SemanticSearchOptions Class

Enables a debugging tool that can be used to further explore your reranked results.

Allows the user to choose whether a semantic call should fail completely (default / current behavior), or to return partial results.

Allows the user to set an upper bound on the amount of time it takes for semantic enrichment to finish processing before the request fails.

This parameter is only valid if the query type is 'semantic'. If set, the query returns answers extracted from key passages in the highest ranked documents.The number of answers returned can be configured by appending the pipe character '|' followed by the 'count-(number of answers)' option after the answers parameter value, such as 'extractive|count-3'. Default count is 1. The confidence threshold can be configured by appending the pipe character '|' followed by the 'threshold-(confidence threshold)' option after the answers parameter value, such as 'extractive|threshold-0.9'. Default threshold is 0.7.

This parameter is only valid if the query type is 'semantic'. If set, the query returns captions extracted from key passages in the highest ranked documents. When Captions is set to 'extractive', highlighting is enabled by default, and can be configured by appending the pipe character '|' followed by the 'highlight-(true/false)' option, such as 'extractive|highlight-true'. Defaults to 'None'.

This parameter is only valid if the query type is semantic. When QueryRewrites is set to generative, the query terms are sent to a generate model which will produce 10 (default) rewrites to help increase the recall of the request. The requested count can be configured by appending the pipe character | followed by the count-<number of rewrites> option, such as generative|count-3. Defaults to None.

The name of a semantic configuration that will be used when processing documents for queries of type semantic.

The list of field names used for semantic search.

Allows setting a separate search query that will be solely used for semantic reranking, semantic captions and semantic answers. Is useful for scenarios where there is a need to use different queries between the base retrieval and ranking phase, and the L2 semantic phase.