Merge branch 'main' into chat-memory

Author: CharlesDuboisSAP

docs/guides/ORCHESTRATION_CHAT_COMPLETION.md

@@ -119,6 +119,22 @@ var result = client.chatCompletion(prompt, configWithTemplate);
 
 In this case the template is defined with the placeholder `{{?language}}` which is replaced by the value `German` in the input parameters.
 
+Alternatively, you can use already prepared templates from the [Prompt Registry](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/prompt-registry) of SAP AI Core instead of passing a template in the request yourself.
+
+```java
+var template = TemplateConfig.reference().byId("21cb1358-0bf1-4f43-870b-00f14d0f9f16");
+var configWithTemplate = config.withTemplateConfig(template);
+
+var inputParams = Map.of("language", "Italian", "input", "cloud ERP systems");
+var prompt = new OrchestrationPrompt(inputParams);
+
+var result = client.chatCompletion(prompt, configWithTemplate);
+```
+
+A prompt template can be referenced either by ID as above, or by using a combination of name, scenario, and version. For details on storing a template in the Prompt Registry, refer to [this guide](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-prompt-template-imperative).
+
+You can find [some examples](https://github.com/SAP/ai-sdk-java/tree/main/sample-code/spring-app/src/main/java/com/sap/ai/sdk/app/services/OrchestrationService.java) in our Spring Boot application demonstrating using templates from Prompt Registry.
+
 ## Message history
 
 Include a message history to maintain context in the conversation:

docs/release-notes/release_notes.md

@@ -13,6 +13,7 @@
 ### ✨ New Functionality
 
 - [Orchestration] [Add Spring AI Chat Memory support](https://github.com/SAP/ai-sdk-java/tree/main/docs/guides/SPRING_AI_INTEGRATION.md#chat-memory)
+- [Orchestration] [Prompt templates can be consumed from registry.](https://github.com/SAP/ai-sdk-java/tree/main/docs/guides/ORCHESTRATION_CHAT_COMPLETION.md#Chat-completion-with-Templates)
 
 ### 📈 Improvements
 

foundation-models/openai/src/main/java/com/sap/ai/sdk/foundationmodels/openai/OpenAiError.java

@@ -8,7 +8,6 @@
 import lombok.AccessLevel;
 import lombok.AllArgsConstructor;
 import lombok.Value;
-import lombok.experimental.Delegate;
 
 /**
  * Represents an error response from the OpenAI API.
@@ -20,7 +19,6 @@
 @AllArgsConstructor(onConstructor = @__({@JsonCreator}), access = AccessLevel.PROTECTED)
 public class OpenAiError implements ClientError {
   /** The original error response from the OpenAI API. */
-  @Delegate(types = {ClientError.class})
   ErrorResponse originalResponse;
 
   /**

orchestration/pom.xml

@@ -34,7 +34,7 @@
     <coverage.complexity>83%</coverage.complexity>
     <coverage.line>94%</coverage.line>
     <coverage.instruction>94%</coverage.instruction>
-    <coverage.branch>76%</coverage.branch>
+    <coverage.branch>75%</coverage.branch>
     <coverage.method>93%</coverage.method>
     <coverage.class>100%</coverage.class>
   </properties>

orchestration/src/main/java/com/sap/ai/sdk/orchestration/ConfigToRequestTransformer.java

@@ -5,6 +5,7 @@
 import com.sap.ai.sdk.orchestration.model.ModuleConfigs;
 import com.sap.ai.sdk.orchestration.model.OrchestrationConfig;
 import com.sap.ai.sdk.orchestration.model.Template;
+import com.sap.ai.sdk.orchestration.model.TemplateRef;
 import com.sap.ai.sdk.orchestration.model.TemplatingModuleConfig;
 import io.vavr.control.Option;
 import java.util.ArrayList;
@@ -47,6 +48,9 @@ static TemplatingModuleConfig toTemplateModuleConfig(
      * In this case, the request will fail, since the templating module will try to resolve the parameter.
      * To be fixed with https://github.tools.sap/AI/llm-orchestration/issues/662
      */
+    if (config instanceof TemplateRef) {
+      return config;
+    }
     val template = config instanceof Template t ? t : Template.create().template();
     val messages = template.getTemplate();
     val responseFormat = template.getResponseFormat();

orchestration/src/main/java/com/sap/ai/sdk/orchestration/OrchestrationError.java

@@ -4,10 +4,10 @@
 import com.google.common.annotations.Beta;
 import com.sap.ai.sdk.core.common.ClientError;
 import com.sap.ai.sdk.orchestration.model.ErrorResponse;
+import javax.annotation.Nonnull;
 import lombok.AccessLevel;
 import lombok.AllArgsConstructor;
 import lombok.Value;
-import lombok.experimental.Delegate;
 
