minor updates, mention of 'read-only', added a example listing

Author: rsill-neo4j

modules/ROOT/pages/directives/indexes-and-constraints.adoc

@@ -257,10 +257,11 @@ await neoSchema.assertIndexesAndConstraints({ options: { create: true }});
 With the `@vector` GraphQL directive you can query your database to perform a vector index search.
 Queries are performed by passing in either a vector index or a query phrase.
 
-A query by vector index finds nodes with a vector embedding similar to that index, a nearest neighbor search.
+A query by vector index finds nodes with a vector embedding similar to that index.
+That is, the query performs a nearest neighbor search.
 
 In contrast, a query by phrase (a string of text) forwards the phrase to the link:https://neo4j.com/docs/cypher-manual/current/genai-integrations/[Neo4j GenAI plugin] and the plugin generates a vector embedding for it.
-This embedding is then compared to the node vector embeddings in the database and the result set.
+This embedding is then compared to the node vector embeddings in the database.
 
 [NOTE] 
 .Prerequisites
@@ -272,6 +273,11 @@ This embedding is then compared to the node vector embeddings in the database an
 * Queries by phrase require credentials for the Neo4j GenAI plugin.
 ====
 
+[NOTE]
+====
+Vector index searches are _read-only_ in the sense that no data is persisted in the database.
+====
+
 
 === Definition
 
@@ -294,18 +300,16 @@ input VectorIndexInput {
   queryName: String
   """(Optional) The name of the provider."""
   provider: String
-  """(Optional) The name of the callback function."""
-  callback: String
 }
 ----
 
-If the optional field `provider` is set, the type can be used for a query by phrase, otherwise for a query by vector index. 
+If the optional field `provider` is set, the type is used for a query by phrase, otherwise for a query by vector index. 
 
 === Usage
 
 ==== Query by vector index
 
-Perform a nearest neighbor search by passing a vector index to your database and find nodes with a vector embedding similar to that index.
+Perform a nearest neighbor search by passing a vector index to find nodes with a vector embedding similar to that index.
 
 .Type definition
 [source, graphql]
@@ -343,9 +347,23 @@ query FindSimilarProducts($vector: [Float]!) {
 }
 ----
 
+The input `$vector` is a list of `FLOAT` values and should look similar to this:
+
+.Example query
+[source, graphql]
+----
+{
+  "vector": [
+    0.123456,
+    ...,
+    0.654321,
+  ]
+}
+----
+
 The query returns all `Product` nodes with a vector embedding on their `descriptionVector` property which is similar to the vector index argument `$vector`.
 
-=== Query by phrase
+==== Query by phrase
 
 Perform a query which utilizes the link:https://neo4j.com/docs/cypher-manual/current/genai-integrations/[Neo4j GenAI plugin] to create a vector embedding for a search phrase and then compares it to existing vector embeddings on nodes in the database.