PHPORM-277 Add Builder::vectorSearch()

src/Eloquent/Builder.php

@@ -8,6 +8,7 @@
 use Illuminate\Database\Eloquent\Collection;
 use Illuminate\Database\Eloquent\Model;
 use MongoDB\BSON\Document;
+use MongoDB\Builder\Type\QueryInterface;
 use MongoDB\Builder\Type\SearchOperatorInterface;
 use MongoDB\Driver\CursorInterface;
 use MongoDB\Driver\Exception\WriteException;
@@ -101,6 +102,28 @@ public function search(
         return $this->model->hydrate($results->all());
     }
 
+    /**
+     * Performs a full-text search of the field or fields in an Atlas collection.
+     * NOTE: $search is only available for MongoDB Atlas clusters, and is not available for self-managed deployments.
+     *
+     * @see https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-stage/
+     *
+     * @return Collection<int, TModel>
+     */
+    public function vectorSearch(
+        string $index,
+        array|string $path,
+        array $queryVector,
+        int $limit,
+        bool $exact = false,
+        QueryInterface|array $filter = [],
+        int|null $numCandidates = null,
+    ): Collection {
+        $results = $this->toBase()->vectorSearch($index, $path, $queryVector, $limit, $exact, $filter, $numCandidates);
+
+        return $this->model->hydrate($results->all());
+    }
+
     /** @inheritdoc */
     public function update(array $values, array $options = [])
     {

src/Query/Builder.php

@@ -25,6 +25,7 @@
 use MongoDB\BSON\UTCDateTime;
 use MongoDB\Builder\Search;
 use MongoDB\Builder\Stage\FluentFactoryTrait;
+use MongoDB\Builder\Type\QueryInterface;
 use MongoDB\Builder\Type\SearchOperatorInterface;
 use MongoDB\Driver\Cursor;
 use Override;
@@ -1532,6 +1533,40 @@ public function search(
         return $this->aggregate()->search(...$args)->get();
     }
 
+    /**
+     * Performs a full-text search of the field or fields in an Atlas collection.
+     * NOTE: $search is only available for MongoDB Atlas clusters, and is not available for self-managed deployments.
+     *
+     * @see https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-stage/
+     *
+     * @return Collection<object|array>
+     */
+    public function vectorSearch(
+        string $index,
+        array|string $path,
+        array $queryVector,
+        int $limit,
+        bool $exact = false,
+        QueryInterface|array|null $filter = null,
+        int|null $numCandidates = null,
+    ): Collection {
+        // Forward named arguments to the vectorSearch stage, skip null values
+        $args = array_filter([
+            'index' => $index,
+            'limit' => $limit,
+            'path' => $path,
+            'queryVector' => $queryVector,
+            'exact' => $exact,
+            'filter' => $filter,
+            'numCandidates' => $numCandidates,
+        ], fn ($arg) => $arg !== null);
+
+        return $this->aggregate()
+            ->vectorSearch(...$args)
+            ->addFields(vectorSearchScore: ['$meta' => 'vectorSearchScore'])
+            ->get();
+    }
+
     /**
      * Performs an autocomplete search of the field using an Atlas Search index.
      * NOTE: $search is only available for MongoDB Atlas clusters, and is not available for self-managed deployments.

tests/AtlasSearchTest.php

@@ -5,23 +5,31 @@
 use Illuminate\Database\Eloquent\Collection as EloquentCollection;
 use Illuminate\Support\Collection as LaravelCollection;
 use Illuminate\Support\Facades\Schema;
+use MongoDB\Builder\Query;
 use MongoDB\Builder\Search;
 use MongoDB\Collection as MongoDBCollection;
 use MongoDB\Driver\Exception\ServerException;
 use MongoDB\Laravel\Schema\Builder;
 use MongoDB\Laravel\Tests\Models\Book;
 
