What's New in Milvus version 2.2.9
We are proud to announce the release of Milvus 2.2.9 on behalf of the Milvus community. The 2.2.9 release contains several new and exciting features and many improvements. This blog post will highlight some of the more prominent features. For a complete list of changes, check the release notes.
- 📦 PyPI: https://pypi.org/project/milvus/
- 📚 Docs: https://milvus.io/docs
- 🛠️ Release Notes: https://milvus.io/docs/release_notes.md#v229
- 🐳 Docker Image: docker pull
- 🚀 Release: https://github.com/milvus-io/milvus/releases/tag/v2.2.9
Our community has been asking about many new features, and I am excited to share with you all that this release contains several! Just look at this feature list!
JSON support — Milvus now supports the JSON data type, seamlessly storing JSON as the accompanying vectors' metadata within your collections. You can bulk-insert JSON for large-scale ingestions and perform advanced querying and filtering operations based on the contents of your JSON fields. This JSON support also brings enhanced query performance with filters using JSON fields. Finally, you can use expressions and perform operations specifically on JSON fields within your data. This feature allows you to construct queries and apply filters based on the content and structure of your JSON fields, enabling you to extract relevant information and perform advanced data manipulation. With this support, you can leverage the expressive power of Milvus to interact with and analyze your JSON data in a more precise and flexible manner.
Dynamic schema — Allows you to handle changes to the schema dynamically.
Partition key — Allows partitioning using user-specific columns as the primary keys. This feature also removes the limits to the number of partitions you can have to help with more efficient resource utilization.
Additional features include RBAC and enabling Alibaba Cloud object store.
Please note several bug fixes and performance enhancements in the Milvus 2.2.9 release, so check out the release notes for more details.
In addition to all of the features listed above, Milvus 2.2.9 includes several bug fixes and improvements. To learn more:
See the release notes for version 2.2.9 for the complete list of changes Download Milvus and get started
Chris ChuriloChris Churilo is the VP of Marketing & Community at Zilliz where she leads all community, developer relations, and marketing efforts. Prior to Zilliz, Chris was a founding member of the InfluxData’s go to market efforts and helped propel the time series database platform to dominance in the market. In earlier roles she defined and designed a SaaS monitoring solution at Centroid, and prior to that she was the VP of product management at iPass and was the LOB for several cloud services that required her to track the business and operational metrics and analytics to help identify and resolve issues.
Start Free, Scale Easily
Try the fully-managed vector database built for your GenAI applications.
Try Zilliz Cloud for FreeKeep Reading
Demystifying the Milvus Sizing Tool
Explore how to use the Sizing Tool to select the optimal configuration for your Milvus deployment.
How to Build RAG with Milvus, QwQ-32B and Ollama
Hands-on tutorial on how to create a streamlined, powerful RAG pipeline that balances efficiency, accuracy, and scalability using the QwQ-32B model and Milvus.
OpenAI o1: What Developers Need to Know
In this article, we will talk about the o1 series from a developer's perspective, exploring how these models can be implemented for sophisticated use cases.