What's New in Milvus version 2.2.5
What's New in Milvus version 2.2.5
We are proud to announce the release of Milvus 2.2.5 on behalf of the Milvus community. The 2.2.5 release contains a few new 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#225
- 🐳 Docker Image: docker pull
- 🚀 Release: https://github.com/milvus-io/milvus/releases/tag/v2.2.5
One of the highlights of this release is a applying a security fix for MinIO (MinIO CVE-2023-28432) by updating to the latest MinIO release (RELEASE.2023-03-20T20-16-18Z). In addition, there were several enhancements added including the following feature:
- First/Random replica selection policy — This First/Random replica selection policy selects replicas in a round-robin fashion. If the first replica chosen fails, the policy will randomly select another replica for the operation, improving the throughput by reducing the time it takes to complete.
Please note that there are several bug fixes and performance enhancements in the Milvus 2.2.5 release, so check out the release notes for more details.
Summary
In addition to all of the features listed above, Milvus 2.2.5 includes several bug fixes and improvements. To learn more:
See the release notes for version 2.2.5 for the complete list of changes Download Milvus and get started
Keep Reading

3 Easiest Ways to Use Claude Code on Your Mobile Phone
Run Claude Code from your phone with Remote Control, Happy Coder, or SSH + Tailscale. Comparison table, setup steps, and tools for typing, memory, and parallel tasks.

The Real Bottlenecks in Autonomous Driving — And How AI Infrastructure Can Solve Them
Autonomous driving faces a data bottleneck. Learn how AI-native vector databases like Zilliz solve scale, cost, and insight challenges across AV pipelines.

Introducing DeepSearcher: A Local Open Source Deep Research
In contrast to OpenAI’s Deep Research, this example ran locally, using only open-source models and tools like Milvus and LangChain.



