Charles Xie is the founder and CEO of Zilliz, specializing in constructing next-generation databases and search technologies for AI and LLMs applications. At Zilliz, he also invented Milvus, the world’s hottest open-source vector database for production-ready AI. He’s currently a board member of LF AI & Data Foundation and served because the board’s chairperson in 2020 and 2021. Charles previously worked at Oracle as a founding engineer of the Oracle 12c cloud database project. Charles holds a master’s degree in computer science from the University of Wisconsin-Madison.
Zilliz is the team behind LF AI Milvus®, a widely used open-source vector database. The corporate focuses on simplifying data infrastructure management, aiming to make AI more accessible to corporations, organizations, and individuals alike.
Are you able to share the story behind founding Zilliz and what inspired you to develop Milvus and deal with vector databases?
My journey within the database field spans over 15 years, including six years as a software engineer at Oracle, where I used to be a founding member of the Oracle 12c Multitenant Database team. During this time, I noticed a key limitation: while structured data was well-managed, unstructured data—representing 90% of all data—remained largely untapped, with just one% analyzed meaningfully.
In 2017, the growing ability of AI to process unstructured data marked a turning point. Advances in NLP showed how unstructured data might be transformed into vector embeddings, unlocking its semantic meaning. This inspired me to found Zilliz, with a vision to administer “zillions of information.” Vector embeddings became the cornerstone for bridging the gap between unstructured data and actionable insights. We developed Milvus as a purpose-built vector database to bring this vision to life.
Over the past two years, the industry has validated this approach, recognizing vector databases as foundational for managing unstructured data. For us, it’s about greater than technology—it’s about empowering humanity to harness the potential of unstructured data within the AI era.
How has the journey of Zilliz evolved since its inception six years ago, and what key challenges did you face while pioneering the vector database space?
The journey has been transformative. After we began Zilliz seven years ago, the true challenge wasn’t fundraising or hiring—it was constructing a product in completely uncharted territory. With no existing roadmaps, best practices, or established user expectations, we needed to chart our own course.
Our breakthrough got here with the open-sourcing of Milvus. By lowering barriers to adoption and fostering community engagement, we gained invaluable user feedback to iterate and improve the product. When Milvus launched in 2019, we had around 30 users by year-end. This grew to over 200 by 2020 and nearly 1,000 soon after.
Today, vector databases have shifted from a novel concept to essential infrastructure within the AI era, validating the vision we began with.
As a vector database company, what unique technical capabilities does Zilliz offer to support multimodal vector search in modern AI applications?
Zilliz has developed advanced technical capabilities to support multimodal vector search:
- Hybrid Search: We enable simultaneous searches across different modalities, similar to combining a picture’s visual features with its text description.
- Optimized Algorithms: Proprietary quantization techniques balance recall accuracy and memory efficiency for cross-modal searches.
- Real-Time and Offline Processing: Our dual-track system supports low-latency real-time writes and high-throughput offline imports, ensuring data freshness.
- Cost Efficiency: Our Prolonged Capability instances leverage intelligent Tiered Storage to cut back storage costs significantly while maintaining high performance.
- Embedded AI Models: By integrating multimodal embedding and rating models, we’ve lowered the barrier to implementing complex search applications.
These capabilities allow developers to efficiently handle diverse data types, making modern AI applications more robust and versatile.
How do you see Multimodal RAG advancing AI’s ability to handle complex real-world data like images, audio, and videos alongside text?
Multimodal RAG (Retrieval-Augmented Generation) represents a pivotal evolution in AI. While text-based RAG has been distinguished, most enterprise data spans images, videos, and audio. The power to integrate these diverse formats into AI workflows is critical.
This shift is timely, because the AI community debates the boundaries of accessible web text data for training. While text data is finite, multimodal data stays vastly underutilized—starting from corporate videos to Hollywood movies and audio recordings.
Multimodal RAG unlocks this untapped reservoir, enabling AI systems to process and leverage these wealthy data types. It’s not nearly addressing data scarcity; it’s about expanding the boundaries of AI’s capabilities to raised understand and interact with the true world.
How does Zilliz differentiate itself from competitors within the rapidly growing vector database market?
Zilliz stands out through several unique elements:
- Dual Identity: We’re each an AI company and a database company, pushing the boundaries of information management and AI integration.
- Cloud-Native Design: Milvus 2.0 was the primary distributed vector database to adopt a disaggregated storage and compute architecture, enabling scalability and cost-efficiency for over 100 billion vectors.
- Proprietary Enhancements: Our Cardinal engine achieves 3x the performance of open-source Milvus and 10x over competitors. We also offer disk-based indexing and intelligent Tier Storage for cost-effective scaling.
- Continuous Innovation: From hybrid search capabilities to migration tools like VTS, we’re continuously advancing vector database technology.
Our commitment to open source ensures flexibility, while our managed service, Zilliz Cloud, delivers enterprise-grade performance with minimal operational complexity.
Are you able to elaborate on the importance of Zilliz Cloud and its role in democratizing AI and making vector search services accessible to small developers and enterprises alike?
