[Inference API] Add unified api for chat completions

docs/changelog/117589.yaml

@@ -0,0 +1,5 @@
+pr: 117589
+summary: "[Inference API] Add unified api for chat completions"
+area: Machine Learning
+type: enhancement
+issues: []

server/src/main/java/org/elasticsearch/TransportVersions.java

@@ -207,6 +207,7 @@ static TransportVersion def(int id) {
     public static final TransportVersion INDEXING_PRESSURE_THROTTLING_STATS = def(8_798_00_0);
     public static final TransportVersion REINDEX_DATA_STREAMS = def(8_799_00_0);
     public static final TransportVersion ESQL_REMOVE_NODE_LEVEL_PLAN = def(8_800_00_0);
+    public static final TransportVersion ML_INFERENCE_UNIFIED_COMPLETIONS_API = def(8_801_00_0);
     /*
      * STOP! READ THIS FIRST! No, really,
      *        ____ _____ ___  ____  _        ____  _____    _    ____    _____ _   _ ___ ____    _____ ___ ____  ____ _____ _

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

@@ -111,6 +111,21 @@ void infer(
         ActionListener<InferenceServiceResults> listener
     );
 
+    /**
+     * Perform completion inference on the model using the unified schema.
+     *
+     * @param model        The model
+     * @param request Parameters for the request
+     * @param timeout      The timeout for the request
+     * @param listener     Inference result listener
+     */
+    void unifiedCompletionInfer(
+        Model model,
+        UnifiedCompletionRequest request,
+        TimeValue timeout,
+        ActionListener<InferenceServiceResults> listener
+    );
+
     /**
      * Chunk long text according to {@code chunkingOptions} or the
      * model defaults if {@code chunkingOptions} contains unset