Add upper limit to Multilingual E5 Small as well

Author: kderusso

x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elasticsearch/MultilingualE5SmallModel.java

@@ -12,6 +12,9 @@
 
 public class MultilingualE5SmallModel extends ElasticsearchInternalModel {
 
+    // Ensure that inference endpoints based on E5 small don't go past its window size
+    public static final int E5_SMALL_MAX_WINDOW_SIZE = 300;
+
     public MultilingualE5SmallModel(
         String inferenceEntityId,
         TaskType taskType,
@@ -20,6 +23,15 @@ public MultilingualE5SmallModel(
         ChunkingSettings chunkingSettings
     ) {
         super(inferenceEntityId, taskType, service, serviceSettings, chunkingSettings);
+        if (chunkingSettings != null && chunkingSettings.maxChunkSize() != null) {
+            if (chunkingSettings.maxChunkSize() > E5_SMALL_MAX_WINDOW_SIZE) throw new IllegalArgumentException(
+                serviceSettings.modelId()
+                    + " does not support chunk sizes larger than "
+                    + E5_SMALL_MAX_WINDOW_SIZE
+                    + ". Requested chunk size: "
+                    + chunkingSettings.maxChunkSize()
+            );
+        }
     }
 
     @Override

x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elasticsearch/MultilingualE5SmallModelTests.java

@@ -0,0 +1,35 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0; you may not use this file except in compliance with the Elastic License
+ * 2.0.
+ */
+
+package org.elasticsearch.xpack.inference.services.elasticsearch;
+
+import org.elasticsearch.inference.TaskType;
+import org.elasticsearch.test.ESTestCase;
+import org.elasticsearch.xpack.inference.chunking.SentenceBoundaryChunkingSettings;
+
+import static org.hamcrest.Matchers.equalTo;
+
+public class MultilingualE5SmallModelTests extends ESTestCase {
+
+    public void testHugeChunkingSettings() {
+        Exception expectedException = expectThrows(
+            IllegalArgumentException.class,
+            () -> new MultilingualE5SmallModel(
+                "foo",
+                TaskType.TEXT_EMBEDDING,
+                ElasticsearchInternalService.NAME,
+                MultilingualE5SmallInternalServiceSettings.defaultEndpointSettings(randomBoolean()),
+                new SentenceBoundaryChunkingSettings(10000, 0)
+            )
+        );
+
+        assertThat(
+            expectedException.getMessage(),
+            equalTo(".multilingual-e5-small does not support chunk sizes larger than 300. Requested chunk size: 10000")
+        );
+    }
+}