chore: Update deprecated models (#380)

* Update text-embedding-ada-002 to text-embedding-3-small

* Update gpt-35-turbo to gpt-4o-mini

* Small fix

---------

Co-authored-by: Jonas Israel <[email protected]>

Author: Jonas-Isr

docs/blog/Introducing.md

@@ -94,7 +94,7 @@ Please open a [feature request](https://github.com/SAP/ai-sdk-java/issues/new/ch
 
 ```java
 var result = 
-  OpenAiClient.forModel(GPT_35_TURBO)
+  OpenAiClient.forModel(GPT_4O_MINI)
     .withSystemPrompt("You are a helpful AI")
     .chatCompletion("Hello World! Why is this phrase so famous?");
 

docs/guides/AI_CORE_DEPLOYMENT.md

@@ -50,11 +50,11 @@ In addition to the prerequisites above, we assume you have already set up the fo
         "executableId": "azure-openai",
         "id": "12345-123-123-123-123456abcdefg",
         "inputArtifactBindings": [],
-        "name": "gpt-35-turbo",
+        "name": "gpt-4o-mini",
         "parameterBindings": [
           {
             "key": "modelName",
-            "value": "gpt-35-turbo"
+            "value": "gpt-4o-mini"
           },
           {
             "key": "modelVersion",

docs/guides/OPENAI_CHAT_COMPLETION.md

@@ -71,7 +71,7 @@ In addition to the prerequisites above, we assume you have already set up the fo
         "id": "d123456abcdefg",
         "deploymentUrl": "https://api.ai.region.aws.ml.hana.ondemand.com/v2/inference/deployments/d123456abcdefg",
         "configurationId": "12345-123-123-123-123456abcdefg",
-        "configurationName": "gpt-35-turbo",
+        "configurationName": "gpt-4o-mini",
         "scenarioId": "foundation-models",
         "status": "RUNNING",
         "statusMessage": null,
@@ -86,7 +86,7 @@ In addition to the prerequisites above, we assume you have already set up the fo
           "resources": {
             "backendDetails": {
               "model": {
-                "name": "gpt-35-turbo",
+                "name": "gpt-4o-mini",
                 "version": "latest"
               }
             }
@@ -106,7 +106,7 @@ In addition to the prerequisites above, we assume you have already set up the fo
 
 ```java
 var result =
-    OpenAiClient.forModel(GPT_35_TURBO)
+    OpenAiClient.forModel(GPT_4O_MINI)
         .withSystemPrompt("You are a helpful AI")
         .chatCompletion("Hello World! Why is this phrase so famous?");
 
@@ -146,7 +146,7 @@ var userMessage =
 var request =
     new OpenAiChatCompletionParameters().addMessages(systemMessage, userMessage);
 
-var result = OpenAiClient.forModel(GPT_35_TURBO).chatCompletion(request);
+var result = OpenAiClient.forModel(GPT_4O_MINI).chatCompletion(request);
 
 String resultMessage = result.getContent();
 ```
@@ -162,7 +162,7 @@ To target a specific version, you can specify the model version along with the m
 
 ```java
 OpenAiChatCompletionOutput result =
-    OpenAiClient.forModel(GPT_35_TURBO.withVersion("1106")).chatCompletion(request);
+    OpenAiClient.forModel(GPT_4O_MINI.withVersion("1106")).chatCompletion(request);
 ```
 
 ## Chat completion with Custom Model
@@ -187,7 +187,7 @@ This is a blocking example for streaming and printing directly to the console:
 ```java
 String msg = "Can you give me the first 100 numbers of the Fibonacci sequence?";
 
-OpenAiClient client = OpenAiClient.forModel(GPT_35_TURBO);
+OpenAiClient client = OpenAiClient.forModel(GPT_4O_MINI);
 
 // try-with-resources on stream ensures the connection will be closed
 try (Stream<String> stream = client.streamChatCompletion(msg)) {
@@ -254,7 +254,7 @@ var userMessage =
 var requestParameters =
     new OpenAiChatCompletionParameters().addMessages(userMessage);
 
