engine and a Series of New Features Lead to 10X Performance
SAN FRANCISCO, (GLOBE NEWSWIRE) — Zilliz, the company behind the open-source vector database Milvus, today announced a host of new features to Zilliz Cloud, the company’s fully managed vector database built on Milvus. Highlighted by the company’s groundbreaking Cardinal vector search engine, Zilliz Cloud is a dedicated vector database designed to handle the world’s biggest and most demanding workloads with cost efficiency.
“As companies scale up similarity search for recommendation systems, RAG, and image retrieval, they face a choice between overprovisioning hardware or spending months tuning vector indexes,” said Charles Xie, founder and CEO of Zilliz. “Our latest release increases query performance by 10X over previous configurations, with AutoIndex dynamically adapting indexing strategies to each dataset—ultimately letting teams focus on building AI applications instead of managing vector databases.”
Zilliz Cloud for GenAI Readiness and Future-Proofing
In 2025 and beyond, many enterprises will focus on AI in production, which requires increased scalability, better performance and higher reliability requirements. AI applications, particularly those leveraging vector embedding from deep learning, require processing and searching through enormous amounts of high-dimensional data that traditional databases can’t efficiently handle. Zilliz Cloud is part of the essential infrastructure for GenAI initiative, and its latest innovations address these modern challenges with a more scalable, performant and cost-efficient database that provides the best price-performance ratio in the market.
Zilliz Cloud consistently demonstrates clear ROI and business value, making it a strategic investment in AI infrastructure for enterprises looking to unlock the power of data. Key features of Zilliz Cloud include:
- Enhanced Search Accuracy. A significant upgrade to ANN search, supporting a wide range of advanced operations such as hybrid search with multi-vector fields, filtered search using scalar fields to refine results, range search within a specified distance, grouping search to ensure diverse results. It also accommodates both dense and sparse vectors, enabling precise and relevant outcomes across different data types and making it highly effective for complex AI applications.
- Significant Cost Savings through Hierarchical Storage. Traditional vector databases rely on in-memory storage, resulting in high costs and limited scalability. Hierarchical storage addresses these issues by strategically distributing data across various storage tiers, including memory, local disks, and distributed object stores. This approach delivers a 10x cost reduction while enabling the management of substantially larger data volumes.
- AutoIndex. Zero manual index tuning with an intelligent system that automatically selects the best search strategy based on customers’ data and hardware setup, eliminating the complexity of manual configuration without sacrificing optimal search performance.
- Supercharged Performance. Delivers high-performance vector search through three layers of optimization: advanced algorithms including unified IVF-based and graph-based approaches that maintain high accuracy even with filtered results; engineering solutions like specialized memory allocation and multi-threading for real-world performance; and low-level kernel optimizations for x86 and ARM platforms that achieve up to 3X speedup over unoptimized implementations.
Enterprise-Grade Performance and Scalability
Zilliz Cloud is the most scalable vector database solution on the market, thanks to its fully distributed architecture for large-scale deployments. Additionally, Zilliz Cloud has achieved breakthrough performance metrics, including 10X higher performance in production deployments.
The platform monitors for 41 alerts within 26 separate metrics across infrastructure and data operations to minimize service disruptions and optimize performance. Auth0-based single sign-on (SSO) simplifies IT management and provides an extra layer of security, while a 99.95% uptime SLA ensures that enterprises avoid downtime for their mission-critical workloads. Finally, integrations such as Prometheus allow businesses to leverage their existing tools to streamline operations.
A Foundation Built on Open-Source Innovation
Zilliz Cloud is built on Milvus, the company’s high-performance open-source vector database that is purpose-built to handle billions of vectors. The open-source nature of Zilliz fosters continuous innovation and development, with an active and expansive community that includes users and open-source contributors that share new ideas, collaborate on projects and promote innovation and learning.
Community members regularly contribute code and other valuable contributions, creating a sense of trust and validation across the industry. In this vein, Zilliz Cloud is the natural enterprise evolution of proven open-source technology.
Named a Leader in Forrester’s 2024 Wave™ report for Vector Database Providers, Zilliz Cloud has solved vector search on a large scale thanks to its distributed approach to indexing strategies and optimization with underlying hardware via multiple deployment and service model offerings. The product differentiates itself in the market with AI-powered optimization, universal vector support, availability across 12 regions globally and support for AWS Graviton processors.
To read more about the latest Zilliz Cloud release, visit our 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 Churillo, VP of Marketing
[email protected]
A photo accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/de3af54e-0b52-4a84-b747-e8252a0f24fb
Read More: AvePoint Introduces First-to-Market Benchmarking Data for Microsoft 365 Copilot