DOCSP-48385 Make Atlas Vector Search page

snooty.toml

@@ -31,3 +31,4 @@ driver-short = "Node.js driver"
 mdb-server = "MongoDB Server"
 min-node-version = "v16.20.1"
 stable-api = "Stable API"
+vector-search = "Atlas Vector Search"

source/atlas-vector-search.txt

@@ -0,0 +1,136 @@
+.. _node-atlas-vector-search:
+
+================================
+Run an Atlas Vector Search Query
+================================
+
+.. facet::
+   :name: genre
+   :values: reference
+
+.. meta::
+   :keywords: code example, semantic, nearest
+
+.. contents:: On this page
+   :local:
+   :backlinks: none
+   :depth: 2
+   :class: singlecol
+
+Overview
+--------
+
+In this guide, you can learn how to use the Atlas Vector Search feature
+in the {+driver-short+}. 
+
+You can use {+vector-search+} to perform a vector search on your data stored in
+Atlas. Vector search allows you to query your data based on semantic meaning
+rather than just keyword matches, which helps you retrieve more relevant search
+results. It enables your AI-powered applications to support use cases such as
+semantic search, hybrid search, and generative search, including
+Retrieval-Augmented Generation (RAG).
+
+To learn more about {+vector-search+}, see the :atlas:`{+vector-search+}
+</atlas-vector-search/vector-search-overview/>` guides in the MongoDB Atlas
+documentation.
+
+.. important:: Feature Compatibility
+
+   To learn what 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
+-----------------------
+
+To use this feature, you must create a vector search index and index your
+vector embeddings. To learn about how to programmatically create a
+vector search index, see the :atlas:`Create an Atlas Vector Search Index
+</atlas-vector-search/vector-search-type/#create-an-atlas-vector-search-index>` section in the
+Atlas documentation. To learn more about vector embeddings, see
+:atlas:`How to Create Vector Embeddings
+</atlas-vector-search/create-embeddings/>` in the Atlas documentation.
+
+After you create a vector search index on your vector embeddings, you
+can reference this index in your pipeline stage, as shown in the
+following example.
+
+Sample Data
+~~~~~~~~~~~
+
+The example on this page shows how to build an aggregation pipeline that uses the
+``$vectorSearch`` stage to perform a vector search on the
+``sample_mflix.embedded_movies`` collection in the :atlas:`Atlas sample datasets
+</sample-data>`.
+
+To learn how to create a free MongoDB Atlas cluster and load the sample datasets, see the
+:atlas:`Get Started with Atlas </getting-started>` guide.
+
+Vector Search Example
+~~~~~~~~~~~~~~~~~~~~~
+
+You can perform a vector search query by using the ``$vectorSearch`` stage
+in an :ref:`aggregation pipeline <node-aggregation>`. To perform a vector
+search on a collection, you must first have a collection with a field that contains
+vector embeddings and a vector search index that covers that field. 
+
+In the following example, the aggregation pipeline searches the ``plot``  field of each
+document in the collection for text semantically related to the term "time travel". The
+``queryVector`` field in the ``$vectorSearch`` pipeline is the vector representation of
+your query.
+
+.. io-code-block::
+   :copyable: true
+
+   .. input:: /includes/aggregation/atlas-vector-search-example.js
+      :language: javascript
+      :dedent:
+
+   .. output:: 
+      :language: json
+      :visible: false
+
+      '{"plot":"A reporter, learning of time travelers visiting 20th century disasters, tries to change the history they know by averting upcoming disasters.","title":"Thrill Seekers","score":0.7892671227455139}'
+      '{"plot":"At the age of 21, Tim discovers he can travel in time and change what happens and has happened in his own life. His decision to make his world a better place by getting a girlfriend turns out not to be as easy as you might think.","title":"About Time","score":0.7843604683876038}'
+      '{"plot":"Hoping to alter the events of the past, a 19th century inventor instead travels 800,000 years into the future, where he finds humankind divided into two warring races.","title":"The Time Machine","score":0.7801066637039185}'
+      `{"plot":"After using his mother's newly built time machine, Dolf gets stuck involuntary in the year 1212. He ends up in a children's crusade where he confronts his new friends with modern techniques...","title":"Crusade in Jeans","score":0.7789170742034912}`
+      '{"plot":"An officer for a security agency that regulates time travel, must fend for his life against a shady politician who has a tie to his past.","title":"Timecop","score":0.7771612405776978}'
+      '{"plot":"A time-travel experiment in which a robot probe is sent from the year 2073 to the year 1973 goes terribly wrong thrusting one of the project scientists, a man named Nicholas Sinclair into a...","title":"A.P.E.X.","score":0.7730885744094849}'
+      `{"plot":"Agent J travels in time to M.I.B.'s early days in 1969 to stop an alien from assassinating his friend Agent K and changing history.","title":"Men in Black 3","score":0.7712380886077881}`
+      '{"plot":"Bound by a shared destiny, a teen bursting with scientific curiosity and a former boy-genius inventor embark on a mission to unearth the secrets of a place somewhere in time and space that exists in their collective memory.","title":"Tomorrowland","score":0.7669923901557922}'
+      '{"plot":"With the help of his uncle, a man travels to the future to try and bring his girlfriend back to life.","title":"Love Story 2050","score":0.7649372816085815}'
+      '{"plot":"A dimension-traveling wizard gets stuck in the 21st century because cell-phone radiation interferes with his magic. With his home world on the brink of war, he seeks help from a jaded ...","title":"The Portal","score":0.7640786170959473}'
+
+This query uses the ``$vectorSearch`` stage to:
+
+- Perform an Approximate Nearest Neighbor (ANN) vector search
+
+- Search for the specified term in the ``plot_embedding`` field
+
+- Set the number of nearest neighbors used in the search to 150 by using the
+  ``numCandidates`` option
+
+- Return a maximum of 10 documents from the query using the ``limit`` option
+
+It uses the ``$project`` stage to:
+
+- Only include the movie ``plot`` and ``title`` fields in the results
+
+- Add a ``score`` field to show the relevance of each result to the search term
+
+Additional Information
+----------------------
+
+To see more Atlas Vector Search tutorials for the {+driver-short+}, see the :atlas:`Atlas
+Vector Search tutorials </atlas-vector-search/tutorials/>` in the Atlas documentation.
+
+To learn more about the syntax of the ``$vectorSearch`` pipeline stage,
+see the Syntax and Fields sections of the 
+:atlas:`Create and Run Queries </atlas-vector-search/vector-search-stage/#syntax>`
+guide in the Atlas Vector Search section of the Atlas documentation.
+
+API Documentation
+~~~~~~~~~~~~~~~~~
+
+To learn more about the ``aggregate()`` method, see `aggregate()
+<{+api+}/classes/Collection.html#aggregate>`__ in the API documentation.