Vector search has been utilized by tech giants since 2015, but proprietary implementations limited its broader adoption. At Zilliz, we’re democratizing this technology through two complementary approaches:
- Open Source: Milvus allows developers to construct and own their vector search infrastructure, lowering technical barriers.
- Managed Service: Zilliz Cloud eliminates operational overhead, offering a straightforward, cost-effective solution for businesses to adopt vector search without requiring specialized engineers.
This dual approach makes vector search accessible to each developers and enterprises, enabling them to deal with constructing revolutionary AI applications.
With advancements in LLMs and foundation models, what do you suspect will likely be the following big shift in AI data infrastructure?
The following big shift will likely be the wholesale transformation of AI data infrastructure to handle unstructured data, which makes up 90% of the world’s data. Existing systems, designed for structured data, are ill-equipped for this shift.
This transformation will impact every layer of the information stack, from foundational databases to security protocols and observability systems. It’s not about incremental upgrades—it’s about creating recent paradigms tailored to the complexities of unstructured data.
This transformation will touch every aspect of the information stack:
- Foundational database systems
- Data pipelines and ETL processes
- Data cleansing and transformation mechanisms
- Security and encryption protocols
- Compliance and governance frameworks
- Data observability systems
We’re not only talking about upgrading existing systems – we’re constructing entirely recent paradigms. It’s like moving from a world optimized for organizing books in a library to 1 that should manage, understand, and process your entire web. This shift represents a complete recent world, where every component of information infrastructure might have to be reimagined from the bottom up.
This revolution will redefine how we store, manage, and process data, unlocking vast opportunities for AI innovation.
How has the combination of NVIDIA GPUs influenced the performance and scalability of your vector search?
The mixing of NVIDIA GPUs has significantly enhanced our vector search performance in two key areas.
First, in index constructing, which is one of the crucial compute-intensive operations in vector databases. In comparison with traditional database indexing, vector index construction requires several orders of magnitude more computational power. By leveraging GPU acceleration, we have dramatically reduced index-building time, enabling faster data ingestion and improved data visibility.
Second, GPUs have been crucial for high-throughput query use cases. In applications like e-commerce, where systems must handle 1000’s and even tens of 1000’s of queries per second (QPS), GPU’s parallel processing capabilities have proven invaluable. By utilizing GPU acceleration, we are able to efficiently process these high-volume vector similarity searches while maintaining low latency.
Since 2021, we have been collaborating with NVIDIA to optimize our algorithms for GPU architecture, while also developing our system to support heterogeneous computing across different processor architectures. This provides our customers the flexibleness to decide on essentially the most suitable hardware infrastructure for his or her specific needs.
As vector databases play a critical role in AI, do you see their application extending beyond traditional use cases like suggestion systems and search to industries like healthcare?
Vector databases are rapidly expanding beyond traditional applications like suggestion systems and search, penetrating industries we never imagined before. Let me share some examples.
In healthcare and pharmaceutical research, vector databases are revolutionizing drug discovery. Molecules might be vectorized based on their functional properties, and using advanced features like range search, researchers can discover all potential drug candidates which may treat specific diseases or symptoms. Unlike traditional top-k searches, range search identifies all molecules inside a certain distance of the goal, providing a comprehensive view of potential candidates.
In autonomous driving, vector databases are enhancing vehicle safety and performance. One interesting application is in handling edge cases – when unusual scenarios are encountered, the system can quickly search through massive databases of comparable situations to search out relevant training data for fine-tuning the autonomous driving models.
We’re also seeing revolutionary applications in financial services for fraud detection, cybersecurity for threat detection, and targeted promoting for improved customer engagement. As an illustration, in banking, transactions might be vectorized and compared against historical patterns to discover potential fraudulent activities.
The facility of vector databases lies of their ability to grasp and process similarity in any domain – whether it’s molecular structures, driving scenarios, financial patterns, or security threats. As AI continues to evolve, we’re just scratching the surface of what is possible. The power to efficiently process and find patterns in vast amounts of unstructured data opens up possibilities we’re only starting to explore.
How can developers and enterprises best engage with Zilliz and Milvus to leverage vector database technology of their AI projects?
There are two principal paths to leverage vector database technology with Zilliz and Milvus, each fitted to different needs and priorities. Should you value flexibility and customization, Milvus, our open-source solution, is your best option. With Milvus, you’ll be able to:
- Experiment freely and learn the technology at your personal pace
- Customize the answer to your specific requirements
- Contribute to development and modify the codebase
- Maintain complete control over your infrastructure
Nonetheless, if you ought to deal with constructing your application without managing infrastructure, Zilliz Cloud is the optimal selection. It offers:
- An out-of-the-box solution with one-click deployment
- Enterprise-grade security and compliance
- High availability and stability
- Optimized performance without operational overhead
Consider it this manner: in case you enjoy ‘tinkering’ and wish maximum flexibility, go together with Milvus. If you ought to minimize operational complexity and get straight to constructing your application, select Zilliz Cloud.
Each paths will get you to your destination – it’s only a matter of how much of the journey you ought to control versus how quickly that you must arrive