-var client = OpenAiClient.forModel(GPT_35_TURBO);
+var client = OpenAiClient.forModel(GPT_4O_MINI);
 var totalOutput = new OpenAiChatCompletionOutput();
 
 // Prepare the stream before starting the thread to handle any initialization exceptions
@@ -292,7 +292,7 @@ Get the embeddings of a text input in list of float values:
 ```java
 var request = new OpenAiEmbeddingRequest(List.of("Hello World"));
 
-OpenAiEmbeddingResponse response = OpenAiClient.forModel(TEXT_EMBEDDING_ADA_002).embedding(request);
+OpenAiEmbeddingResponse response = OpenAiClient.forModel(TEXT_EMBEDDING_3_SMALL).embedding(request);
 float[] embedding = embedding.getEmbeddings().get(0);
 ```
 
@@ -302,7 +302,7 @@ float[] embedding = embedding.getEmbeddings().get(0);
 ```java
 var request = new OpenAiEmbeddingParameters().setInput("Hello World");
 
-OpenAiEmbeddingOutput embedding = OpenAiClient.forModel(TEXT_EMBEDDING_ADA_002).embedding(request);
+OpenAiEmbeddingOutput embedding = OpenAiClient.forModel(TEXT_EMBEDDING_3_SMALL).embedding(request);
 
 float[] embedding = embedding.getData().get(0).getEmbedding();
 ```

docs/guides/SPRING_AI_INTEGRATION.md

@@ -51,7 +51,7 @@ The Orchestration client is integrated in Spring AI classes:
 
 ```java
 ChatModel client = new OrchestrationChatModel();
-OrchestrationModuleConfig config = new OrchestrationModuleConfig().withLlmConfig(GPT_35_TURBO);
+OrchestrationModuleConfig config = new OrchestrationModuleConfig().withLlmConfig(GPT_4O_MINI);
 OrchestrationChatOptions opts = new OrchestrationChatOptions(config);
 
 Prompt prompt = new Prompt("What is the capital of France?", opts);
@@ -66,7 +66,7 @@ Configure Orchestration modules withing Spring AI:
 
 ```java
 ChatModel client = new OrchestrationChatModel();
-OrchestrationModuleConfig config = new OrchestrationModuleConfig().withLlmConfig(GPT_35_TURBO);
+OrchestrationModuleConfig config = new OrchestrationModuleConfig().withLlmConfig(GPT_4O_MINI);
 
 val masking =
     DpiMasking.anonymization()
@@ -91,7 +91,7 @@ to the frontend in real-time.
 
 ```java
 ChatModel client = new OrchestrationChatModel();
-OrchestrationModuleConfig config = new OrchestrationModuleConfig().withLlmConfig(GPT_35_TURBO);
+OrchestrationModuleConfig config = new OrchestrationModuleConfig().withLlmConfig(GPT_4O_MINI);
 OrchestrationChatOptions opts = new OrchestrationChatOptions(config);
 
 Prompt prompt =
@@ -130,7 +130,7 @@ Then add your tool to the options:
 
 ```java
 ChatModel client = new OrchestrationChatModel();
-OrchestrationModuleConfig config = new OrchestrationModuleConfig().withLlmConfig(GPT_35_TURBO);
+OrchestrationModuleConfig config = new OrchestrationModuleConfig().withLlmConfig(GPT_4O_MINI);
 OrchestrationChatOptions opts = new OrchestrationChatOptions(config);
 
