feat: [vertexai] update gapic library to the latest version (#11129)

PiperOrigin-RevId: 672705511

Co-authored-by: Jaycee Li <jayceeli@google.com>

Author: copybara-service[bot]

java-vertexai/google-cloud-vertexai/src/main/java/com/google/cloud/vertexai/api/LlmUtilityServiceClient.java

@@ -315,7 +315,7 @@ public LlmUtilityServiceStub getStub() {
    *
    * @param endpoint Required. The name of the Endpoint requested to perform token counting. Format:
    *     `projects/{project}/locations/{location}/endpoints/{endpoint}`
-   * @param instances Required. The instances that are the input to token counting call. Schema is
+   * @param instances Optional. The instances that are the input to token counting call. Schema is
    *     identical to the prediction schema of the underlying model.
    * @throws com.google.api.gax.rpc.ApiException if the remote call fails
    */
@@ -351,7 +351,7 @@ public final CountTokensResponse countTokens(EndpointName endpoint, List<Value>
    *
    * @param endpoint Required. The name of the Endpoint requested to perform token counting. Format:
    *     `projects/{project}/locations/{location}/endpoints/{endpoint}`
-   * @param instances Required. The instances that are the input to token counting call. Schema is
+   * @param instances Optional. The instances that are the input to token counting call. Schema is
    *     identical to the prediction schema of the underlying model.
    * @throws com.google.api.gax.rpc.ApiException if the remote call fails
    */
@@ -383,6 +383,8 @@ public final CountTokensResponse countTokens(String endpoint, List<Value> instan
    *           .setModel("model104069929")
    *           .addAllInstances(new ArrayList<Value>())
    *           .addAllContents(new ArrayList<Content>())
+   *           .setSystemInstruction(Content.newBuilder().build())
+   *           .addAllTools(new ArrayList<Tool>())
    *           .build();
    *   CountTokensResponse response = llmUtilityServiceClient.countTokens(request);
    * }
@@ -417,6 +419,8 @@ public final CountTokensResponse countTokens(CountTokensRequest request) {
    *           .setModel("model104069929")
    *           .addAllInstances(new ArrayList<Value>())
    *           .addAllContents(new ArrayList<Content>())
+   *           .setSystemInstruction(Content.newBuilder().build())
+   *           .addAllTools(new ArrayList<Tool>())
    *           .build();
    *   ApiFuture<CountTokensResponse> future =
    *       llmUtilityServiceClient.countTokensCallable().futureCall(request);
@@ -451,7 +455,7 @@ public final UnaryCallable<CountTokensRequest, CountTokensResponse> countTokensC
    *
    * @param endpoint Required. The name of the Endpoint requested to get lists of tokens and token
    *     ids.
-   * @param instances Required. The instances that are the input to token computing API call. Schema
+   * @param instances Optional. The instances that are the input to token computing API call. Schema
    *     is identical to the prediction schema of the text model, even for the non-text models, like
    *     chat models, or Codey models.
    * @throws com.google.api.gax.rpc.ApiException if the remote call fails
@@ -488,7 +492,7 @@ public final ComputeTokensResponse computeTokens(EndpointName endpoint, List<Val
    *
    * @param endpoint Required. The name of the Endpoint requested to get lists of tokens and token
    *     ids.
-   * @param instances Required. The instances that are the input to token computing API call. Schema
+   * @param instances Optional. The instances that are the input to token computing API call. Schema
    *     is identical to the prediction schema of the text model, even for the non-text models, like
    *     chat models, or Codey models.
    * @throws com.google.api.gax.rpc.ApiException if the remote call fails
@@ -519,6 +523,8 @@ public final ComputeTokensResponse computeTokens(String endpoint, List<Value> in
    *                       "[PROJECT]", "[LOCATION]", "[ENDPOINT]")
    *                   .toString())
    *           .addAllInstances(new ArrayList<Value>())
+   *           .setModel("model104069929")
+   *           .addAllContents(new ArrayList<Content>())
    *           .build();
    *   ComputeTokensResponse response = llmUtilityServiceClient.computeTokens(request);
    * }
@@ -551,6 +557,8 @@ public final ComputeTokensResponse computeTokens(ComputeTokensRequest request) {
    *                       "[PROJECT]", "[LOCATION]", "[ENDPOINT]")
    *                   .toString())
    *           .addAllInstances(new ArrayList<Value>())
+   *           .setModel("model104069929")
+   *           .addAllContents(new ArrayList<Content>())
    *           .build();
    *   ApiFuture<ComputeTokensResponse> future =
    *       llmUtilityServiceClient.computeTokensCallable().futureCall(request);

