Update vector-search.md

Author: jcodella

articles/cosmos-db/mongodb/vcore/vector-search.md

@@ -52,10 +52,17 @@ To create a vector index, use the following `createIndexes` template:
 | `index_name` | string | Unique name of the index. |
 | `path_to_property` | string | Path to the property that contains the vector. This path can be a top-level property or a dot notation path to the property. If a dot notation path is used, then all the nonleaf elements can't be arrays. |
 | `kind` | string | Type of vector index to create. Currently, `vector-ivf` is the only supported index option. |
-| `numLists` | integer | This integer is the number of clusters that the inverted file (IVF) index uses to group the vector data. We recommend that `numLists` is set to `rowCount()/1000` for up to 1 million rows and to `sqrt(rowCount)` for more than 1 million rows. |
+| `numLists` | integer | This integer is the number of clusters that the inverted file (IVF) index uses to group the vector data. We recommend that `numLists` is set to `rowCount()/1000` for up to 1 million rows and to `sqrt(rowCount)` for more than 1 million rows. Using a `numLists` value of `1` is akin to performing brute-force search. |
 | `similarity` | string | Similarity metric to use with the IVF index. Possible options are `COS` (cosine distance), `L2` (Euclidean distance), and `IP` (inner product). |
 | `dimensions` | integer | Number of dimensions for vector similarity. The maximum number of supported dimensions is `2000`. |
 
+> [!IMPORTANT]
+> Setting the _numLists_ parameter correctly is critical to achieving good accuracy and perormance. We recommend that `numLists` is set to `rowCount()/1000` for up to 1 million rows and to `sqrt(rowCount)` for more than 1 million rows.
+>
+> As the number of items in your database grows, you should tune _numLists_ to be larger in order to achieve good latency performance for vector search.
+>
+> If you're experimenting with a new scenario or creating a small demo, you can start with `numLists` set to `1` to perform a brute-force search across all vectors. This should provdie you with the most accurate results from the vector search. 
+
 ## Examples
 
 The following examples show you how to index vectors, add documents that have vector properties, perform a vector search, and retrieve the index configuration.
@@ -77,7 +84,7 @@ db.runCommand({
       },
       cosmosSearchOptions: {
         kind: 'vector-ivf',
-        numLists: 100,
+        numLists: 3,
         similarity: 'COS',
         dimensions: 3
       }
@@ -176,7 +183,7 @@ In this example, `vectorIndex` is returned with all the `cosmosSearch` parameter
     name: 'vectorSearchIndex',
     cosmosSearch: {
       kind: 'vector-ivf',
-      numLists: 100,
+      numLists: 3,
       similarity: 'COS',
       dimensions: 3
     },