DOCSP-51350: Vector search queries

source/atlas-vector-search.txt

@@ -2,4 +2,127 @@
 
 ================================
 Run an Atlas Vector Search Query
-================================
+================================
+
+.. facet::
+   :name: genre
+   :values: reference
+
+.. meta::
+   :keywords: full text, text analyzer, meta, pipeline, scoring, Lucene, AI, artificial intelligence, code example, semantic, nearest
+   :description: Learn about how to use Atlas Vector Search in the {+driver-short+}.
+
+.. contents:: On this page
+   :local:
+   :backlinks: none
+   :depth: 2
+   :class: singlecol
+
+Overview
+--------
+
+In this guide, you can learn how to use the {+driver-short+} to perform
+:atlas:`Atlas Vector Search </atlas-vector-search/vector-search-overview/>`
+queries. The ``Aggregates`` builders class provides the
+the ``vectorSearch()`` helper method, which you can use to
+create a :atlas:`$vectorSearch </atlas-vector-search/vector-search-stage/>`
+pipeline stage. 
+
+.. important:: Feature Compatibility
+
+   To learn which versions of MongoDB Atlas support this feature, see
+   :atlas:`Limitations </atlas-vector-search/vector-search-stage/#limitations>`
+   in the MongoDB Atlas documentation.
+
+Perform a Vector Search
+-----------------------
+
+Before you can perform Atlas Vector Search queries, you must create an Atlas Vector Search
+index on your collection. To learn about how to programmatically create a
+vector search index, see the :ref:`kotlin-sync-search-avs-indexes` guide.
+
+Then, you can run an Atlas Vector Search query by using the
+``vectorSearch()`` method in an aggregation pipeline. This
+method accepts the following parameters:
+
+- ``path``: The field to search
+- ``queryVector``: The vector embedding that represents your search query
+- ``indexName``: The name of the Atlas Vector Search index to use
+- ``limit``: The maximum number of results to return
+- ``options``: *(Optional)* A set of options that you can use to configure the
+  vector search query
+
+Vector Search Example
+~~~~~~~~~~~~~~~~~~~~~
+
+The following example performs an Atlas Vector Search query on the ``plot_embedding``
+vector field and prints the ``title`` value of the first five results:
+
+.. io-code-block::
+
+   .. input:: /includes/vector-search.kt
+      :start-after: start-vs
+      :end-before: end-vs
+      :language: kotlin
+      :dedent:
+
+   .. output::
+      :visible: false
+
+      {"title": "Berserk: The Golden Age Arc I - The Egg of the King"}
+      {"title": "Rollerball"}
+      {"title": "After Life"}
+      {"title": "What Women Want"}
+      {"title": "Truth About Demons"}
+
+.. tip:: Query Vector Type
+
+   The preceding example creates an instance of ``BinaryVector`` to
+   serve as the query vector, but you can also create a ``List`` of
+   ``Double`` instances. However, we recommend that you use the
+   ``BinaryVector`` type to improve storage efficiency.
+
+The following example shows how to run the aggregation and print
+the vector search meta-score from the result of the preceding
+aggregation pipeline:
+
+.. io-code-block::
+
+   .. input:: /includes/vector-search.kt
+      :start-after: start-vs-score
+      :end-before: end-vs-score
+      :language: kotlin
+      :dedent:
+
+   .. output::
+      :visible: false
+
+      Title: Berserk: The Golden Age Arc I - The Egg of the King, Score: 0.49899211525917053
+      Title: Rollerball, Score: 0.4976102113723755
+      Title: After Life, Score: 0.4965665936470032
+      Title: What Women Want, Score: 0.49622756242752075
+      Title: Truth About Demons, Score: 0.49614521861076355
+
+.. tip:: Vector Search Tutorials
+
+   To view more tutorials that show how to run Atlas Vector Search queries,
+   see the :atlas:`Atlas Vector Search Tutorials </atlas-vector-search/tutorials>`
+   in the MongoDB Atlas documentation.
+
+API Documentation
+-----------------
+
+To learn more about the methods and types mentioned in this
+guide, see the following API documentation:
+
+- `Aggregates.vectorSearch()
+  <{+core-api+}/client/model/Aggregates.html#vectorSearch(com.mongodb.client.model.search.FieldSearchPath,java.lang.Iterable,java.lang.String,long,com.mongodb.client.model.search.VectorSearchOptions)>`__
+
+- `FieldSearchPath
+  <{+core-api+}/client/model/search/FieldSearchPath.html>`__
+
+- `VectorSearchOptions
+  <{+core-api+}/client/model/search/VectorSearchOptions.html>`__
+
+- `Projections.metaVectorSearchScore()
+  <{+core-api+}/client/model/Projections.html#metaVectorSearchScore(java.lang.String)>`__

source/includes/vector-search.kt

@@ -0,0 +1,85 @@
+package org.example
+
+import com.mongodb.ConnectionString
+import com.mongodb.kotlin.client.MongoClient
+import com.mongodb.MongoClientSettings
+import com.mongodb.client.model.Aggregates.project
+import com.mongodb.client.model.Aggregates.vectorSearch
+import com.mongodb.client.model.search.FieldSearchPath
+import com.mongodb.client.model.Projections
+import com.mongodb.client.model.search.SearchPath.fieldPath
+import org.bson.BinaryVector
+import org.bson.conversions.Bson
+import com.mongodb.client.model.search.VectorSearchOptions.approximateVectorSearchOptions
+import org.bson.Document
+
+fun main() {
+    val uri = "<connection string>"
+
+    val settings = MongoClientSettings.builder()
+        .applyConnectionString(ConnectionString(uri))
+        .retryWrites(true)
+        .build()
+
+    val mongoClient = MongoClient.create(settings)
+    val database = mongoClient.getDatabase("sample_mflix")
+    val collection = database.getCollection<Document>("embedded_movies")
+
+    // start-vs
+    val vectorValues = FloatArray(1536) { i -> (i % 10).toFloat() * 0.1f }
+    val queryVector = BinaryVector.floatVector(vectorValues)
+    val indexName = "<vector search index>"
+
+    // Specifies the path of the field to search
+    val fieldSearchPath: FieldSearchPath = fieldPath("plot_embedding")
+
+    // Creates the vector search pipeline stage with numCandidates and limit
+    val pipeline: List<Bson> = listOf(
+        vectorSearch(
+            fieldSearchPath,
+            queryVector,
+            indexName,
+            5L, 
+            approximateVectorSearchOptions(150)
+        ),
+        project(
+            Projections.fields(
+                Projections.excludeId(),
+                Projections.include("title")
+            )
+        )
+    )
+
+    val results = collection.aggregate(pipeline)
+
+    results.forEach { doc ->
+        println(doc.toJson())
+    }
+    // end-vs
+
+    // start-vs-score
+    val pipeline: List<Bson> = listOf(
+        vectorSearch(
+            fieldSearchPath,
+            queryVector,
+            indexName,
+            5L, // limit parameter
+            approximateVectorSearchOptions(150)
+        ),
+        project(
+            Projections.fields(
+                Projections.excludeId(),
+                Projections.include("title"),
+                Projections.metaVectorSearchScore("score")
+            )
+        )
+    )
+
+    val results = collection.aggregate(pipeline)
+
+    results.forEach { doc ->
+        val score = doc.getDouble("vectorSearchScore")
+        println("Title: ${doc.getString("title")}, Score: ${doc.getDouble("score")}")
+    }
+    // end-vs-score
+}