java-vertexai/google-cloud-vertexai/src/main/java/com/google/cloud/vertexai/api/PredictionServiceClient.java

@@ -1378,8 +1378,12 @@ public final UnaryCallable<ExplainRequest, ExplainResponse> explainCallable() {
    * }
    * }</pre>
    *
-   * @param model Required. The name of the publisher model requested to serve the prediction.
-   *     Format: `projects/{project}/locations/{location}/publishers/&#42;/models/&#42;`
+   * @param model Required. The fully qualified name of the publisher model or tuned model endpoint
+   *     to use.
+   *     <p>Publisher model format:
+   *     `projects/{project}/locations/{location}/publishers/&#42;/models/&#42;`
+   *     <p>Tuned model endpoint format:
+   *     `projects/{project}/locations/{location}/endpoints/{endpoint}`
    * @param contents Required. The content of the current conversation with the model.
    *     <p>For single-turn queries, this is a single instance. For multi-turn queries, this is a
    *     repeated field that contains conversation history + latest request.

java-vertexai/google-cloud-vertexai/src/main/java/com/google/cloud/vertexai/api/stub/EndpointServiceStubSettings.java

@@ -22,6 +22,7 @@
 import com.google.api.core.ApiFunction;
 import com.google.api.core.ApiFuture;
 import com.google.api.core.BetaApi;
+import com.google.api.core.ObsoleteApi;
 import com.google.api.gax.core.GaxProperties;
 import com.google.api.gax.core.GoogleCredentialsProvider;
 import com.google.api.gax.core.InstantiatingExecutorProvider;
@@ -402,6 +403,7 @@ public static InstantiatingExecutorProvider.Builder defaultExecutorProviderBuild
   }
 
   /** Returns the default service endpoint. */
+  @ObsoleteApi("Use getEndpoint() instead")
   public static String getDefaultEndpoint() {
     return "aiplatform.googleapis.com:443";
   }

java-vertexai/google-cloud-vertexai/src/main/java/com/google/cloud/vertexai/api/stub/GrpcPredictionServiceStub.java

@@ -385,24 +385,12 @@ protected GrpcPredictionServiceStub(
         streamDirectPredictTransportSettings =
             GrpcCallSettings.<StreamDirectPredictRequest, StreamDirectPredictResponse>newBuilder()
                 .setMethodDescriptor(streamDirectPredictMethodDescriptor)
-                .setParamsExtractor(
-                    request -> {
-                      RequestParamsBuilder builder = RequestParamsBuilder.create();
-                      builder.add("endpoint", String.valueOf(request.getEndpoint()));
-                      return builder.build();
-                    })
                 .build();
     GrpcCallSettings<StreamDirectRawPredictRequest, StreamDirectRawPredictResponse>
         streamDirectRawPredictTransportSettings =
             GrpcCallSettings
                 .<StreamDirectRawPredictRequest, StreamDirectRawPredictResponse>newBuilder()
                 .setMethodDescriptor(streamDirectRawPredictMethodDescriptor)
-                .setParamsExtractor(
-                    request -> {
-                      RequestParamsBuilder builder = RequestParamsBuilder.create();
-                      builder.add("endpoint", String.valueOf(request.getEndpoint()));
-                      return builder.build();
-                    })
                 .build();
     GrpcCallSettings<StreamingPredictRequest, StreamingPredictResponse>
         streamingPredictTransportSettings =