Documentation for query_vector base64 parameter

docs/reference/elasticsearch/rest-apis/retrievers/diversify-retriever.md

@@ -46,10 +46,13 @@ The ordering of results returned from the inner retriever is preserved.
     :::
 
 `query_vector`
-:   (Optional, array of `float` or `byte`)
+:   (Optional, array of `float` or `byte`, or string)
 
     Query vector. Must have the same number of dimensions as the vector field you are searching against.
-    Must be either an array of floats or a hex-encoded byte vector.
+    Must be one of:
+      - An array of floats
+      - A hex-encoded byte vector (one byte per dimension; for `bit`, one byte per 8 dimensions){applies_to}`stack: ga 9.0-9.3`
+      - A base64-encoded vector string. Base64 supports `float` and `bfloat16` (big-endian), `byte`, and `bit` encodings depending on the target field type. {applies_to}`stack: ga 9.4`
     If you provide a `query_vector`, you cannot also provide a `query_vector_builder`.
 
 `query_vector_builder`

docs/reference/elasticsearch/rest-apis/retrievers/knn-retriever.md

@@ -18,9 +18,13 @@ A kNN retriever returns top documents from a [k-nearest neighbor search (kNN)](d
 
 
 `query_vector`
-:   (Required if `query_vector_builder` is not defined, array of `float`)
+:   (Required if `query_vector_builder` is not defined, array of `float` or string)
 
-    Query vector. Must have the same number of dimensions as the vector field you are searching against. Must be either an array of floats or a hex-encoded byte vector.
+    Query vector. Must have the same number of dimensions as the vector field you are searching against.
+    Must be one of:
+      - An array of floats
+      - A hex-encoded byte vector (one byte per dimension; for `bit`, one byte per 8 dimensions). {applies_to}`stack: ga 9.0-9.3`
+      - A base64-encoded vector string. Base64 supports `float` and `bfloat16` (big-endian), `byte`, and `bit` encodings depending on the target field type. {applies_to}`stack: ga 9.4` {applies_to}`serverless: ga`
 
 
 `query_vector_builder`

docs/reference/query-languages/query-dsl/query-dsl-knn-query.md

@@ -66,6 +66,40 @@
     ```
     % TEST[continued]
 
+3. {applies_to}`stack: ga 9.0-9.3` You can also provide a hex-encoded query vector string. Hex query vectors are byte-oriented (one byte per dimension, represented as two hex characters). For example, `[-5, 9, -12]` as signed bytes is `fb09f4`.
+
+    ```console
+    POST my-image-index/_search
+    {
+      "size" : 3,
+      "query" : {
+        "knn": {
+          "field": "image-vector",
+          "query_vector": "fb09f4",
+          "k": 10
+        }
+      }
+    }
+    ```
+    % TEST[continued]
+
+4. {applies_to}`stack: ga 9.4` You can also provide a base64-encoded query vector string. For example, `[-5, 9, -12]` encoded as float32 big-endian bytes is `wKAAAEEQAADBQAAA`.
+
+    ```console
+    POST my-image-index/_search
+    {
+      "size" : 3,
+      "query" : {
+        "knn": {
+          "field": "image-vector",
+          "query_vector": "wKAAAEEQAADBQAAA",
+          "k": 10
+        }
+      }
+    }
+    ```
+    % TEST[continued]
+
 
 ## Top-level parameters for `knn` [knn-query-top-level-parameters]
 
@@ -74,7 +108,12 @@
 
 
 `query_vector`
-:   (Optional, array of floats or string) Query vector. Must have the same number of dimensions as the vector field you are searching against. Must be either an array of floats or a hex-encoded byte vector. Either this or `query_vector_builder` must be provided.
+:   (Optional, array of floats or string) Query vector. Must have the same number of dimensions as the vector field you are searching against.
+    Must be one of:
+      - An array of floats
+      - A hex-encoded byte vector (one byte per dimension; for `bit`, one byte per 8 dimensions). {applies_to}`stack: ga 9.0-9.3`
+      - A base64-encoded vector string. Base64 supports `float` and `bfloat16` (big-endian), `byte`, and `bit` encodings depending on the target field type. {applies_to}`stack: ga 9.4` {applies_to}`serverless: ga`
+    Either this or `query_vector_builder` must be provided.
 
 
 `query_vector_builder`