Changelog

Features: Added support for regular-expression filtering in our query language, enabling more flexible querying logic.
Benchmarks: Published the new TopK Benchmarks results, showcasing performance and scalability across production-like workloads for multiple providers.
Billing: Shipped billing, unlocking end-to-end usage tracking and payment workflows.
Performance: Shipped distributed compaction to optimize cost and improve indexing throughput per collection.

Features: Added update()API to simplify partial record updates.
Features: Shipped support for delete-by-filter operations for more flexible bulk deletions.
Docs & SDKs: Added support for Cohere’s embed-v4 model in semantic_index() and exposed organization limits in ddb-management-plane for improved visibility and management.

Docs & SDKs: Published SDK reference for Python and JavaScript clients, and added detailed docstrings for a smoother developer experience in both SDKs
Python SDK: Released AsyncClient for easier async workflows.
String Operators: Added lt, lte, gt, gte, min, and max.
Query Helpers: Introduced any and all helpers.
List Support: Added contains and in operators for list fields.
Observability: Added Query Latency and Write Latency charts to the Usage Metrics in console.
New Data Type: Added int8 vector support.
Eager Caching: Added support for eager caching to mitigate tail latencies for concurrent read/write workloads.
Faster GETs: Added option to cache raw document data and improved performance with zero-copy design.
Performance: Improved performance for queries with default & strong consistency level.

Lists Data Type: Native support for list fields.
Performance: Added skip_refine query option to improve speed when reranking isn’t needed.
Monitoring: Usage Metrics now available directly in the console.

Math Operators: Added ln, exp, sqrt, square, min, max, and abs.
Advanced Querying: Introduced choose, match_all, match_any, coalesce, and boost (with null coalescing).
Binary Data: Added bytes() constructor to the Python SDK.
Performance: Optimized workload distribution for large-sacle deployments.

Sparse Vectors: Added support for f32 and u8 sparse vector fields.
Benchmarks: Published billion-scale benchmarks for dense & sparse vector search with filtering.