Values.VectorSearchBedrockRerankingConfigurationSourceConfiguration for using Amazon Bedrock foundation models to rerank Knowledge Base vector search results. This enables more sophisticated relevance ranking using large language models.
type nonrec t = {modelConfiguration : VectorSearchBedrockRerankingModelConfiguration.t;Configuration for the Amazon Bedrock foundation model used for reranking. This includes the model ARN and any additional request fields required by the model.
*)numberOfRerankedResults : VectorSearchBedrockRerankingConfigurationNumberOfRerankedResultsInteger.t
option;The maximum number of results to rerank. This limits how many of the initial vector search results will be processed by the reranking model. A smaller number improves performance but may exclude potentially relevant results.
*)metadataConfiguration : MetadataConfigurationForReranking.t option;Configuration for how document metadata should be used during the reranking process. This determines which metadata fields are included when reordering search results.
*)}val make :
?numberOfRerankedResults:??? ->
?metadataConfiguration:??? ->
modelConfiguration:VectorSearchBedrockRerankingModelConfiguration.t ->
unit ->
tval to_value :
t ->
[> `Structure of
(string
* [> `Integer of
VectorSearchBedrockRerankingConfigurationNumberOfRerankedResultsInteger.t
| `Structure of
(string
* [> `Enum of string
| `Map of
([> `String of AdditionalModelRequestFieldsKey.t ]
* [> `Structure of 'a list ])
list
| `String of BedrockRerankingModelArn.t
| `Structure of
(string
* [> `List of
[> `Structure of
(string
* [> `String of
FieldForRerankingFieldNameString.t ])
list ]
list ])
list ])
list ])
list ]