+use function array_map;
 use function assert;
+use function mt_getrandmax;
+use function rand;
+use function range;
+use function srand;
 use function usleep;
 use function usort;
 
 class AtlasSearchTest extends TestCase
 {
+    private array $vectors;
+
     public function setUp(): void
     {
         parent::setUp();
 
-        Book::insert([
+        Book::insert($this->addVector([
             ['title' => 'Introduction to Algorithms'],
             ['title' => 'Clean Code: A Handbook of Agile Software Craftsmanship'],
             ['title' => 'Design Patterns: Elements of Reusable Object-Oriented Software'],
@@ -42,7 +50,7 @@ public function setUp(): void
             ['title' => 'Understanding Machine Learning: From Theory to Algorithms'],
             ['title' => 'Deep Learning'],
             ['title' => 'Pattern Recognition and Machine Learning'],
-        ]);
+        ]));
 
         $collection = $this->getConnection('mongodb')->getCollection('books');
         assert($collection instanceof MongoDBCollection);
@@ -66,8 +74,9 @@ public function setUp(): void
 
             $collection->createSearchIndex([
                 'fields' => [
-                    ['type' => 'vector', 'numDimensions' => 16, 'path' => 'vector16', 'similarity' => 'cosine'],
+                    ['type' => 'vector', 'numDimensions' => 4, 'path' => 'vector4', 'similarity' => 'cosine'],
                     ['type' => 'vector', 'numDimensions' => 32, 'path' => 'vector32', 'similarity' => 'euclidean'],
+                    ['type' => 'filter', 'path' => 'title'],
                 ],
             ], ['name' => 'vector', 'type' => 'vectorSearch']);
         } catch (ServerException $e) {
@@ -131,7 +140,7 @@ public function testGetIndexes()
             ],
             [
                 'name' => 'vector',
-                'columns' => ['vector16', 'vector32'],
+                'columns' => ['vector4', 'vector32', 'title'],
                 'type' => 'vectorSearch',
                 'primary' => false,
                 'unique' => false,
@@ -199,4 +208,57 @@ public function testDatabaseBuilderAutocomplete()
             'Modern Operating Systems',
         ], $results->all());
     }
+
+    public function testDatabaseBuilderVectorSearch()
+    {
+        $results = $this->getConnection('mongodb')->table('books')
+            ->vectorSearch(
+                index: 'vector',
+                path: 'vector4',
+                queryVector: $this->vectors[7], // This is an exact match of the vector
+                limit: 4,
+                exact: true,
+            );
+
+        self::assertInstanceOf(LaravelCollection::class, $results);
+        self::assertCount(4, $results);
+        self::assertSame('The Art of Computer Programming', $results->first()['title']);
+        self::assertSame(1.0, $results->first()['vectorSearchScore']);
+    }
+
+    public function testEloquentBuilderVectorSearch()
+    {
+        $results = Book::vectorSearch(
+            index: 'vector',
+            path: 'vector4',
+            queryVector: $this->vectors[7],
+            limit: 5,
+            numCandidates: 15,
+            // excludes the exact match
+            filter: Query::query(
+                title: Query::ne('The Art of Computer Programming'),
+            ),
+        );
+
+        self::assertInstanceOf(EloquentCollection::class, $results);
+        self::assertCount(5, $results);
+        self::assertInstanceOf(Book::class, $results->first());
+        self::assertNotSame('The Art of Computer Programming', $results->first()->title);
+        self::assertSame('The Mythical Man-Month: Essays on Software Engineering', $results->first()->title);
+        self::assertThat(
+            $results->first()->vectorSearchScore,
+            self::logicalAnd(self::isType('float'), self::greaterThan(0.9), self::lessThan(1.0)),
+        );
+    }
+
+    /** Generate random vectors */
+    private function addVector(array $items): array
+    {
+        srand(1);
+        foreach ($items as &$item) {
+            $this->vectors[] = $item['vector4'] = array_map(fn () => rand() / mt_getrandmax(), range(0, 3));
+        }
+
+        return $items;
+    }
 }