Zilliz Vector DB Now on Azure
Zilliz, the company behind the widely used open-source vector database Milvus, announced the general availability of its "Bring Your Own Cloud" (BYOC) offering on Microsoft Azure. This move makes Zilliz Cloud's managed vector database service available across all major cloud providers, giving enterprises more flexibility for building AI applications.
The "Bring Your Own Cloud" (BYOC) model from Zilliz addresses a critical enterprise dilemma: using a powerful managed service without moving sensitive data outside of an organization's own security perimeter. With BYOC, the Zilliz-managed control plane operates separately from the data plane, which is deployed directly inside the customer's own cloud account, ensuring data remains within their control. This architecture simplifies compliance with regulations like GDPR and allows companies to apply their existing security and governance frameworks. Zilliz claims this launch makes it the first managed vector database provider to offer a BYOC option across all three major cloud platforms: Amazon Web Services, Google Cloud Platform, and now Microsoft Azure. This multi-cloud flexibility is crucial for enterprises that use different cloud providers for various business units or have data residency requirements that vary by region. The expansion to Azure was a deliberate final step, targeting the large number of enterprises standardized on Microsoft's cloud ecosystem. For organizations heavily invested in Azure, this integration allows them to run their vector database in the same environment as other Azure AI services, like Azure OpenAI. This co-location eliminates cross-cloud data movement, reduces latency for AI workflows, and can lower costs. Customers can also leverage their existing Microsoft enterprise agreements and reserved capacity, streamlining billing and procurement. Underpinning Zilliz Cloud is the open-source vector database Milvus, which the company created. Milvus is designed for large-scale AI applications, capable of handling billions of vectors with low-latency search results, making it popular for use cases like retrieval-augmented generation (RAG), recommendation engines, and semantic search. Zilliz Cloud is engineered to support these billion-scale workloads with sub-10ms latency. The platform's management is streamlined for engineering teams through a Zilliz Cloud Terraform Provider, which allows for the automation of BYOC deployments. This enables integration into existing Infrastructure-as-Code (IaC) workflows, significantly speeding up the deployment of production-grade AI infrastructure from months to days. Zilliz also provides tools for migrating from other vector databases like Pinecone, Qdrant, and Weaviate.
