Zilliz announced the release of Milvus 2.5

Zilliz announced the release of Milvus 2.5, the latest version of the open source vector database, introducing native full-text search capabilities that unify vector and keyword search in a single system. This update represents a significant leap forward in search technology, allowing developers to build more powerful and efficient search applications with less complexity. 

• Milvus LinkedIn Post
• Milvus X Post

Here are the key features that make this release special: 

• Built-in Full-Text Search: Sparse-BM25 integration, enabling powerful text processing capabilities without requiring pre-generated vector embeddings. This is a game-changer for combining semantic search with keyword precision.
• Enhanced Text Filtering: New text match capability leverages Tantivy’s analyzers for precise natural language matching, perfect for combining with vector similarity search.
• Bitmap Index: Introducing a new indexing system that significantly accelerates filtering on low-cardinality fields, improving query performance for filtered searches.
• Improved Data Management: Added support for nullable properties and default values in scalar fields, providing greater flexibility in data handling.
• Cluster Management WebUI (Beta): A comprehensive dashboard for monitoring system health and tracking performance metrics for large Milvus production deployment.

Learn more in the Milvus.io Blog Post