v0.8.0

[generall]

Change log

🔮 Features

• Experimental support for distributed deployment - [docs] [issues]

  • Cluster topology synchronization via Raft consensus protocol
  • Sharding for the collections
  • Distributed search and updates
  • Cluster status API - [sharding] cluster status API #605

• Filtering by similarity score - Score filtering request #113

• On-disk payload storage - [real-time index] on-disk payload storage #406

  • Store large payload with less RAM usage

• On-flight payload indexing - payload indexes are available without segment re-build

  • Streaming updates for Numeric, Keyword, and Geo indexes: [real-time index] add In-mem btree numeric index #575, [real-time index] OnDIsk persistence layer for keyword index #592, [real-time index] OnDIsk persistence layer for geo index #593

🔧 Improvements

• Faster payload index - Better use of column index #461

• Better error reporting

  • Return errors as JSON HTTP 422 errors do not return JSON #555
  • Better handling of mismatched enums Broken String IDs that Result in Json deserialize error #551

• Enable CORS headers for Swagger UI access - Endpoint for queries UI #610

• HNSW Speed improvements (Disable simd on small dimensions #508, optimize push in fixed priority queue #513)

• Storage optimization

  • RocksDB better log rotation - RocksDB creates huge LOG.* files by default #516
  • Disable redundant WAL in RocksDB - Disable wal for rocksdb #576
  • Unite RocksDB columns in single DB - Unite rocksdb of segment #585
  • Parallel segment creation - Parallel segments creation #598

• Better support for Int payload in gRPC - gRPC int payload #564

🚧 Breaking changes

• Due to significant changes in payload storage, collections created with the previous engine version are not compatible with the new version. The most straightforward migration approach would be to re-create collections with the latest version from scratch. Breaking changes are required to make our v1.0 release as legacy-free as possible. Hope for your understanding.

⌛ Work-in-progress

• We are continuing the development of Distributed Deployment. In next release we will address shard re-balancing and replication issues. Stay tuned and check out our Roadmap for details.

---

This discussion was created from the release v0.8.0.