From f3a907beadcf7235e94aed7e956a8d37fd27e4cb Mon Sep 17 00:00:00 2001
From: duncdrum <d.paterson@me.com>
Date: Tue, 22 Sep 2026 14:50:40 +0200
Subject: [PATCH] feat: add hsg-embedding vector field for hybrid search

Hybrid search ranks a hit only when that node stores this vector beside
hsg-fulltext. The vector uses the keyword field's expression when it has
one. Where that field is limited by an if test, the same test gates the
vector, because vector-field does not read if.
---
 collection.xconf | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/collection.xconf b/collection.xconf
index ac7587ee..89d3f153 100644
--- a/collection.xconf
+++ b/collection.xconf
@@ -1,13 +1,16 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <collection xmlns="http://exist-db.org/collection-config/1.0">
     <index xmlns:xs="http://www.w3.org/2001/XMLSchema">
-        <lucene>
+        <lucene vector-store="db">
             <analyzer class="org.apache.lucene.analysis.standard.StandardAnalyzer"/>
             <text qname="visit">
                 <!-- start required facets and fields -->
                 <facet dimension="hsg-category" expression="'department'"/>
                 <facet dimension="hsg-publication" expression="'visits'"/>
                 <field expression="visitor, description, from" name="hsg-fulltext"/>
+                <vector-field name="hsg-embedding" expression="visitor, description, from"
+                    dimension="384" similarity="cosine"
+                    embedding="local" model="all-MiniLM-L6-v2"/>
                 <field expression="'/departmenthistory/visits/' || year-from-date(./start-date)"
                     name="hsg-url"/>
                 <!-- end required facets and fields -->