- Added parallel prefill for compressed vector cache and non‑blocking segment drop in compaction, boosting HNSW performance and reliability.
- Enhanced validation (shard read‑only reason, batch class name, near‑object, ref2vec config) and fixed numerous bugs including autoschema handling, nested nil props, argument order errors, data races, long‑text vectorization, and GRPC gro...
- Introduced new capabilities such as segments cleanup improvements, limit for HNSW visited‑list pool, and support for updating generative and reranker modules.
v1.26.8 - Compressed vector cache parallel prefill and Non-blocking segment drop in compaction improvements
Official Weaviate changelog summary with source attribution, release tags, and community reactions.
Track this Weaviate release note alongside related changelog updates, risky changes, and weekly digest signals from the developer community.
Verify the original release note
Every summary should remain traceable to the original changelog or release source.
Follow this in context
Turn this Weaviate release note into a weekly digest for the tools you actually use.
Create digestMore Weaviate changelog updates
Bound digest RPC memtable snapshots to the requested key range and improved async replication performance by negotiating binary digest encoding and carrying byte ID digests end‑to‑end.
Added new REST search endpoints (bm25, hybrid, near object, aggregate counts) and backup role inclusion feature.
Fix async replication handling, including local resolution of replicas, leaked goroutine fixes, and proper tenant restoration on failures.