Blog
Zilliz Cloud: a Fully-Managed Vector Database That Minimizes Users’ Costs for Building AI Apps

Zilliz Cloud: a Fully-Managed Vector Database That Minimizes Users’ Costs for Building AI Apps

Aug 01, 20235 min read

Re-evaluating the value of vector databases

The growth of Artificial Intelligence Generated Content (AIGC) has led to the advancement of vector search technologies, creating new demands and expanding the user base beyond algorithm engineers to include application and backend developers. The improvement in model generalization has also made it easier to build AI applications.

As a vector database engineer and the product designer behind Zilliz Cloud, recent changes have prompted me to re-evaluate the value of vector databases. At Zilliz, we prioritize providing our customers with a user-friendly, efficient, reliable, and affordable product. One of our most important goals is to offer a vector database that minimizes usage costs for developers throughout their development cycle. This goal includes faster vector search speed, lower storage costs, and freeing up users from maintenance and operations to focus on their business. The latest release of Zilliz Cloud is a significant step towards achieving this goal.

Zilliz Cloud minimizes the overall usage costs for AI developers

The latest Zilliz Cloud is a game-changing update for developers looking to build generative AI applications. It brings many exciting features to the table, such as partition key, dynamic schema, and JSON support. Moreover, Zilliz Cloud offers more affordable pricing options, making it accessible to all developers regardless of budget. By minimizing the overall usage costs, Zilliz Cloud makes it possible for traditional companies and startups to create innovative AI applications.

When using vector databases, there are usually costs related to development, hardware, and maintenance. Zilliz Cloud distinguishes itself by greatly minimizing these costs. In the following sections, we will explore how Zilliz Cloud make it happen.

Minimized development costs

Lower development costs mean streamlined development processes, enabling developers to focus on building their applications and avoid unnecessary time expenditure on complex deployments, difficult-to-navigate APIs, and adaptation efforts.

Zilliz Cloud introduces many new features that can minimize development costs and relieve the burden on developers. For example, Zilliz Cloud now supports the following features.

Dynamic schema allows users to insert entities with dynamically varied fields into a collection instead of being limited to a predefined static schema.
The JSON data type allows for more flexible data storage.
A RESTful interface makes API usage more straightforward and more streamlined.
Multi-tenant partition keys ensure both efficient queries and data separation for multi-tenant applications.
Intelligent Index 2.0 eliminates the need to understand complex index types and configurations.
Access via either API keys or passwords can better cater to developers' habits.

Minimized costs for hardware resources

Memory and computation are among the most expensive resources in vector databases because they are computationally and memory intensive. Therefore, minimizing memory and computational costs is crucial to making vector databases more accessible.

Zilliz Cloud includes many features to minimize hardware costs, not just in lab testing environments but also in massive production environments.

The newly introduced Cost-Optimized compute unit (CU) has the same storage capacity as the existing Capacity-Optimized CU but is about 30% cheaper. The Cost-Optimized CU is best for users on a limited budget who don't require demanding latency or query throughput but still want top-tier solutions.
Scalar filtering is now faster with vectorized execution, reducing the time for running a single scalar filtering from 2ms to less than 0.5ms. In the meantime, multiple execution plans based on cost evaluation have been available to improve graph connectivity in extensive data filtering, enhancing the performance of scalar filtering by more than 50x in specific cases.
More pricing options with drastic price reductions cater to various requirements: Starter, Standard, Enterprise, and Self-hosted plans. Each plan meticulously balances cost, performance, service quality, and compliance, ensuring every user can find a tailored solution that meets their needs.
VectorDBBench, an open-source benchmarking tool, has been introduced to evaluate various vector databases based on QPS, capacity, latency, and other metrics. This tool can help users select the best vector database for their business needs.

Minimized maintenance costs

Maintenance costs are a crucial but often overlooked expense. Zilliz Cloud alleviates users' maintenance concerns, enabling users to concentrate on their core business operations.

The free serverless tier offers up to 2 collections, each handling up to 500,000 vectors of 768 dimensions or more on a smaller scale. This new offering provides significant data-handling capabilities without requiring extensive infrastructure investments.
The new Organizations and Roles feature simplifies team access and permission management with fine-grained control over resource accessibility. This feature allows for secure and flexible collaborative workflows, making it especially useful for large organizations with multiple projects and team members needing access to Zilliz Cloud's vector database services.
The rolling upgrade feature ensures that users' systems remain available and responsive to requests, providing a seamless and uninterrupted experience.

For more details about Zilliz Cloud’s new features, see our release notes.

What can we expect from Zilliz Cloud in the future?

Since its inception, Zilliz Cloud has been committed to enhancing developers' productivity and empowering users to uncover the vast potential of unstructured data. We welcome new ideas and suggestions and are excited to collaborate with everyone to advance vector searching. In future releases, we will introduce more features, including:

Unstructured data processing pipelines
Support for more complex aggregation functions
Next-generation scalar query engine and vector retrieval engine
Automatic scaling instance types
Global expansion of our services

And more! Stay tuned!

Getting started with Zilliz Cloud

Start for free with the new Starter Plan! A great plan to get started with no installation hassles and does not require a credit card!
Or start your 30-day free trial of the Standard plan with $100 worth of credits upon registration and the opportunity to earn up to $200 worth of credits in total.
Dive deeper into the Zilliz Cloud documentation.
Check out the guide on migrating from Milvus to Zilliz Cloud.

James Luan
James Luan is the VP of Engineering at Zilliz. With a master's degree in computer engineering from Cornell University, he has extensive experience as a Database Engineer at Oracle, Hedvig, and Alibaba Cloud. James played a crucial role in developing HBase, Alibaba Cloud's open-source database, and Lindorm, a self-developed NoSQL database. He is also a respected member of the Technical Advisory Committee of LF AI & Data Foundation, contributing his expertise to shaping the future of AI and data technologies.