Blog
Milvus 2.2.6 : nouvelles fonctionnalités et mises à jour

Milvus 2.2.6 : nouvelles fonctionnalités et mises à jour

Apr 29, 20230 min read

Nouveautés de Milvus version 2.2.6

Nous déconseillons fortement d’utiliser Milvus version 2.2.5 en raison de certains problèmes critiques corrigés dans la version 2.2.6. Pour obtenir la liste complète des modifications, consultez les notes de version.

📦 PyPI : https://pypi.org/project/milvus/
📚 Docs : https://milvus.io/docs
🛠️ Notes de version : https://milvus.io/docs/release_notes.md#226
🐳 Image Docker : docker pull
🚀 Version : https://github.com/milvus-io/milvus/releases/tag/v2.2.6

Veuillez noter qu’il existe plusieurs corrections de bugs et améliorations de performances dans la version Milvus 2.2.6 ; consultez donc les notes de version pour plus de détails.

Mis à jour le Jul 13, 2026

Chris Churilo
Chris 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.

Continuer à lire

VDBBench Adds Cost-Aware Benchmarking for Vector Databases

Compare Zilliz Cloud, Pinecone, and turbopuffer with VDBBench cost-aware vector database benchmarks across latency, freshness, multitenancy, and cold starts.

Our Journey to 35K+ GitHub Stars: The Real Story of Building Milvus from Scratch

Join us in celebrating Milvus, the vector database that hit 35.5K stars on GitHub. Discover our story and how we’re making AI solutions easier for developers.

Creating Collections in Zilliz Cloud Just Got Way Easier

We've enhanced the entire collection creation experience to bring advanced capabilities directly into the interface, making it faster and easier to build production-ready schemas without switching tools.