This release introduces Object Time-to-Live (TTL), zstd compression support, flat index RQ quantization, multimodal support with Weaviate Embeddings, runtime configurable OIDC certificates and much more.
The Weaviate Java client v6 is now generally available! This release brings a completely redesigned API that embraces modern Java patterns, simplifies common operations, and makes working with vector databases more intuitive than ever.
1.34 introduces flat index support with RQ quantization, server-side batching improvements, new client libraries, Contextual AI integration and much more.
Weaviate Cloud gets an updated pricing model.
1.33 brings compression by default for optimal resource utilization, powerful 1-bit rotational quantization (RQ), streamlined server-side batch imports, enhanced OIDC group management, and collection aliases become generally available (GA).
Learn how Search Mode compares against Hybrid Search on the BEIR, LoTTe, BRIGHT, EnronQA, and WixQA Information Retrieval benchmarks.
The Query Agent is now generally available! Learn how the interface to databases is shifting with the introduction of agentic retrievers – domain experts at using Weaviate’s APIs with your data.
1.32 adds collection aliases for no-downtime collection migrations, efficient & powerful rotational quantization (RQ), GA replica movement, memory reduction with compressed HNSW connections and more!
Learn about the new certified Weaviate Confluent Apache Kafka Connector!
1.31 adds MUVERA for multi-vector embeddings, new BM25 operators, the ability to add new object vectors, and more!
Learn about how you can use our new agentic personalization service to provide user-catered recommendations from Weaviate collections.
Read about BlockMax WAND and multi-vector embeddings in GA, API-based user management, RAG improvements, xAI model support, and more!
