feat: [DevOps] Update orchestration specification

orchestration/src/main/java/com/sap/ai/sdk/orchestration/model/EmbeddingsModelDetails.java

@@ -37,6 +37,12 @@ public class EmbeddingsModelDetails
   @JsonProperty("params")
   private EmbeddingsModelParams params;
 
+  @JsonProperty("timeout")
+  private Integer timeout = 600;
+
+  @JsonProperty("max_retries")
+  private Integer maxRetries = 2;
+
   @JsonAnySetter @JsonAnyGetter
   private final Map<String, Object> cloudSdkCustomFields = new LinkedHashMap<>();
 
@@ -136,6 +142,75 @@ public void setParams(@Nullable final EmbeddingsModelParams params) {
     this.params = params;
   }
 
+  /**
+   * Set the timeout of this {@link EmbeddingsModelDetails} instance and return the same instance.
+   *
+   * @param timeout Timeout for the Embeddings request in seconds. This parameter is currently
+   *     ignored for Vertex AI models. Minimum: 1 Maximum: 600
+   * @return The same instance of this {@link EmbeddingsModelDetails} class
+   */
+  @Nonnull
+  public EmbeddingsModelDetails timeout(@Nullable final Integer timeout) {
+    this.timeout = timeout;
+    return this;
+  }
+
+  /**
+   * Timeout for the Embeddings request in seconds. This parameter is currently ignored for Vertex
+   * AI models. minimum: 1 maximum: 600
+   *
+   * @return timeout The timeout of this {@link EmbeddingsModelDetails} instance.
+   */
+  @Nonnull
+  public Integer getTimeout() {
+    return timeout;
+  }
+
+  /**
+   * Set the timeout of this {@link EmbeddingsModelDetails} instance.
+   *
+   * @param timeout Timeout for the Embeddings request in seconds. This parameter is currently
+   *     ignored for Vertex AI models. Minimum: 1 Maximum: 600
+   */
+  public void setTimeout(@Nullable final Integer timeout) {
+    this.timeout = timeout;
+  }
+
+  /**
+   * Set the maxRetries of this {@link EmbeddingsModelDetails} instance and return the same
+   * instance.
+   *
+   * @param maxRetries Maximum number of retries for the Embeddings request. This parameter is
+   *     currently ignored for Vertex AI models. Minimum: 0 Maximum: 5
+   * @return The same instance of this {@link EmbeddingsModelDetails} class
+   */
+  @Nonnull
+  public EmbeddingsModelDetails maxRetries(@Nullable final Integer maxRetries) {
+    this.maxRetries = maxRetries;
+    return this;
+  }
+
+  /**
+   * Maximum number of retries for the Embeddings request. This parameter is currently ignored for
+   * Vertex AI models. minimum: 0 maximum: 5
+   *
+   * @return maxRetries The maxRetries of this {@link EmbeddingsModelDetails} instance.
+   */
+  @Nonnull
+  public Integer getMaxRetries() {
+    return maxRetries;
+  }
+
+  /**
+   * Set the maxRetries of this {@link EmbeddingsModelDetails} instance.
+   *
+   * @param maxRetries Maximum number of retries for the Embeddings request. This parameter is
+   *     currently ignored for Vertex AI models. Minimum: 0 Maximum: 5
+   */
+  public void setMaxRetries(@Nullable final Integer maxRetries) {
+    this.maxRetries = maxRetries;
+  }
+
   /**
    * Get the names of the unrecognizable properties of the {@link EmbeddingsModelDetails}.
    *
@@ -178,6 +253,8 @@ public Map<String, Object> toMap() {
     if (name != null) declaredFields.put("name", name);
     if (version != null) declaredFields.put("version", version);
     if (params != null) declaredFields.put("params", params);
+    if (timeout != null) declaredFields.put("timeout", timeout);
+    if (maxRetries != null) declaredFields.put("maxRetries", maxRetries);
     return declaredFields;
   }
 
@@ -205,12 +282,14 @@ public boolean equals(@Nullable final java.lang.Object o) {
     return Objects.equals(this.cloudSdkCustomFields, embeddingsModelDetails.cloudSdkCustomFields)
         && Objects.equals(this.name, embeddingsModelDetails.name)
         && Objects.equals(this.version, embeddingsModelDetails.version)
-        && Objects.equals(this.params, embeddingsModelDetails.params);
+        && Objects.equals(this.params, embeddingsModelDetails.params)
+        && Objects.equals(this.timeout, embeddingsModelDetails.timeout)
+        && Objects.equals(this.maxRetries, embeddingsModelDetails.maxRetries);
   }
 
   @Override
   public int hashCode() {
-    return Objects.hash(name, version, params, cloudSdkCustomFields);
+    return Objects.hash(name, version, params, timeout, maxRetries, cloudSdkCustomFields);
   }
 
