[AI] [Inference] use model version 2024-05-01-preview as default #44517 (#44528)

* [AI] [Inference] use model version 2024-05-01-preview as default

* add customization for getLatest in ModelServiceVersion

* update test recordings to use api-version 2024-05-01-preview

Author: glharper

sdk/ai/azure-ai-inference/CHANGELOG.md

@@ -1,14 +1,10 @@
 # Release History
 
-## 1.0.0-beta.4 (Unreleased)
-
-### Features Added
-
-### Breaking Changes
+## 1.0.0-beta.4 (2025-03-14)
 
 ### Bugs Fixed
 
-### Other Changes
+- #44517: Use ModelServiceVersion (api-version) of 2024-05-01-preview as default 
 
 ## 1.0.0-beta.3 (2025-02-20)
 

sdk/ai/azure-ai-inference/assets.json

@@ -2,5 +2,5 @@
   "AssetsRepo" : "Azure/azure-sdk-assets",
   "AssetsRepoPrefixPath" : "java",
   "TagPrefix" : "java/ai/azure-ai-inference",
-  "Tag" : "java/ai/azure-ai-inference_0f2ce572e3"
+  "Tag" : "java/ai/azure-ai-inference_36b486be14"
 }

sdk/ai/azure-ai-inference/customization/src/main/java/InferenceCustomizations.java

@@ -2,6 +2,7 @@
 import com.azure.autorest.customization.Customization;
 import com.azure.autorest.customization.LibraryCustomization;
 import com.azure.autorest.customization.PackageCustomization;
+import com.azure.autorest.customization.MethodCustomization;
 import org.slf4j.Logger;
 import com.github.javaparser.StaticJavaParser;
 
@@ -38,6 +39,10 @@ public void customize(LibraryCustomization customization, Logger logger) {
                         "}"))));
             });
         });
+        PackageCustomization base = customization.getPackage("com.azure.ai.inference");
+        ClassCustomization serviceVersion = base.getClass("ModelServiceVersion");
+        serviceVersion.getMethod("getLatest")
+            .replaceBody("return V2024_05_01_PREVIEW;");
         customizeChatCompletionsBaseClasses(customization, logger);
     }
 

sdk/ai/azure-ai-inference/src/main/java/com/azure/ai/inference/ModelServiceVersion.java

@@ -40,6 +40,6 @@ public String getVersion() {
      * @return The latest {@link ModelServiceVersion}.
      */
     public static ModelServiceVersion getLatest() {
-        return V2024_08_01_PREVIEW;
+        return V2024_05_01_PREVIEW;
     }
 }

sdk/ai/azure-ai-inference/src/samples/java/com/azure/ai/inference/usage/StructuredJsonChatSample.java

@@ -6,6 +6,7 @@
 
 import com.azure.ai.inference.ChatCompletionsClient;
 import com.azure.ai.inference.ChatCompletionsClientBuilder;
+import com.azure.ai.inference.ModelServiceVersion;
 import com.azure.ai.inference.models.ChatCompletions;
 import com.azure.ai.inference.models.ChatCompletionsOptions;
 import com.azure.ai.inference.models.ChatRequestMessage;
@@ -62,6 +63,7 @@ public static void main(String[] args) {
         ChatCompletionsClient client = new ChatCompletionsClientBuilder()
             .credential(new AzureKeyCredential(key))
             .endpoint(endpoint)
+            .serviceVersion(ModelServiceVersion.V2024_08_01_PREVIEW)
             .buildClient();
 
         List<ChatRequestMessage> chatMessages = new ArrayList<>();

sdk/ai/azure-ai-inference/src/test/java/com/azure/ai/inference/ChatCompletionsSyncClientTest.java

@@ -83,6 +83,10 @@ private ChatCompletionsClient getChatCompletionsClient(HttpClient httpClient) {
         return getBuilder(httpClient).buildClient();
     }
 
+    private ChatCompletionsClient getChatCompletionsClientForStructuredJSON(HttpClient httpClient) {
+        return getBuilder(httpClient).serviceVersion(ModelServiceVersion.V2024_08_01_PREVIEW).buildClient();
+    }
+
     private ChatCompletionsClient getChatCompletionsClientWithTracing(HttpClient httpClient,
         SpanProcessor spanProcessor, boolean captureContent) {
         final OpenTelemetryTracingOptions tracingOptions
@@ -226,7 +230,7 @@ public void testGetCompletionsWithStructuredJSON(HttpClient httpClient) {
                 put("additionalProperties", BinaryData.fromString("false"));
             }
         };
-        client = getChatCompletionsClient(httpClient);
+        client = getChatCompletionsClientForStructuredJSON(httpClient);
 
         List<ChatRequestMessage> chatMessages = new ArrayList<>();
         chatMessages.add(new ChatRequestSystemMessage("You are a helpful assistant."));