# Should + vector search

**URL:** <https://forum.opensearch.org/t/should-vector-search/16636>\
**Category:** OpenSearch\
**Tags:** query-workbench\
**Created:** [November 11, 2023, 6:19pm UTC](https://forum.opensearch.org/t/should-vector-search/16636 "2023-11-11T18:19:11Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ardito.bryan](https://sea1.discourse-cdn.com/flex019/user_avatar/forum.opensearch.org/ardito.bryan/32/6420_2.png) [@ardito.bryan](https://forum.opensearch.org/u/ardito.bryan)\
**Post date:** [November 11, 2023, 6:19pm UTC](https://forum.opensearch.org/t/should-vector-search/16636/1 "2023-11-11T18:19:11Z")

</div>

Suppose my index has:

- A vector field called “text\_encoded”
- A field called “field1”, that can contain one or more of the following classes: “A”, “B”, “C” as list (ex. “field1” : [“A”], or “field1” : [“A”, “C”])

I would like to write an OpenSearch query that can:

- select the samples with field1 classes containing either “A” OR “C”
- return similarity scores only

If I use the “should” instruction, it returns relevance scores instead.  
How can I only make it return cosine similarity scores?

Thank you