From 7111a05de3e0e048aee03309566338efb495ce1f Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Tue, 31 Oct 2023 15:42:48 +0000
Subject: [PATCH] Add missing `scores` parameter in
 `MLPutTrainedModelVocabularyRequest` (#2321) (#2323)

This adds the missing scores parameter that was introduced in v8.9.0.

[Docs](https://www.elastic.co/guide/en/elasticsearch/reference/8.9/put-trained-model-vocabulary.html#ml-put-trained-model-vocabulary-request-body) say:

> (Optional, array) Vocabulary value scores used by sentence-piece tokenization. Must have the same length as vocabulary. Required for unigram sentence-piece tokenized models like XLMRoberta and T5.

(cherry picked from commit e279583a47508af40eb07b84694c5aae7885aa09)

Co-authored-by: David Olaru <dolaru@elastic.co>
---
 output/schema/schema.json                     | 24 ++++++++++++++++++-
 output/typescript/types.ts                    |  1 +
 .../MlPutTrainedModelVocabularyRequest.ts     |  8 +++++++
 3 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/output/schema/schema.json b/output/schema/schema.json
index 3cbb5bf14a..009e7920fb 100644
--- a/output/schema/schema.json
+++ b/output/schema/schema.json
@@ -153534,6 +153534,28 @@
                 }
               }
             }
+          },
+          {
+            "availability": {
+              "serverless": {},
+              "stack": {
+                "since": "8.9.0"
+              }
+            },
+            "description": "The optional vocabulary value scores if required by the tokenizer.",
+            "name": "scores",
+            "required": false,
+            "since": "8.9.0",
+            "type": {
+              "kind": "array_of",
+              "value": {
+                "kind": "instance_of",
+                "type": {
+                  "name": "double",
+                  "namespace": "_types"
+                }
+              }
+            }
           }
         ]
       },
@@ -153564,7 +153586,7 @@
         }
       ],
       "query": [],
-      "specLocation": "ml/put_trained_model_vocabulary/MlPutTrainedModelVocabularyRequest.ts#L23-L52"
+      "specLocation": "ml/put_trained_model_vocabulary/MlPutTrainedModelVocabularyRequest.ts#L24-L60"
     },
     {
       "body": {
diff --git a/output/typescript/types.ts b/output/typescript/types.ts
index 25845e4a36..49c54acb2b 100644
--- a/output/typescript/types.ts
+++ b/output/typescript/types.ts
@@ -14291,6 +14291,7 @@ export interface MlPutTrainedModelVocabularyRequest extends RequestBase {
   body?: {
     vocabulary: string[]
     merges?: string[]
+    scores?: double[]
   }
 }
 
diff --git a/specification/ml/put_trained_model_vocabulary/MlPutTrainedModelVocabularyRequest.ts b/specification/ml/put_trained_model_vocabulary/MlPutTrainedModelVocabularyRequest.ts
index 2dd8894005..c202fb7a3a 100644
--- a/specification/ml/put_trained_model_vocabulary/MlPutTrainedModelVocabularyRequest.ts
+++ b/specification/ml/put_trained_model_vocabulary/MlPutTrainedModelVocabularyRequest.ts
@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { double } from '@_types/Numeric'
 
 /**
  * Creates a trained model vocabulary.
@@ -48,5 +49,12 @@ export interface Request extends RequestBase {
      * @availability serverless
      */
     merges?: string[]
+
+    /**
+     * The optional vocabulary value scores if required by the tokenizer.
+     * @availability stack since=8.9.0
+     * @availability serverless
+     */
+    scores?: double[]
   }
 }