Added e2e test + docs

Author: CharlesDuboisSAP

docs/guides/SPRING_AI_INTEGRATION.md

@@ -50,8 +50,7 @@ Prompt prompt = new Prompt("What is the capital of France?", opts);
 ChatResponse response = client.call(prompt);
 ```
 
-Please
-find [an example in our Spring Boot application](../../sample-code/spring-app/src/main/java/com/sap/ai/sdk/app/controllers/SpringAiOrchestrationController.java).
+Please find [an example in our Spring Boot application](../../sample-code/spring-app/src/main/java/com/sap/ai/sdk/app/controllers/SpringAiOrchestrationController.java).
 
 ## Orchestration Masking
 
@@ -76,3 +75,27 @@ ChatResponse response = client.call(prompt);
 
 Please
 find [an example in our Spring Boot application](../../sample-code/spring-app/src/main/java/com/sap/ai/sdk/app/controllers/SpringAiOrchestrationController.java).
+
+## Stream chat completion
+
+It's possible to pass a stream of chat completion delta elements, e.g. from the application backend
+to the frontend in real-time.
+
+```java
+ChatModel client = new OrchestrationChatModel();
+OrchestrationModuleConfig config = new OrchestrationModuleConfig().withLlmConfig(GPT_35_TURBO);
+OrchestrationChatOptions opts = new OrchestrationChatOptions(config);
+
+Prompt prompt =
+    new Prompt(
+        "Can you give me the first 100 numbers of the Fibonacci sequence?", opts);
+Flux<ChatResponse> flux = client.stream(prompt);
+
+// also possible to keep only the chat completion text
+Flux<String> responseFlux = 
+    flux.map(chatResponse -> chatResponse.getResult().getOutput().getContent());
+```
+
+_Note: A Spring endpoint can return `Flux` instead of `ResponseEntity`._
+
+Please find [an example in our Spring Boot application](../../sample-code/spring-app/src/main/java/com/sap/ai/sdk/app/controllers/SpringAiOrchestrationController.java).

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

@@ -37,6 +37,19 @@ public ChatResponse completion() {
     return client.call(prompt);
   }
 
+  /**
+   * Asynchronous stream of an OpenAI chat request
+   *
+   * @return a stream of assistant message responses
+   */
+  @Nonnull
+  public Flux<ChatResponse> streamChatCompletion() {
+    val prompt =
+        new Prompt(
+            "Can you give me the first 100 numbers of the Fibonacci sequence?", defaultOptions);
+    return client.stream(prompt);
+  }
+
   /**
    * Chat request to OpenAI through the Orchestration service with a template.
    *
@@ -74,17 +87,4 @@ public ChatResponse masking() {
 
     return client.call(prompt);
   }
-
-  /**
-   * Asynchronous stream of an OpenAI chat request
-   *
-   * @return a stream of assistant message responses
-   */
-  @Nonnull
-  public Flux<ChatResponse> streamChatCompletion() {
-    val prompt =
-        new Prompt(
-            "Can you give me the first 100 numbers of the Fibonacci sequence?", defaultOptions);
-    return client.stream(prompt);
-  }
 }

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

@@ -3,9 +3,12 @@
 import static org.assertj.core.api.Assertions.assertThat;
 
 import com.sap.ai.sdk.app.services.SpringAiOrchestrationService;
+import java.util.concurrent.atomic.AtomicInteger;
+import lombok.extern.slf4j.Slf4j;
 import org.junit.jupiter.api.Test;
 import org.springframework.ai.chat.model.ChatResponse;
 
+@Slf4j
 public class SpringAiOrchestrationTest {
 
   SpringAiOrchestrationService service = new SpringAiOrchestrationService();
@@ -17,6 +20,26 @@ void testCompletion() {
     assertThat(response.getResult().getOutput().getContent()).contains("Paris");
   }
 
+  @Test
+  void testStreamChatCompletion() {
+    final var stream = service.streamChatCompletion().toStream();
+
+    final var filledDeltaCount = new AtomicInteger(0);
+    stream
+        // foreach consumes all elements, closing the stream at the end
+        .forEach(
+        delta -> {
+          log.info("delta: {}", delta);
+          if (!delta.getResult().getOutput().getContent().isEmpty()) {
+            filledDeltaCount.incrementAndGet();
+          }
+        });
+
+    // the first two and the last delta don't have any content
+    // see OpenAiChatCompletionDelta#getDeltaContent
+    assertThat(filledDeltaCount.get()).isGreaterThan(0);
+  }
+
   @Test
   void testTemplate() {
     ChatResponse response = service.template();