 options.setToolCallbacks(List.of(ToolCallbacks.from(new WeatherMethod())));
@@ -150,7 +150,7 @@ Create a Spring AI `ChatClient` from our `OrchestrationChatModel` and add a chat
 
 ```java
 ChatModel client = new OrchestrationChatModel();
-OrchestrationModuleConfig config = new OrchestrationModuleConfig().withLlmConfig(GPT_35_TURBO);
+OrchestrationModuleConfig config = new OrchestrationModuleConfig().withLlmConfig(GPT_4O_MINI);
 OrchestrationChatOptions opts = new OrchestrationChatOptions(config);
 
 val memory = new InMemoryChatMemory();

sample-code/spring-app/src/main/java/com/sap/ai/sdk/app/controllers/GroundingController.java

@@ -1,6 +1,6 @@
 package com.sap.ai.sdk.app.controllers;
 
-import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.TEXT_EMBEDDING_ADA_002;
+import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.TEXT_EMBEDDING_3_SMALL;
 import static java.time.LocalDate.now;
 import static java.util.stream.Collectors.joining;
 
@@ -139,7 +139,7 @@ Object getDocumentsByCollectionId(
   @GetMapping("/vector/collection/create")
   String createCollection(
       @Nullable @RequestParam(value = "format", required = false) final String format) {
-    final var embeddingConfig = EmbeddingConfig.create().modelName(TEXT_EMBEDDING_ADA_002.name());
+    final var embeddingConfig = EmbeddingConfig.create().modelName(TEXT_EMBEDDING_3_SMALL.name());
     final var request =
         CollectionRequest.create().embeddingConfig(embeddingConfig).title(COLLECTION_TITLE);
     final var documents = CLIENT_VECTOR.createCollection(RESOURCE_GROUP, request);

sample-code/spring-app/src/main/java/com/sap/ai/sdk/app/services/OpenAiService.java

@@ -1,8 +1,8 @@
 package com.sap.ai.sdk.app.services;
 
-import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.GPT_35_TURBO;
 import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.GPT_4O;
-import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.TEXT_EMBEDDING_ADA_002;
+import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.GPT_4O_MINI;
+import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.TEXT_EMBEDDING_3_SMALL;
 import static com.sap.ai.sdk.foundationmodels.openai.model.OpenAiChatCompletionTool.ToolType.FUNCTION;
 
 import com.sap.ai.sdk.core.AiCoreService;
@@ -35,7 +35,7 @@ public class OpenAiService {
    */
   @Nonnull
   public OpenAiChatCompletionOutput chatCompletion(@Nonnull final String prompt) {
-    return OpenAiClient.forModel(GPT_35_TURBO).chatCompletion(prompt);
+    return OpenAiClient.forModel(GPT_4O_MINI).chatCompletion(prompt);
   }
 
   /**
@@ -50,7 +50,7 @@ public Stream<OpenAiChatCompletionDelta> streamChatCompletionDeltas(
         new OpenAiChatCompletionParameters()
             .addMessages(new OpenAiChatMessage.OpenAiChatUserMessage().addText(message));
 
-    return OpenAiClient.forModel(GPT_35_TURBO).streamChatCompletionDeltas(request);
+    return OpenAiClient.forModel(GPT_4O_MINI).streamChatCompletionDeltas(request);
   }
 
   /**
@@ -60,7 +60,7 @@ public Stream<OpenAiChatCompletionDelta> streamChatCompletionDeltas(
    */
   @Nonnull
   public Stream<String> streamChatCompletion(@Nonnull final String message) {
-    return OpenAiClient.forModel(GPT_35_TURBO)
+    return OpenAiClient.forModel(GPT_4O_MINI)
         .withSystemPrompt("Be a good, honest AI and answer the following question:")
         .streamChatCompletion(message);
   }
@@ -109,7 +109,7 @@ public OpenAiChatCompletionOutput chatCompletionTools(final int months) {
             .setTools(List.of(tool))
             .setToolChoiceFunction("fibonacci");
 
-    return OpenAiClient.forModel(GPT_35_TURBO).chatCompletion(request);
+    return OpenAiClient.forModel(GPT_4O_MINI).chatCompletion(request);
   }
 
   /**
@@ -122,7 +122,7 @@ public OpenAiChatCompletionOutput chatCompletionTools(final int months) {
   public OpenAiEmbeddingOutput embedding(@Nonnull final String input) {
     final var request = new OpenAiEmbeddingParameters().setInput(input);
 
-    return OpenAiClient.forModel(TEXT_EMBEDDING_ADA_002).embedding(request);
+    return OpenAiClient.forModel(TEXT_EMBEDDING_3_SMALL).embedding(request);
   }
 
   /**

sample-code/spring-app/src/main/java/com/sap/ai/sdk/app/services/SpringAiOrchestrationService.java

@@ -1,6 +1,6 @@
 package com.sap.ai.sdk.app.services;
 
-import static com.sap.ai.sdk.orchestration.OrchestrationAiModel.GPT_35_TURBO;
+import static com.sap.ai.sdk.orchestration.OrchestrationAiModel.GPT_4O_MINI;
 
 import com.sap.ai.sdk.orchestration.DpiMasking;
 import com.sap.ai.sdk.orchestration.OrchestrationModuleConfig;
@@ -28,7 +28,7 @@
 public class SpringAiOrchestrationService {
   private final ChatModel client = new OrchestrationChatModel();
   private final OrchestrationModuleConfig config =
-      new OrchestrationModuleConfig().withLlmConfig(GPT_35_TURBO);
+      new OrchestrationModuleConfig().withLlmConfig(GPT_4O_MINI);
   private final OrchestrationChatOptions defaultOptions = new OrchestrationChatOptions(config);
 
   /**

sample-code/spring-app/src/test/java/com/sap/ai/sdk/app/controllers/OpenAiTest.java

@@ -1,6 +1,6 @@
 package com.sap.ai.sdk.app.controllers;
 
-import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.GPT_35_TURBO;
+import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.GPT_4O_MINI;
 import static org.assertj.core.api.Assertions.assertThat;
 
 import com.sap.ai.sdk.app.services.OpenAiService;
@@ -50,7 +50,7 @@ void streamChatCompletion() {
 
     final var totalOutput = new OpenAiChatCompletionOutput();
     final var filledDeltaCount = new AtomicInteger(0);
-    OpenAiClient.forModel(GPT_35_TURBO)
+    OpenAiClient.forModel(GPT_4O_MINI)
         .streamChatCompletionDeltas(request)
         .peek(totalOutput::addDelta)
         // foreach consumes all elements, closing the stream at the end
@@ -88,7 +88,7 @@ void embedding() {
     final var embedding = service.embedding("Hello world");
 
     assertThat(embedding.getData().get(0).getEmbedding()).hasSizeGreaterThan(1);
-    assertThat(embedding.getModel()).isEqualTo("ada");
+    assertThat(embedding.getModel()).isEqualTo("text-embedding-3-small");
     assertThat(embedding.getObject()).isEqualTo("list");
   }
 

sample-code/spring-app/src/test/java/com/sap/ai/sdk/app/controllers/OpenAiV2Test.java

@@ -1,6 +1,6 @@
 package com.sap.ai.sdk.app.controllers;
 
-import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.GPT_35_TURBO;
+import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.GPT_4O_MINI;
 import static com.sap.ai.sdk.foundationmodels.openai.generated.model.ChatCompletionResponseMessageRole.ASSISTANT;
 import static org.assertj.core.api.Assertions.assertThat;
 
@@ -51,7 +51,7 @@ void streamChatCompletion() {
     final var usageRef = new AtomicReference<CompletionUsage>();
     final var filledDeltaCount = new AtomicInteger(0);
 
-    OpenAiClient.forModel(GPT_35_TURBO)
+    OpenAiClient.forModel(GPT_4O_MINI)
         .streamChatCompletionDeltas(prompt)
         // foreach consumes all elements, closing the stream at the end
