Refactor Llama model classes to remove modelId and update embedding request handling

Author: Jan-Kazlouski-elastic

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

@@ -28,7 +28,6 @@
  * This class extends RateLimitGroupingModel and provides common functionality for Llama models.
  */
 public abstract class LlamaModel extends RateLimitGroupingModel {
-    protected String modelId;
     protected URI uri;
     protected RateLimitSettings rateLimitSettings;
 
@@ -51,10 +50,6 @@ protected LlamaModel(RateLimitGroupingModel model, ServiceSettings serviceSettin
         super(model, serviceSettings);
     }
 
-    public String model() {
-        return this.modelId;
-    }
-
     public URI uri() {
         return this.uri;
     }
@@ -66,7 +61,7 @@ public RateLimitSettings rateLimitSettings() {
 
     @Override
     public int rateLimitGroupingHash() {
-        return Objects.hash(modelId, uri, getSecretSettings());
+        return Objects.hash(uri, getSecretSettings());
     }
 
     // Needed for testing only

x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/llama/completion/LlamaChatCompletionModel.java

@@ -105,7 +105,6 @@ public static LlamaChatCompletionModel of(LlamaChatCompletionModel model, Unifie
     }
 
     private void setPropertiesFromServiceSettings(LlamaChatCompletionServiceSettings serviceSettings) {
-        this.modelId = serviceSettings.modelId();
         this.uri = serviceSettings.uri();
         this.rateLimitSettings = serviceSettings.rateLimitSettings();
     }

x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/llama/embeddings/LlamaEmbeddingsModel.java

@@ -75,7 +75,6 @@ public LlamaEmbeddingsModel(LlamaEmbeddingsModel model, LlamaEmbeddingsServiceSe
      * @param serviceSettings the service settings to extract properties from
      */
     private void setPropertiesFromServiceSettings(LlamaEmbeddingsServiceSettings serviceSettings) {
-        this.modelId = serviceSettings.modelId();
         this.uri = serviceSettings.uri();
         this.rateLimitSettings = serviceSettings.rateLimitSettings();
     }

x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/llama/request/embeddings/LlamaEmbeddingsRequest.java

@@ -60,7 +60,8 @@ public HttpRequest createHttpRequest() {
         HttpPost httpPost = new HttpPost(this.uri);
 
         ByteArrayEntity byteEntity = new ByteArrayEntity(
-            Strings.toString(new LlamaEmbeddingsRequestEntity(model.model(), truncationResult.input())).getBytes(StandardCharsets.UTF_8)
+            Strings.toString(new LlamaEmbeddingsRequestEntity(model.getServiceSettings().modelId(), truncationResult.input()))
+                .getBytes(StandardCharsets.UTF_8)
         );
         httpPost.setEntity(byteEntity);