[ML] Remove ChunkingOptions parameter (elastic#117235)

Author: ashm-dev

docs/changelog/117235.yaml

@@ -0,0 +1,5 @@
+pr: 117235
+summary: "Deprecate `ChunkingOptions` parameter"
+area: ES|QL
+type: enhancement
+issues: []

server/src/main/java/org/elasticsearch/inference/ChunkingOptions.java

@@ -112,16 +112,11 @@ void infer(
     );
 
     /**
-     * Chunk long text according to {@code chunkingOptions} or the
-     * model defaults if {@code chunkingOptions} contains unset
-     * values.
-     *
      * @param model           The model
      * @param query           Inference query, mainly for re-ranking
      * @param input           Inference input
      * @param taskSettings    Settings in the request to override the model's defaults
      * @param inputType       For search, ingest etc
-     * @param chunkingOptions The window and span options to apply
      * @param timeout         The timeout for the request
      * @param listener        Chunked Inference result listener
      */
@@ -131,7 +126,6 @@ void chunkedInfer(
         List<String> input,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     );

server/src/main/java/org/elasticsearch/inference/InferenceService.java

@@ -18,7 +18,6 @@
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.index.mapper.vectors.DenseVectorFieldMapper;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceExtension;
@@ -140,7 +139,6 @@ public void chunkedInfer(
             List<String> input,
             Map<String, Object> taskSettings,
             InputType inputType,
-            ChunkingOptions chunkingOptions,
             TimeValue timeout,
             ActionListener<List<ChunkedInferenceServiceResults>> listener
         ) {

x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestDenseInferenceServiceExtension.java

@@ -17,7 +17,6 @@
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceExtension;
@@ -128,7 +127,6 @@ public void chunkedInfer(
             List<String> input,
             Map<String, Object> taskSettings,
             InputType inputType,
-            ChunkingOptions chunkingOptions,
             TimeValue timeout,
             ActionListener<List<ChunkedInferenceServiceResults>> listener
         ) {

x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestRerankingServiceExtension.java

@@ -17,7 +17,6 @@
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceExtension;
@@ -131,7 +130,6 @@ public void chunkedInfer(
             List<String> input,
             Map<String, Object> taskSettings,
             InputType inputType,
-            ChunkingOptions chunkingOptions,
             TimeValue timeout,
             ActionListener<List<ChunkedInferenceServiceResults>> listener
         ) {

x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestSparseInferenceServiceExtension.java

@@ -19,7 +19,6 @@
 import org.elasticsearch.common.xcontent.ChunkedToXContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceExtension;
@@ -160,7 +159,6 @@ public void chunkedInfer(
             List<String> input,
             Map<String, Object> taskSettings,
             InputType inputType,
-            ChunkingOptions chunkingOptions,
             TimeValue timeout,
             ActionListener<List<ChunkedInferenceServiceResults>> listener
         ) {

x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestStreamingCompletionServiceExtension.java

@@ -30,7 +30,6 @@
 import org.elasticsearch.core.Releasable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.InferenceService;
 import org.elasticsearch.inference.InferenceServiceRegistry;
 import org.elasticsearch.inference.InputType;
@@ -337,16 +336,7 @@ private void onFinish() {
                 }
             };
             inferenceProvider.service()
-                .chunkedInfer(
-                    inferenceProvider.model(),
-                    null,
-                    inputs,
-                    Map.of(),
-                    InputType.INGEST,
-                    new ChunkingOptions(null, null),
-                    TimeValue.MAX_VALUE,
-                    completionListener
-                );
+                .chunkedInfer(inferenceProvider.model(), null, inputs, Map.of(), InputType.INGEST, TimeValue.MAX_VALUE, completionListener);
         }
 
         private FieldInferenceResponseAccumulator ensureResponseAccumulatorSlot(int id) {

x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/action/filter/ShardBulkInferenceActionFilter.java

@@ -12,7 +12,6 @@
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.InferenceService;
 import org.elasticsearch.inference.InferenceServiceResults;
 import org.elasticsearch.inference.InputType;
@@ -76,13 +75,12 @@ public void chunkedInfer(
         List<String> input,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
         init();
         // a non-null query is not supported and is dropped by all providers
-        doChunkedInfer(model, new DocumentsOnlyInput(input), taskSettings, inputType, chunkingOptions, timeout, listener);
+        doChunkedInfer(model, new DocumentsOnlyInput(input), taskSettings, inputType, timeout, listener);
     }
 
     protected abstract void doInfer(
@@ -99,7 +97,6 @@ protected abstract void doChunkedInfer(
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     );

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

@@ -15,7 +15,6 @@
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -289,7 +288,6 @@ protected void doChunkedInfer(
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {