VectorSearchRerankingConfiguration
Configuration for reranking vector search results to improve relevance. Reranking applies additional relevance models to reorder the initial vector search results based on more sophisticated criteria.
Types
Properties
Link copied to clipboard
Configuration for using Amazon Bedrock foundation models to rerank search results. This is required when the reranking type is set to BEDROCK.
Link copied to clipboard
The type of reranking to apply to vector search results. Currently, the only supported value is BEDROCK, which uses Amazon Bedrock foundation models for reranking.
Functions
Link copied to clipboard
inline fun copy(block: VectorSearchRerankingConfiguration.Builder.() -> Unit = {}): VectorSearchRerankingConfiguration