Tokenization makes or breaks hybrid search. See how Weaviate's accent folding, custom stopwords, and /v1/tokenize endpoint power multilingual BM25.
This release introduces the built-in MCP Server, Extensible Tokenizers, Diversity Search (MMR), and Query Profiling as previews, along with Incremental Backups, Gemini audio support for multi2vec-google, and the new BlobHash property type.
This release introduces HFresh vector index (Preview), and brings Server-side Batching, Object TTL, Async Replication Improvements, Drop Inverted Indices, and Backup Restoration Cancellation to general availability.
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.
1.34 introduces flat index support with RQ quantization, server-side batching improvements, new client libraries, Contextual AI integration and much more.
Hands-on patterns: Design pattern for gen-AI enterprise applications, with Arize AI.
Learn how Weaviate's native multi-tenancy architecture delivers scalable vector search with one shard per tenant, dynamic resource management, and true data isolation.
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).
Get spun around by our new vector quantization algorithm that utilizes the power of random rotations to improve the speed-quality tradeoff of vector search with Weaviate.
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!
Design for speed, build for experience.
Master the art of scaling a vector database like Weaviate.
