Skip to main content
Version: User Guides (Cloud)

Release Notes

You can find the history of Zilliz Cloud releases in these docs.

Release Notes (June 18, 2024) [READ MORE]

In this release, Zilliz Cloud has unveiled an array of new features backed by Milvus 2.4, including sparse vector support, enhanced multi-vector and hybrid search, an inverted index and fuzzy matching for faster queries, and grouping search for document-level recall. It also introduces Float16 and BFloat16 data types for improved search efficiency. In addition, the Pipelines feature now tracks token usage stats with every data ingestion and search request, streamlining performance monitoring. You can find detailed stats on the invoice page.

Release Notes (May 15, 2024) [READ MORE]

This update to Zilliz Cloud introduces the Serverless plan in BETA. It is designed for applications with variable query volumes, requiring minimal configuration and offering seamless scalability. This plan is now available on GCP us-west1 (Oregon) and includes a free trial during the BETA period. Additionally, new regions are supported for dedicated clusters: Germany West Central (Frankfurt) for Azure, and europe-west3 (Frankfurt) and us-east-4 (Virginia) for GCP. This release also introduces several enhancements to monitoring metrics, search precision control, and import jobs.

Release Notes (April 3, 2024) [READ MORE]

This update introduces powerful tools and enhancements to Zilliz Cloud: new Connectors for easy data ingestion from sources like Object Storage, Rerankers to improve search relevance, a Metrics Monitoring API for in-depth system state analytics, and a Cross Cloud Data Import feature allowing direct import from AWS S3, Google Cloud Storage, and Azure Blob Storage to vector database instances. These features combine to elevate data ingestion, search precision, and operational insight, streamlining the management of vector databases in the cloud.

Release Notes (Mar 13, 2024) [READ MORE]

Zilliz Cloud has introduced two major enhancements in its latest release. Firstly, Pipelines now support six state-of-the-art (SOTA) embedding models, which expands your data processing capabilities. The other major enhancement is that the Collection Playground feature has been added to simplify your onboarding experience. With this feature, you can easily perform basic Create, Run, Update, and Delete (CRUD) operations directly from the Zilliz Cloud console, making your data interaction processes more streamlined. You can try these new features today to enjoy a more efficient and effective workflow.

Release Notes (Dec 11, 2023) [READ MORE]

Now Zilliz Cloud services are available on Azure, starting with the East US region. Additionally, we introduce Zilliz Cloud Pipelines (Beta) which transforms unstructured data into vector embeddings for ingestion and retrieval. The release also brings improved RBAC and credential management within Clusters, with three predefined roles (admin, read-write, read-only) for user administration. Other updates include enhanced error message content and stability improvements for more reliable service.

Release Notes (Oct 17, 2023) [READ MORE]

We're pleased to announce the launch of our AWS Frankfurt region in the EU. Accompanying this expansion, we introduce beta features: Range Search, Upsert, and Cosine Metric Type, enhancing search capabilities and data management efficiency. Additional functionalities include API Key Access, Retrieve Raw Vectors, JSON_CONTAINS Filter, and Entity Count. Noteworthy improvements in RBAC, billing, pricing calculation, account management, and service stability have also been implemented for an enhanced user experience.

Release Notes (June 11, 2023) [READ MORE]

The release of Zilliz Cloud sets a new standard in vector database management. It significantly enhances the user experience for beginners, offers more affordable and flexible pricing options, enables seamless team collaboration, and provides flexible schema management. Key features of this update include a serverless cluster, diverse tier plans, cost-optimized CU, organization and collaboration support, RBAC support, partition key, dynamic schema, and JSON type support. Try out this game-changing update today!