inference timeout for internal services

Author: Samiul-TheSoccerFan

x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elasticsearch/BaseElasticsearchInternalService.java

@@ -263,6 +263,10 @@ private void preferredVariantFromPlatformArchitecture(ActionListener<PreferredMo
         );
     }
 
+    protected TimeValue getConfiguredInferenceTimeout() {
+        return clusterService.getClusterSettings().get(InferencePlugin.SEMANTIC_TEXT_INFERENCE_TIMEOUT);
+    }
+
     boolean isClusterInElasticCloud() {
         // Use the ml lazy node count as a heuristic to determine if in Elastic cloud.
         // A value > 0 means scaling should be available for ml nodes

x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elasticsearch/ElasticsearchInternalService.java

@@ -613,6 +613,9 @@ public void infer(
         TimeValue timeout,
         ActionListener<InferenceServiceResults> listener
     ) {
+        if (timeout == null) {
+            timeout = getConfiguredInferenceTimeout();
+        }
         if (model instanceof ElasticsearchInternalModel esModel) {
             var taskType = model.getConfigurations().getTaskType();
             if (TaskType.TEXT_EMBEDDING.equals(taskType)) {