Hybrid Search

This page describes the parameters for hybrid search as part of AI libs.

.ai.hybrid.rrf

The .ai.hybrid.rrf function applies reciprocal ranked fusion on search results.

Name	Type(s)	Description
`results`	(real[]; long[])[] \| int[][] \| long[][]	The list of nearest neighbor results from `bm25` or dense search
`const`	int \| long \| real \| float	The constant term for RRF (typically 60)

Type	Description
long[]	Re-ranked IDs

Copy

 a:101 102 103 104 105;
 b:103 106 101 107 108;
 .ai.hybrid.rrf[(a;b);60];

 101 103 102 106 104 107 105 108

The .ai.hybrid.wrrf function applies weighted reciprocal ranked fusion on search results.

Name	Type(s)	Description
`results`	(real[]; long[])[] \| int[][] \| long[][]	The list of nearest neighbor results from `bm25` or dense search
`weights`	long[]	The list of weightings, same length as results
`const`	int \| long \| real \| float	The constant term for RRF (typically 60)

Type	Description
long[]	Re-ranked IDs

Copy

 a:101 102 103 104 105;
 b:103 106 101 107 108;
 .ai.hybrid.wrrf[(a;b);1 2;60];

 103 101 106 107 108 102 104 105