 /**
  * Orchestration error response.
@@ -18,6 +18,17 @@
 @Value
 @Beta
 public class OrchestrationError implements ClientError {
-  @Delegate(types = {ClientError.class})
   ErrorResponse originalResponse;
+
+  /**
+   * Gets the error message from the contained original response.
+   *
+   * @return the error message
+   */
+  @Nonnull
+  public String getMessage() {
+    return originalResponse.getCode() == 500
+        ? originalResponse.getMessage() + " located in " + originalResponse.getLocation()
+        : originalResponse.getMessage();
+  }
 }

orchestration/src/test/java/com/sap/ai/sdk/orchestration/OrchestrationUnitTest.java

@@ -126,6 +126,21 @@ void testCompletion() {
     assertThat(result.getContent()).isNotEmpty();
   }
 
+  @Test
+  void testCompletionError() {
+    stubFor(
+        post(urlPathEqualTo("/completion"))
+            .willReturn(
+                aResponse()
+                    .withStatus(500)
+                    .withBodyFile("error500Response.json")
+                    .withHeader("Content-Type", "application/json")));
+
+    assertThatThrownBy(() -> client.chatCompletion(prompt, config))
+        .hasMessage(
+            "Request failed with status 500 Server Error and error message: 'Internal Server Error located in Masking Module - Masking'");
+  }
+
   @Test
   void testGrounding() throws IOException {
     stubFor(
@@ -185,9 +200,10 @@ void testGrounding() throws IOException {
             "First chunk```Second chunk```Last found chunk");
     assertThat(groundingModule.getData()).isEqualTo(groundingData);
 
-    final String requestBody = new String(fileLoader.apply("groundingRequest.json").readAllBytes());
-    verify(
-        postRequestedFor(urlPathEqualTo("/completion")).withRequestBody(equalToJson(requestBody)));
+    try (var requestInputStream = fileLoader.apply("groundingRequest.json")) {
+      final String request = new String(requestInputStream.readAllBytes());
+      verify(postRequestedFor(urlPathEqualTo("/completion")).withRequestBody(equalToJson(request)));
+    }
   }
 
   @Test
@@ -864,4 +880,56 @@ void testResponseFormatText() throws IOException {
       verify(postRequestedFor(anyUrl()).withRequestBody(equalToJson(request)));
     }
   }
+
+  @Test
+  void testTemplateFromPromptRegistryById() throws IOException {
+    {
+      stubFor(
+          post(anyUrl())
+              .willReturn(
+                  aResponse()
+                      .withBodyFile("templateReferenceResponse.json")
+                      .withHeader("Content-Type", "application/json")));
+
+      var template = TemplateConfig.reference().byId("21cb1358-0bf1-4f43-870b-00f14d0f9f16");
+      var configWithTemplate = config.withTemplateConfig(template);
+
+      var inputParams = Map.of("language", "Italian", "input", "Cloud ERP systems");
+      var prompt = new OrchestrationPrompt(inputParams);
+
+      final var response = client.chatCompletion(prompt, configWithTemplate);
+      assertThat(response.getContent()).startsWith("I sistemi ERP (Enterprise Resource Planning)");
+      assertThat(response.getOriginalResponse().getModuleResults().getTemplating()).hasSize(2);
+
+      try (var requestInputStream = fileLoader.apply("templateReferenceByIdRequest.json")) {
+        final String request = new String(requestInputStream.readAllBytes());
+        verify(postRequestedFor(anyUrl()).withRequestBody(equalToJson(request)));
+      }
+    }
+  }
+
+  @Test
+  void testTemplateFromPromptRegistryByScenario() throws IOException {
+    stubFor(
+        post(anyUrl())
+            .willReturn(
+                aResponse()
+                    .withBodyFile("templateReferenceResponse.json")
+                    .withHeader("Content-Type", "application/json")));
+
+    var template = TemplateConfig.reference().byScenario("test").name("test").version("0.0.1");
+    var configWithTemplate = config.withTemplateConfig(template);
+
+    var inputParams = Map.of("language", "Italian", "input", "Cloud ERP systems");
+    var prompt = new OrchestrationPrompt(inputParams);
+
+    final var response = client.chatCompletion(prompt, configWithTemplate);
+    assertThat(response.getContent()).startsWith("I sistemi ERP (Enterprise Resource Planning)");
+    assertThat(response.getOriginalResponse().getModuleResults().getTemplating()).hasSize(2);
+
+    try (var requestInputStream = fileLoader.apply("templateReferenceByScenarioRequest.json")) {
+      final String request = new String(requestInputStream.readAllBytes());
+      verify(postRequestedFor(anyUrl()).withRequestBody(equalToJson(request)));
+    }
+  }
 }