   @Override
@@ -221,6 +300,8 @@ public String toString() {
     sb.append("    name: ").append(toIndentedString(name)).append("\n");
     sb.append("    version: ").append(toIndentedString(version)).append("\n");
     sb.append("    params: ").append(toIndentedString(params)).append("\n");
+    sb.append("    timeout: ").append(toIndentedString(timeout)).append("\n");
+    sb.append("    maxRetries: ").append(toIndentedString(maxRetries)).append("\n");
     cloudSdkCustomFields.forEach(
         (k, v) ->
             sb.append("    ").append(k).append(": ").append(toIndentedString(v)).append("\n"));

orchestration/src/main/java/com/sap/ai/sdk/orchestration/model/LLMModelDetails.java

@@ -41,6 +41,12 @@ public class LLMModelDetails
   @JsonProperty("params")
   private Map<String, Object> params = new HashMap<>();
 
+  @JsonProperty("timeout")
+  private Integer timeout = 600;
+
+  @JsonProperty("max_retries")
+  private Integer maxRetries = 2;
+
   @JsonAnySetter @JsonAnyGetter
   private final Map<String, Object> cloudSdkCustomFields = new LinkedHashMap<>();
 
@@ -159,6 +165,74 @@ public void setParams(@Nullable final Map<String, Object> params) {
     this.params = params;
   }
 
+  /**
+   * Set the timeout of this {@link LLMModelDetails} instance and return the same instance.
+   *
+   * @param timeout Timeout for the LLM request in seconds. This parameter is currently ignored for
+   *     Vertex AI models. Minimum: 1 Maximum: 600
+   * @return The same instance of this {@link LLMModelDetails} class
+   */
+  @Nonnull
+  public LLMModelDetails timeout(@Nullable final Integer timeout) {
+    this.timeout = timeout;
+    return this;
+  }
+
+  /**
+   * Timeout for the LLM request in seconds. This parameter is currently ignored for Vertex AI
+   * models. minimum: 1 maximum: 600
+   *
+   * @return timeout The timeout of this {@link LLMModelDetails} instance.
+   */
+  @Nonnull
+  public Integer getTimeout() {
+    return timeout;
+  }
+
+  /**
+   * Set the timeout of this {@link LLMModelDetails} instance.
+   *
+   * @param timeout Timeout for the LLM request in seconds. This parameter is currently ignored for
+   *     Vertex AI models. Minimum: 1 Maximum: 600
+   */
+  public void setTimeout(@Nullable final Integer timeout) {
+    this.timeout = timeout;
+  }
+
+  /**
+   * Set the maxRetries of this {@link LLMModelDetails} instance and return the same instance.
+   *
+   * @param maxRetries Maximum number of retries for the LLM request. This parameter is currently
+   *     ignored for Vertex AI models. Minimum: 0 Maximum: 5
+   * @return The same instance of this {@link LLMModelDetails} class
+   */
+  @Nonnull
+  public LLMModelDetails maxRetries(@Nullable final Integer maxRetries) {
+    this.maxRetries = maxRetries;
+    return this;
+  }
+
+  /**
+   * Maximum number of retries for the LLM request. This parameter is currently ignored for Vertex
+   * AI models. minimum: 0 maximum: 5
+   *
+   * @return maxRetries The maxRetries of this {@link LLMModelDetails} instance.
+   */
+  @Nonnull
+  public Integer getMaxRetries() {
+    return maxRetries;
+  }
+
+  /**
+   * Set the maxRetries of this {@link LLMModelDetails} instance.
+   *
+   * @param maxRetries Maximum number of retries for the LLM request. This parameter is currently
+   *     ignored for Vertex AI models. Minimum: 0 Maximum: 5
+   */
+  public void setMaxRetries(@Nullable final Integer maxRetries) {
+    this.maxRetries = maxRetries;
+  }
+
   /**
    * Get the names of the unrecognizable properties of the {@link LLMModelDetails}.
    *
@@ -200,6 +274,8 @@ public Map<String, Object> toMap() {
     if (name != null) declaredFields.put("name", name);
     if (version != null) declaredFields.put("version", version);
     if (params != null) declaredFields.put("params", params);
+    if (timeout != null) declaredFields.put("timeout", timeout);
+    if (maxRetries != null) declaredFields.put("maxRetries", maxRetries);
     return declaredFields;
   }
 
@@ -227,12 +303,14 @@ public boolean equals(@Nullable final java.lang.Object o) {
     return Objects.equals(this.cloudSdkCustomFields, llMModelDetails.cloudSdkCustomFields)
         && Objects.equals(this.name, llMModelDetails.name)
         && Objects.equals(this.version, llMModelDetails.version)
-        && Objects.equals(this.params, llMModelDetails.params);
+        && Objects.equals(this.params, llMModelDetails.params)
+        && Objects.equals(this.timeout, llMModelDetails.timeout)
+        && Objects.equals(this.maxRetries, llMModelDetails.maxRetries);
   }
 
