Branch9065 (#9066) (#9071)

* fixing quantization queries - wip



* Fixed ondisk binary quantization queries



---------




(cherry picked from commit b9b00e2)

Signed-off-by: Aruna Govindaraju <[email protected]>
Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aruna Govindaraju <[email protected]>
Co-authored-by: kolchfa-aws <[email protected]>

_search-plugins/knn/knn-vector-quantization.md

@@ -321,6 +321,11 @@ To configure BQ for the Faiss engine, define a `knn_vector` field and specify th
 ```json
 PUT my-vector-index
 {
+  "settings" : {
+    "index": {
+      "knn": true
+    }
+  },
   "mappings": {
     "properties": {
       "my_vector_field": {
@@ -349,6 +354,11 @@ To specify the compression level, set the `compression_level` parameter:
 ```json
 PUT my-vector-index
 {
+  "settings" : {
+    "index": {
+      "knn": true
+    }
+  },
   "mappings": {
     "properties": {
       "my_vector_field": {
@@ -359,6 +369,8 @@ PUT my-vector-index
         "mode": "on_disk",
         "compression_level": "16x",
         "method": {
+          "name": "hnsw",
+          "engine": "faiss",
             "parameters": {
                 "ef_construction": 16
             }
@@ -375,6 +387,11 @@ The following example further fine-tunes the configuration by defining `ef_const
 ```json
 PUT my-vector-index
 {
+  "settings" : {
+    "index": {
+      "knn": true
+    }
+  },
   "mappings": {
     "properties": {
       "my_vector_field": {