Announcing the release of Spice v1.8.2! 🔍
Spice v1.8.2 is a patch release focused on reliability, validation, performance, and bug fixes, with improvements across DuckDB acceleration, S3 Vectors, document tables, and HTTP search.
/v1/search HTTP EndpointSpice now supports table relations for the additional_columns and where parameters in the /v1/search endpoint. This enables improved search for multi-dataset use cases, where filters and columns can be used on specific datasets.
Example:
In this example, search results from the tbl1 dataset will include columns foo and baz, where foo > 100000. For tbl2, columns bar and baz will be returned.
duckdb_index_scan_percentage and duckdb_index_scan_max_count parameters, supporting fine-tuning of index scan behavior for improved query performance.Example:
Hive-Style Partitioning: In file-partitioned mode, the DuckDB data accelerator uses Hive-style partitioning for more efficient file management.
Table-Based Partitioning: Spice now supports partitioning DuckDB accelerations within a single file. This approach maintains ACID guarantees for full and append mode refreshes, while optimizing resource usage and improving query performance. Configure via the partition_mode parameter:
ConflictException, ensuring robust error handling during index creation and improving reliability for large-scale multi-index vector search.location column as the primary key, improving performance, consistency, and query reliability.No breaking changes.
No major cookbook updates.
The Spice Cookbook (opens in a new tab) includes 81 recipes to help you get started with Spice quickly and easily.
To upgrade to v1.8.2, use one of the following methods:
CLI:
Homebrew:
Docker:
Pull the spiceai/spiceai:1.8.2 image:
For available tags, see DockerHub (opens in a new tab).
Helm:
AWS Marketplace:
🎉 Spice is now available in the AWS Marketplace (opens in a new tab)!
duckdb_partition_mode to partition_mode param by @sgrebnov (opens in a new tab) in #7622 (opens in a new tab)