Apache Solr open-source search software
Ref guide - Improve docs for Dense Vector reranking examples (#4532)
Adam Quigleyd33bac878bec
diff --git a/solr/solr-ref-guide/modules/query-guide/pages/dense-vector-search.adoc b/solr/solr-ref-guide/modules/query-guide/pages/dense-vector-search.adocindex a9e965f0ae6..fd9a916a88a 100644--- a/solr/solr-ref-guide/modules/query-guide/pages/dense-vector-search.adoc+++ b/solr/solr-ref-guide/modules/query-guide/pages/dense-vector-search.adoc@@ -816,7 +816,37 @@ Some use cases where `includeTags` and/or `excludeTags` may be more useful then-=== Usage in Re-Ranking Query+[[vector-reranking]]+== Usage in Re-Ranking Query++Dense vector similarity scores can be used to xref:query-guide:query-re-ranking.adoc[re-rank] first pass query results.+Possible use cases include:++* Re-ranking approximate results from a quantized vector field using full fidelity float vectors.+* Re-ranking lexical search results with dense vector similarity scores.++Details about using the ReRank Query Parser can be found in the xref:query-guide:query-re-ranking.adoc[Query Re-Ranking] section.++=== Re-Ranking with vectorSimilarity Function Query++The xref:query-guide:function-queries.adoc#vectorsimilarity-function[vectorSimilarity()] function can be used with the `{!func}` query parser to re-rank by vector similarity.+When used as a function query, `vectorSimilarity()` computes the exact similarity for only the candidate documents selected for re-ranking, without traversing the index graph.++Here is an example of re-ranking a lexical query using a `DenseVectorField` named `vector`:++[source,text]+?q=title:phone&rq={!rerank reRankQuery=$rqq reRankDocs=100 reRankWeight=1}&rqq={!func}vectorSimilarity(vector,[1.0,2.0,3.0,4.0])++NOTE: The default `reRankOperator` is `add`, which sums the first-pass score and the vector similarity score.+Since these scores may differ in magnitude, you can adjust `reRankWeight` to control the balance between them, or use `reRankOperator=replace` to score re-ranked documents by vector similarity alone.++When using a quantized vector field type (such as `ScalarQuantizedDenseVectorField`), the KNN first pass scores are computed on the quantized vectors.+Here is an example of re-ranking those results with exact float similarity scores, where `topK` matches `reRankDocs`:++[source,text]+?q={!knn f=vector topK=100}[1.0,2.0,3.0,4.0]&rq={!rerank reRankQuery=$rqq reRankDocs=100 reRankWeight=1 reRankOperator=replace}&rqq={!func}vectorSimilarity(vector,[1.0,2.0,3.0,4.0])++=== Re-Ranking with knn Query ParserBoth dense vector search query parsers can be used to rerank first pass query results:@@ -834,8 +864,6 @@ the k-nearest neighbors(*in the whole index*) of the target vector to search.This means the second pass `knn` is executed on the whole index anyway, which is a current limitation.The final ranked list of results will have the first pass score(main query `q`) added to the second pass score(the approximated similarityFunction distance to the target vector to search) multiplied by a multiplicative factor(reRankWeight).--Details about using the ReRank Query Parser can be found in the xref:query-guide:query-re-ranking.adoc[Query Re-Ranking] section.====diff --git a/solr/solr-ref-guide/modules/query-guide/pages/query-re-ranking.adoc b/solr/solr-ref-guide/modules/query-guide/pages/query-re-ranking.adocindex 737ebef74af..598b966d115 100644--- a/solr/solr-ref-guide/modules/query-guide/pages/query-re-ranking.adoc+++ b/solr/solr-ref-guide/modules/query-guide/pages/query-re-ranking.adoc@@ -134,6 +134,9 @@ In the example below, the scores for the top 1000 documents matching the query "q=phone&rq={!rerank reRankQuery=$rqq reRankDocs=1000 reRankWeight=1 reRankOperator=replace}&rqq={!func v=div(1,sum(1,price))}----+xref:query-guide:dense-vector-search.adoc[Dense vector fields] can also be used for re-ranking via the xref:query-guide:function-queries.adoc#vectorsimilarity-function[vectorSimilarity()] function query.+This computes exact vector similarity only for the re-ranked candidate documents. See xref:query-guide:dense-vector-search.adoc#vector-reranking[Usage in Re-Ranking Query] for examples and details.+=== LTR Query Parser