IBX-9846: Added embedding visitor to allow search by embeddings

composer.json

@@ -16,7 +16,7 @@
         "php": "^7.4 || ^8.0",
         "ext-json": "*",
         "ext-xmlwriter": "*",
-        "ibexa/core": "~4.6.0@dev",
+        "ibexa/core": "dev-taxonomy-suggestions as 4.6.x-dev",
         "netgen/query-translator": "^1.0.2",
         "symfony/http-kernel": "^5.0",
         "symfony/dependency-injection": "^5.0",

src/contracts/Query/EmbeddingVisitor.php

@@ -0,0 +1,16 @@
+<?php
+
+/**
+ * @copyright Copyright (C) Ibexa AS. All rights reserved.
+ * @license For full copyright and license information view LICENSE file distributed with this source code.
+ */
+namespace Ibexa\Contracts\Solr\Query;
+
+use Ibexa\Contracts\Core\Repository\Values\Content\Query\Embedding;
+
+abstract class EmbeddingVisitor
+{
+    abstract public function canVisit(Embedding $embedding): bool;
+
+    abstract public function visit(Embedding $embedding, int $limit): string;
+}

src/lib/Query/Common/EmbeddingVisitor/Aggregate.php

@@ -0,0 +1,59 @@
+<?php
+
+/**
+ * @copyright Copyright (C) Ibexa AS. All rights reserved.
+ * @license For full copyright and license information view LICENSE file distributed with this source code.
+ */
+namespace Ibexa\Solr\Query\Common\EmbeddingVisitor;
+
+use Ibexa\Contracts\Core\Repository\Exceptions\NotImplementedException;
+use Ibexa\Contracts\Core\Repository\Values\Content\Query\Embedding;
+use Ibexa\Contracts\Solr\Query\EmbeddingVisitor;
+
+final class Aggregate extends EmbeddingVisitor
+{
+    /**
+     * @var iterable<\Ibexa\Contracts\Solr\Query\EmbeddingVisitor>
+     */
+    protected iterable $visitors = [];
+
+    /**
+     * @param \Ibexa\Contracts\Solr\Query\EmbeddingVisitor[] $visitors
+     */
+    public function __construct(iterable $visitors = [])
+    {
+        $this->visitors = $visitors;
+    }
+
+    public function canVisit(Embedding $embedding): bool
+    {
+        return $this->findVisitor($embedding) !== null;
+    }
+
+    /**
+     * Map field value to a proper Solr representation.
+     *
+     * @throws \Ibexa\Contracts\Core\Repository\Exceptions\NotImplementedException
+     */
+    public function visit(Embedding $embedding, int $limit): string
+    {
+        foreach ($this->visitors as $visitor) {
+            if ($visitor->canVisit($embedding)) {
+                return $visitor->visit($embedding, $limit);
+            }
+        }
+
+        throw new NotImplementedException('No visitor available for: ' . \get_class($embedding));
+    }
+
+    private function findVisitor(Embedding $embedding): ?EmbeddingVisitor
+    {
+        foreach ($this->visitors as $visitor) {
+            if ($visitor->canVisit($embedding)) {
+                return $visitor;
+            }
+        }
+
+        return null;
+    }
+}

src/lib/Query/Common/QueryConverter/NativeQueryConverter.php

@@ -6,9 +6,11 @@
  */
 namespace Ibexa\Solr\Query\Common\QueryConverter;
 
+use Ibexa\Contracts\Core\Repository\Values\Content\EmbeddingQuery;
 use Ibexa\Contracts\Core\Repository\Values\Content\Query;
 use Ibexa\Contracts\Solr\Query\AggregationVisitor;
 use Ibexa\Contracts\Solr\Query\CriterionVisitor;
+use Ibexa\Contracts\Solr\Query\EmbeddingVisitor;
 use Ibexa\Contracts\Solr\Query\SortClauseVisitor;
 use Ibexa\Solr\Query\FacetFieldVisitor;
 use Ibexa\Solr\Query\QueryConverter;
@@ -44,6 +46,8 @@ class NativeQueryConverter extends QueryConverter
      */
     private $aggregationVisitor;
 