         .forEach(
@@ -67,7 +67,7 @@ void streamChatCompletion() {
     assertThat(filledDeltaCount.get()).isGreaterThan(0);
 
     assertThat(usageRef.get().getTotalTokens()).isGreaterThan(0);
-    assertThat(usageRef.get().getPromptTokens()).isEqualTo(14);
+    assertThat(usageRef.get().getPromptTokens()).isGreaterThan(0);
     assertThat(usageRef.get().getCompletionTokens()).isGreaterThan(0);
   }
 
@@ -90,7 +90,7 @@ void embedding() {
     assertThat(embedding.getEmbeddingVectors()).isInstanceOf(ArrayList.class);
     assertThat(embedding.getEmbeddingVectors().get(0)).isInstanceOf(float[].class);
 
-    assertThat(embedding.getOriginalResponse().getModel()).isEqualTo("ada");
+    assertThat(embedding.getOriginalResponse().getModel()).isEqualTo("text-embedding-3-small");
     assertThat(embedding.getOriginalResponse().getObject()).isEqualTo("list");
   }
 

sample-code/spring-app/src/test/java/com/sap/ai/sdk/app/services/OpenAiServiceV2.java

@@ -1,8 +1,8 @@
 package com.sap.ai.sdk.app.services;
 
-import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.GPT_35_TURBO;
 import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.GPT_4O;
-import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.TEXT_EMBEDDING_ADA_002;
+import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.GPT_4O_MINI;
+import static com.sap.ai.sdk.foundationmodels.openai.OpenAiModel.TEXT_EMBEDDING_3_SMALL;
 import static com.sap.ai.sdk.foundationmodels.openai.generated.model.ChatCompletionTool.TypeEnum.FUNCTION;
 
 import com.sap.ai.sdk.core.AiCoreService;
@@ -37,7 +37,7 @@ public class OpenAiServiceV2 {
    */
   @Nonnull
   public OpenAiChatCompletionResponse chatCompletion(@Nonnull final String prompt) {
-    return OpenAiClient.forModel(GPT_35_TURBO)
+    return OpenAiClient.forModel(GPT_4O_MINI)
         .chatCompletion(new OpenAiChatCompletionRequest(prompt));
   }
 
@@ -51,7 +51,7 @@ public Stream<OpenAiChatCompletionDelta> streamChatCompletionDeltas(
       @Nonnull final String message) {
     final var request = new OpenAiChatCompletionRequest(OpenAiMessage.user(message));
 
-    return OpenAiClient.forModel(GPT_35_TURBO).streamChatCompletionDeltas(request);
+    return OpenAiClient.forModel(GPT_4O_MINI).streamChatCompletionDeltas(request);
   }
 
   /**
@@ -61,7 +61,7 @@ public Stream<OpenAiChatCompletionDelta> streamChatCompletionDeltas(
    */
   @Nonnull
   public Stream<String> streamChatCompletion(@Nonnull final String message) {
-    return OpenAiClient.forModel(GPT_35_TURBO)
+    return OpenAiClient.forModel(GPT_4O_MINI)
         .withSystemPrompt("Be a good, honest AI and answer the following question:")
         .streamChatCompletion(message);
   }
@@ -107,7 +107,7 @@ public OpenAiChatCompletionResponse chatCompletionTools(final int months) {
             .withTools(List.of(tool))
             .withToolChoice(OpenAiToolChoice.function("fibonacci"));
 
-    return OpenAiClient.forModel(GPT_35_TURBO).chatCompletion(request);
+    return OpenAiClient.forModel(GPT_4O_MINI).chatCompletion(request);
   }
 
   /**
@@ -120,7 +120,7 @@ public OpenAiChatCompletionResponse chatCompletionTools(final int months) {
   public OpenAiEmbeddingResponse embedding(@Nonnull final String input) {
     final var request = new OpenAiEmbeddingRequest(List.of(input));
 
-    return OpenAiClient.forModel(TEXT_EMBEDDING_ADA_002).embedding(request);
+    return OpenAiClient.forModel(TEXT_EMBEDDING_3_SMALL).embedding(request);
   }
 
   /**