orchestration/src/test/resources/__files/error500Response.json

@@ -0,0 +1,14 @@
+{
+  "request_id": "d647775b-725b-428a-90b7-348cbf30f7f4",
+  "code": 500,
+  "message": "Internal Server Error",
+  "location": "Masking Module - Masking",
+  "module_results": {
+    "templating": [
+      {
+        "role": "user",
+        "content": "yo"
+      }
+    ]
+  }
+}

orchestration/src/test/resources/__files/templateReferenceResponse.json

@@ -0,0 +1,59 @@
+{
+  "request_id": "c02a6e4c-5552-4a72-a801-b6512d4f2f2a",
+  "module_results": {
+    "templating": [
+      {
+        "role": "system",
+        "content": "Please answer in Italian"
+      },
+      {
+        "role": "user",
+        "content": "Give me a short introduction of Cloud ERP systems."
+      }
+    ],
+    "llm": {
+      "id": "chatcmpl-B6zYkaS7gjo5Ye6U87iK0B2dp4hde",
+      "object": "chat.completion",
+      "created": 1741006302,
+      "model": "gpt-4o-2024-08-06",
+      "system_fingerprint": "fp_b705f0c291",
+      "choices": [
+        {
+          "index": 0,
+          "message": {
+            "role": "assistant",
+            "content": "I sistemi ERP (Enterprise Resource Planning) basati su cloud sono soluzioni software che consentono alle aziende di gestire e integrare le loro operazioni aziendali principali attraverso una piattaforma centralizzata accessibile via internet. A differenza dei"
+          },
+          "finish_reason": "length"
+        }
+      ],
+      "usage": {
+        "completion_tokens": 50,
+        "prompt_tokens": 25,
+        "total_tokens": 75
+      }
+    }
+  },
+  "orchestration_result": {
+    "id": "chatcmpl-B6zYkaS7gjo5Ye6U87iK0B2dp4hde",
+    "object": "chat.completion",
+    "created": 1741006302,
+    "model": "gpt-4o-2024-08-06",
+    "system_fingerprint": "fp_b705f0c291",
+    "choices": [
+      {
+        "index": 0,
+        "message": {
+          "role": "assistant",
+          "content": "I sistemi ERP (Enterprise Resource Planning) basati su cloud sono soluzioni software che consentono alle aziende di gestire e integrare le loro operazioni aziendali principali attraverso una piattaforma centralizzata accessibile via internet. A differenza dei"
+        },
+        "finish_reason": "length"
+      }
+    ],
+    "usage": {
+      "completion_tokens": 50,
+      "prompt_tokens": 25,
+      "total_tokens": 75
+    }
+  }
+}

orchestration/src/test/resources/templateReferenceByIdRequest.json

@@ -0,0 +1,29 @@
+{
+  "orchestration_config" : {
+    "module_configurations" : {
+      "llm_module_config" : {
+        "model_name" : "gpt-4o",
+        "model_params" : {
+          "max_tokens" : 50,
+          "temperature" : 0.1,
+          "frequency_penalty" : 0,
+          "presence_penalty" : 0,
+          "top_p" : 1,
+          "n" : 1
+        },
+        "model_version" : "latest"
+      },
+      "templating_module_config" : {
+        "template_ref" : {
+          "id" : "21cb1358-0bf1-4f43-870b-00f14d0f9f16"
+        }
+      }
+    },
+    "stream" : false
+  },
+  "input_params" : {
+    "input" : "Cloud ERP systems",
+    "language" : "Italian"
+  },
+  "messages_history" : [ ]
+}