Zilliz

Vector database for production-ready AI

To democratise AI, Zilliz is committed to simplifying data management for AI applications and making vector databases accessible to every organisation.

Vector databases have become essential for powering advanced AI applications, which demand high recall, low latency, and robust throughput. Zilliz has positioned itself at the forefront of this field with its vector database management system, Milvus.

Building on its initial success, Zilliz released Milvus 2.4m in 2024, which significantly enhances vector search capabilities. This version introduced GPU indexing, leveraging NVIDIA's CUDA-Accelerated Graph Index for Vector Retrieval (CAGRA), which outperforms traditional CPU-based indexes like HNSW. In 2026, Milvus 2.6 was released, harnessing even more power at a lower cost.

Zilliz's commitment to innovation is further demonstrated by the expansion of its Hybrid Search capabilities, including a beta version of sparse vector embeddings for more accurate and semantically rich searches. These advancements, along with the evolution of Zilliz Cloud, emphasise the company's dedication to pushing the boundaries of what vector databases can achieve and make the future of the company an exciting one.