+    private EmbeddingVisitor $embeddingVisitor;
+
     /**
      * Construct from visitors.
      *
@@ -55,26 +59,32 @@ public function __construct(
         CriterionVisitor $criterionVisitor,
         SortClauseVisitor $sortClauseVisitor,
         FacetFieldVisitor $facetBuilderVisitor,
-        AggregationVisitor $aggregationVisitor
+        AggregationVisitor $aggregationVisitor,
+        EmbeddingVisitor $embeddingVisitor
     ) {
         $this->criterionVisitor = $criterionVisitor;
         $this->sortClauseVisitor = $sortClauseVisitor;
         $this->facetBuilderVisitor = $facetBuilderVisitor;
         $this->aggregationVisitor = $aggregationVisitor;
+        $this->embeddingVisitor = $embeddingVisitor;
     }
 
     public function convert(Query $query, array $languageSettings = [])
     {
         $params = [
             'q' => '{!lucene}' . $this->criterionVisitor->visit($query->query),
-            'fq' => '{!lucene}' . $this->criterionVisitor->visit($query->filter),
+            'fq' => ['{!lucene}' . $this->criterionVisitor->visit($query->filter)],
             'sort' => $this->getSortClauses($query->sortClauses),
             'start' => $query->offset,
             'rows' => $query->limit,
             'fl' => '*,score,[shard]',
             'wt' => 'json',
         ];
 
+        if ($query instanceof EmbeddingQuery && $query->getEmbedding() !== null) {
+            $params['fq'][] = $this->embeddingVisitor->visit($query->getEmbedding(), $query->limit);
+        }
+
         $facetParams = $this->getFacetParams($query->facetBuilders);
         if (!empty($facetParams)) {
             $params['facet'] = 'true';

src/lib/Resources/config/container/solr.yml

@@ -100,6 +100,7 @@ services:
             - '@ibexa.solr.query.content.sort_clause_visitor.aggregate'
             - '@ibexa.solr.query.content.facet_builder_visitor.aggregate'
             - '@ibexa.solr.query.content.aggregation_visitor.dispatcher'
+            - '@Ibexa\Solr\Query\Common\EmbeddingVisitor\Aggregate'
 
     ibexa.solr.query_converter.location:
         class: Ibexa\Solr\Query\Common\QueryConverter\NativeQueryConverter
@@ -108,6 +109,7 @@ services:
             - '@ibexa.solr.query.location.sort_clause_visitor.aggregate'
             - '@ibexa.solr.query.location.facet_builder_visitor.aggregate'
             - '@ibexa.solr.query.location.aggregation_visitor.dispatcher'
+            - '@Ibexa\Solr\Query\Common\EmbeddingVisitor\Aggregate'
 
     Ibexa\Solr\Gateway\UpdateSerializer:
         arguments:

src/lib/Resources/config/container/solr/services.yml

@@ -28,6 +28,10 @@ services:
         arguments:
             $client: '@ibexa.solr.http_client'
 
+    Ibexa\Solr\Query\Common\EmbeddingVisitor\Aggregate:
+        arguments:
+            $visitors: !tagged ibexa.search.solr.query.content.embedding.visitor
+
     # Note: services tagged with 'ibexa.search.solr.query.content.criterion.visitor'
     # are registered to this one using compilation pass
     ibexa.solr.query.content.criterion_visitor.aggregate:

src/lib/Resources/config/solr/managed-schema.xml

@@ -0,0 +1,169 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!DOCTYPE schema [
+<!ENTITY langfields SYSTEM "language-fieldtypes.xml">
+<!ENTITY customfields SYSTEM "custom-fields-types.xml">
+]>
+<!--
+This is the Solr schema file. This file should be named "schema.xml" and should
+be in the conf directory under the solr home (i.e. ./solr/conf/schema.xml by
+default) or located where the classloader for the Solr webapp can find it.
+
+It provides the default types and definitions for a functional Solr based
+search in eZ Publish 5. You may extend it with your own definitions, but you
+should not remove or drastically change the existing definitions.
+-->
+
+<schema name="eZ Publish 5 base schema" version="1.5">
+    <!--
+    language specific field types are included here, there should be at least
+    a field type with the name "text" be defined"
+    Included in the eZ platform distribution are configurations for various
+    languages, including additional files like stopwords or other features
+    under the directory "solr.languages"
+    -->
+    &langfields;
+
+    <!--
+    custom field types and fields are included from a separate file to ease upgrades
+    -->
+    &customfields;
+
+    <!--
+      Default types by Solr. Will be reused for dynamic fields.
+    -->
+    <fieldType name="string" class="solr.TextField" sortMissingLast="true">
+      <analyzer type="index">
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true" sortMissingLast="true">
+        <analyzer type="index">
+            <tokenizer class="solr.KeywordTokenizerFactory"/>
+            <filter class="solr.LowerCaseFilterFactory"/>
+        </analyzer>
+        <analyzer type="query">
+            <tokenizer class="solr.KeywordTokenizerFactory"/>
+            <filter class="solr.LowerCaseFilterFactory"/>
+        </analyzer>
+    </fieldType>
+
+    <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+    <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
+    <!--
+      Numeric field types that index values using KD-trees.
+      Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
+    -->
+    <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+    <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+    <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+    <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
+
+    <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
+    <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+    <fieldType name="random" class="solr.RandomSortField" indexed="true"/>
+
+    <fieldType name="identifier" class="solr.StrField" sortMissingLast="true" />
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" multiValued="false"/>
+    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+    <fieldtype name="binary" class="solr.BinaryField"/>
+    <fieldType name="int" class="solr.IntPointField" docValues="true"/>
+    <fieldType name="float" class="solr.FloatPointField" docValues="true"/>
+    <fieldType name="long" class="solr.LongPointField" docValues="true"/>
+    <fieldType name="double" class="solr.DoublePointField" docValues="true"/>
+    <fieldType name="date" class="solr.DatePointField" docValues="true"/>
+
+    <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
+    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+    <fieldType name="location" class="solr.LatLonPointSpatialField" sortMissingLast="true"/>
+
+    <!-- for 1536-dim models (ada-002 & 3-small) -->
+    <fieldType name="vector_1536"
+               class="solr.DenseVectorField"
+               vectorDimension="1536"
+               similarityFunction="cosine"
+               indexed="true"
+               stored="true" />
+
+    <!-- for the 3072-dim model (3-large) -->
+    <fieldType name="vector_3072"
+               class="solr.DenseVectorField"
+               vectorDimension="3072"
+               similarityFunction="cosine"
+               indexed="true"
+               stored="true"/>
+
+    <!--
+      Required ID field.
+    -->
+    <field name="id" type="string" indexed="true" stored="true" required="true"/>
+
+    <!--
+      Always contains the date a document was added to the index. Might be
+      useful.
+    -->
+    <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
+
+    <!--
+      Points to the root document of a block of nested documents. Required for nested document support.
+    -->
+    <field name="_root_" type="string" indexed="true" stored="true" required="false"/>
+
+    <field name="document_type_id" type="string" indexed="true" stored="true" required="true"/>
+
+    <!--
+      Dynamic field definitions.  If a field name is not found, dynamicFields
+      will be used if the name matches any of the patterns.  RESTRICTION: the
+      glob-like pattern in the name attribute must have a "*" only at the start
+      or the end.  EXAMPLE:  name="*_i" will match any field ending in _i (like
+      myid_i, z_i) Longer patterns will be matched first.  if equal size
+      patterns both match, the first appearing in the schema will be used.
+    -->
+    <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
+    <dynamicField name="*_mi" type="int" indexed="true" stored="true" multiValued="true"/>
+    <dynamicField name="*_id" type="identifier" indexed="true" stored="true"/>
+    <dynamicField name="*_mid" type="identifier" indexed="true" stored="true" multiValued="true"/>
+    <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
+    <dynamicField name="*_ms" type="string" indexed="true" stored="true" multiValued="true"/>
+    <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+    <dynamicField name="*_t" type="text" indexed="true" stored="true" multiValued="true" omitNorms="false"/>
+    <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+    <dynamicField name="*_mb" type="boolean" indexed="true" stored="true" multiValued="true"/>
+    <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+    <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+    <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+    <dynamicField name="*_gl" type="location" indexed="true" stored="true"/>
+    <dynamicField name="*_gl_0_coordinate" type="double" indexed="true" stored="true"/>
+    <dynamicField name="*_gl_1_coordinate" type="double" indexed="true" stored="true"/>
+
+   <!--
+        This field is required to allow random sorting
+    -->
+    <dynamicField name="random*" type="random" indexed="true" stored="false"/>
+
+    <!--
+        This field is required for Embeddings
+    -->
+    <!-- 1536-dim suffix for ada-002 -->
+    <dynamicField name="*_ada002_dv" type="vector_1536"/>
+
+    <!-- 1536-dim suffix for 3-small -->
+    <dynamicField name="*_3small_dv" type="vector_1536"/>
+
+    <!-- 3072-dim suffix for 3-large -->
+    <dynamicField name="*_3large_dv" type="vector_3072"/>
+
+    <!--
+      This field is required since Solr 4
+    -->
+    <field name="_version_" type="long" indexed="true" stored="true" multiValued="false" />
+
+  <uniqueKey>id</uniqueKey>
+</schema>