What's New in Milvus 2.2.10 and 2.2.11
We are excited to announce the release of Milvus versions 2.2.10 and 2.2.11! These latest versions come loaded with numerous enhancements that significantly improve the product's functionality and user experience. We have incorporated feedback from our community of users and made updates to enhance the performance and user experiences further! This blog post will highlight some of the more prominent features. For a complete list of changes, please check the release notes.
📦 PyPI: https://pypi.org/project/milvus/
📚 Docs: https://milvus.io/docs
🛠️ Release Notes:
🐳 Docker Image: docker pull
🚀 Release: milvus-2.2.11
We are continuously enhancing RBAC to expand the security functionalities across different aspects of the system. In version 2.2.10, we introduced the 'FlushAll' function and Database API to the RBAC capabilities. These updates offer improved control over permissions and access to sensitive operations, ultimately enhancing the system's overall security.
Additionally, both versions, 2.2.10 and 2.2.11, introduced several optimizations and upgrades. Notably, in version 2.2.11, we optimized disk usage for RocksMq by enabling zstd compression starting from level 2. This enhancement significantly improves storage efficiency. Additionally, in version 2.2.10, we made a major improvement by replacing the CGO payload writer with a Go payload writer. This change reduced memory usage, leading to improved system performance and stability.
Please note that there are several bug fixes and performance enhancements in the Milvus 2.2.10 & 2.2.1 releases, so check out the release notes for more details.
Summary
In addition to all of the features listed above, Milvus 2.2.10 & 2.2.11 include several bug fixes and improvements. To learn more:
See the release notes for version 2.2.10 & version 2.2.11 for the complete list of changes Download Milvus and get started.
Keep Reading
How to Choose the Best Embedding Model for RAG in 2026: 10 Models Benchmarked
We benchmarked 10 embedding models on cross-modal, cross-lingual, long-document, and dimension compression tasks. See which one fits your RAG pipeline.
Top 10 Context Engineering Techniques You Should Know for Production RAG
A practical guide to context engineering for production LLM systems, covering RAG, context processing, memory, agents, and multimodal context.
Why Not All VectorDBs Are Agent-Ready
Explore why choosing the right vector database is critical for scaling AI agents, and why traditional solutions fall short in production.