From 09d9ba8af89e5aca7f3c6da910151f27110ce941 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 f3b1b6d4a..730760a43 100644
--- a/collection.xconf
+++ b/collection.xconf
@@ -2,13 +2,16 @@
 <collection xmlns="http://exist-db.org/collection-config/1.0">
     <index xmlns:xs="http://www.w3.org/2001/XMLSchema">
         <!-- Lucene index configuration -->
-        <lucene>
+        <lucene vector-store="db">
             <analyzer class="org.apache.lucene.analysis.standard.StandardAnalyzer"/>
             <text index="no" qname="persName">
                 <!-- start required facets and fields -->
                 <facet dimension="hsg-category" expression="'department'"/>
                 <facet dimension="hsg-publication" expression="'pocom'"/>
                 <field name="hsg-fulltext"/>
+                <vector-field name="hsg-embedding"
+                    dimension="384" similarity="cosine"
+                    embedding="local" model="all-MiniLM-L6-v2"/>
                 <field expression="'/departmenthistory/people/' || parent::person/id" name="hsg-url"/>
                 <!-- end required facets and fields -->
             </text>