   @Override
   public int hashCode() {
-    return Objects.hash(name, version, params, cloudSdkCustomFields);
+    return Objects.hash(name, version, params, timeout, maxRetries, cloudSdkCustomFields);
   }
 
   @Override
@@ -243,6 +321,8 @@ public String toString() {
     sb.append("    name: ").append(toIndentedString(name)).append("\n");
     sb.append("    version: ").append(toIndentedString(version)).append("\n");
     sb.append("    params: ").append(toIndentedString(params)).append("\n");
+    sb.append("    timeout: ").append(toIndentedString(timeout)).append("\n");
+    sb.append("    maxRetries: ").append(toIndentedString(maxRetries)).append("\n");
     cloudSdkCustomFields.forEach(
         (k, v) ->
             sb.append("    ").append(k).append(": ").append(toIndentedString(v)).append("\n"));

orchestration/src/main/resources/spec/orchestration.yaml

@@ -173,7 +173,19 @@ components:
           type: string
           default: "latest"
         params:
-          $ref: "#/components/schemas/EmbeddingsModelParams"   
+          $ref: "#/components/schemas/EmbeddingsModelParams"
+        timeout:
+          description: Timeout for the Embeddings request in seconds. This parameter is currently ignored for Vertex AI models.
+          type: integer
+          default: 600
+          minimum: 1
+          maximum: 600
+        max_retries:
+          description: Maximum number of retries for the Embeddings request. This parameter is currently ignored for Vertex AI models.
+          type: integer
+          default: 2
+          minimum: 0
+          maximum: 5
     EmbeddingsModelParams:
       type: object
       description: Additional parameters for generating input's embeddings. Default values are used for mandatory parameters.
@@ -828,6 +840,18 @@ components:
             n: 2
             stream_options:
               include_usage: true
+        timeout:
+          description: Timeout for the LLM request in seconds. This parameter is currently ignored for Vertex AI models.
+          type: integer
+          default: 600
+          minimum: 1
+          maximum: 600
+        max_retries:
+          description: Maximum number of retries for the LLM request. This parameter is currently ignored for Vertex AI models.
+          type: integer
+          default: 2
+          minimum: 0
+          maximum: 5
 
     # --- Templating Module with User Defined Template ---
     # response_format api definition taken from: https://github.com/openai/openai-openapi/blob/e0cb2d721753e13e69e918465795d6e9f87ab15a/openapi.yaml#L12286

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

@@ -1400,6 +1400,8 @@ void testEmbeddingCallWithMasking() {
                             "model": {
                               "name": "text-embedding-3-large",
                               "version": "latest",
+                              "timeout" : 600,
+                              "max_retries" : 2,
                               "params": {
                                 "encoding_format": "float",
                                 "dimensions": 5,

orchestration/src/test/resources/chatMemory.json

@@ -5,7 +5,9 @@
         "model": {
           "name": "gpt-4o",
           "params": {},
-          "version": "latest"
+          "version": "latest",
+          "timeout" : 600,
+          "max_retries" : 2
         },
         "prompt": {
           "template": [
@@ -31,4 +33,4 @@
   },
   "placeholder_values": {},
   "messages_history": []
-}
+}

orchestration/src/test/resources/filteringLooseRequest.json

@@ -12,7 +12,9 @@
             "top_p": 1,
             "n": 1
           },
-          "version": "latest"
+          "version": "latest",
+          "timeout" : 600,
+          "max_retries" : 2
         },
         "prompt": {
           "template": [
@@ -63,4 +65,4 @@
   },
   "placeholder_values": {},
   "messages_history": []
-}
+}

orchestration/src/test/resources/groundingHelpSapComRequest.json

@@ -12,7 +12,9 @@
             "top_p": 1,
             "n": 1
           },
-          "version": "latest"
+          "version": "latest",
+          "timeout" : 600,
+          "max_retries" : 2
         },
         "prompt": {
           "template": [
@@ -53,4 +55,4 @@
     "userMessage": "What is a fuzzy search?"
   },
   "messages_history": []
-}
+}

orchestration/src/test/resources/groundingRequest.json

@@ -12,7 +12,9 @@
             "top_p": 1,
             "n": 1
           },
-          "version": "latest"
+          "version": "latest",
+          "timeout" : 600,
+          "max_retries" : 2
         },
         "prompt": {
           "template": [
@@ -94,4 +96,4 @@
     "query": "String used for similarity search in database"
   },
   "messages_history": []
-}
+}

orchestration/src/test/resources/jsonObjectRequest.json

@@ -5,7 +5,9 @@
         "model": {
           "name": "gpt-4o-mini",
           "params": {},
-          "version": "latest"
+          "version": "latest",
+          "timeout" : 600,
+          "max_retries" : 2
         },
         "prompt": {
           "template": [
@@ -29,4 +31,4 @@
   },
   "placeholder_values": {},
   "messages_history": []
-}
+}