AIDB 4.1.0 release notes v7

Released: 19 May 2025

AIDB 4.1.0 includes the following enhancements and bug fixes:

TypeDescription
Enhancement Automatic unnesting of preparer results: The preparer pipeline now unnests result collections for operations that transform the shape of input data with an additional dimension. This allows preparer output to be consumed more easily by other preparers or knowledge bases. Unnested results include a new part_id column to track the new dimension, and a unique_id column for unique identification.
EnhancementChanged output column for chunk_text(): The enumeration column returned by the chunk_text() primitive function is now part_id instead of chunk_id to match the other preparer primitives and operations.
EnhancementBatch processing for embeddings with external models: The external model providers embeddings, openai_embeddings, and nim_embeddings can now send a batch of inputs in a single request rather than multiple concurrent requests. This can improve performance and hardware utilization. The feature is fully configurable and can be disabled.