DOCSP-34578 Vector search index (#598)

* DOCSP-34578 vector search index

* DOCSP-34578 add ref

* DOCSP-34578 nit fix

* DOCSP-34578 LT feedback

* DOCSP-34578 add note

* DOCSP-34578 link to atlas

Author: jocelyn-mendez1

source/indexes.txt

@@ -83,7 +83,16 @@ Create an Index
 Create an Atlas Search Index
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-To create an Atlas Search index, see :ref:`compass-create-search-index`.
+Atlas Search indexes let you query data in `Atlas Search
+<https://www.mongodb.com/docs/atlas/atlas-search/>`__. For more
+information, see :ref:`compass-create-search-index`.
+
+Create an Atlas Vector Search Index
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Atlas Vector Search indexes enable you to index vector data *and* other data 
+types, which facilitates semantic searches on the indexed fields. For more
+information, see :ref:`compass-create-vector-search`. 
 
 .. _compass-wildcard-index:
 
@@ -168,3 +177,4 @@ Limitations
    :titlesonly:
 
    /indexes/create-search-index
+   /indexes/create-vector-search-index

source/indexes/create-vector-search-index.txt

@@ -0,0 +1,145 @@
+.. _compass-create-vector-search:
+
+===================================
+Create an Atlas Vector Search Index
+===================================
+
+.. contents:: On this page
+   :local:
+   :backlinks: none
+   :depth: 1
+   :class: singlecol
+
+.. versionadded:: 1.42.1
+
+You can create :atlas:`Atlas Vector Search indexes 
+</atlas-vector-search/vector-search-overview/>` using |compass|. These indexes 
+enable you to index vector data *and* other data types, which facilitates 
+semantic searches on the indexed fields. Atlas Vector Search indexes support 
+indexing vector data by identifying the most similar vectors. The index 
+determines similarity by calculating the distance between the query vector 
+and the vectors stored in the index.
+
+About this Task
+---------------
+
+To create an Atlas Search index, your deployment must align with one of the 
+following cases:
+
+- A deployment hosted on `MongoDB Atlas <https://www.mongodb.com/docs/atlas/>`__ and
+  have an Atlas cluster tier of M10 or higher.
+
+- A local deployment that is set up using the `Atlas CLI
+  <https://www.mongodb.com/docs/atlas/cli/stable/atlas-cli-deploy-local/>`__.
+
+Additionally, your deployment must run MongoDB version 7.0 or later.
+
+Steps
+-----
+
+.. procedure::
+   :style: normal
+   
+   .. step:: Open the index creation dialog
+
+      From the :ref:`Indexes <indexes-tab>` tab, click the
+      :guilabel:`Create` button and then click :guilabel:`Search Index`.
+
+   .. step:: Specify a name for the index
+
+   .. step:: Select the Atlas Search Index type
+
+      Select :guilabel:`Vector Search`.
+
+   .. step:: Provide the Atlas Vector Search Index configurations
+
+      You must initially provide the following default vector search index 
+      configurations. You can modify the configurations later.
+
+      .. list-table::
+         :header-rows: 1
+         :widths: 20 10 70
+
+         * - Field
+           - Type
+           - Description
+
+         * - ``path``
+           - string
+           - The field name to index.
+        
+         * - ``numDimensions``
+           - int 
+           - The number of vector dimensions, which Atlas Search enforces at index- and 
+             query-time. This value can't be greater than 2048.
+        
+         * - ``similarity``
+           - string
+           - The vector similarity function used to search for the top K-nearest neighbors.
+             Select from the following functions:
+
+             .. list-table::
+                :header-rows: 1
+                :widths: 50 50
+
+                * - Function
+                  - Description
+
+                * - ``euclidean``
+                  - A function that measures the distance between ends of vectors. This function 
+                    allows you to measure similarity based on varying dimensions. 
+
+                * - ``cosine``
+                  - A function that measures similarity based on the angle between vectors. This 
+                    function allows you to measure similarity that isn't scaled by magnitude. 
+                    
+                    You can't use zero magnitude vectors with cosine. To measure cosine similarity, 
+                    we recommend that you normalize your vectors and use dotProduct instead.
+
+                * - ``dotProduct``
+                  -  A function that measures similarly to cosine, but takes into account the 
+                     magnitude of the vector. This function allows you to efficiently measure 
+                     similarity based on both angle and magnitude. To use dotProduct, you must 
+                     normalize the vector to unit length at index- and query-time.
+
+   .. step:: Click :guilabel:`Create Search Index`
+
+Example
+-------
+
+The following example definition uses the ``sample_mflix.embedded_movies`` collection 
+and indexes the ``plot_embedding`` field to create an Atlas Vector Search index: 
+
+.. code-block:: javascript
+
+   {
+      "fields": [ {
+         "type": "vector",
+         "path": "plot_embedding",
+         "numDimensions": 1536,
+         "similarity": "euclidean"
+      } ]
+   }
+
+Results
+-------
+
+To view the status of your created index, go to the :guilabel:`Indexes`
+tab and set the toggle at the top-right to :guilabel:`Search Indexes`.
+
+The :guilabel:`Status` column indicates the status of the index. When
+the status is :guilabel:`Ready`, your index is ready to use.
+
+For more information on search index statuses, see
+:ref:`search-index-status`.
+
+Learn More
+----------
+
+- :ref:`compass-indexes`
+
+- :atlas:`How to Index Fields for Vector Search 
+  </atlas-vector-search/vector-search-type/#std-label-avs-types-vector-search>`
+
+- :atlas:`How to Perform Semantic Search Against Data in Your Atlas Cluster
+  </atlas-vector-search/vector-search-tutorial/>`