google-cloud-ai_platform-v1 0.34.0 → 0.35.0

data/lib/google/cloud/aiplatform/v1/prediction_service_pb.rb

@@ -14,7 +14,7 @@ require 'google/cloud/aiplatform/v1/types_pb'
 require 'google/protobuf/struct_pb'
 
 
-descriptor_data = "\n3google/cloud/aiplatform/v1/prediction_service.proto\x12\x1agoogle.cloud.aiplatform.v1\x1a\x1cgoogle/api/annotations.proto\x1a\x17google/api/client.proto\x1a\x1fgoogle/api/field_behavior.proto\x1a\x19google/api/httpbody.proto\x1a\x19google/api/resource.proto\x1a,google/cloud/aiplatform/v1/explanation.proto\x1a&google/cloud/aiplatform/v1/types.proto\x1a\x1cgoogle/protobuf/struct.proto\"\xaa\x01\n\x0ePredictRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12.\n\tinstances\x18\x02 \x03(\x0b\x32\x16.google.protobuf.ValueB\x03\xe0\x41\x02\x12*\n\nparameters\x18\x03 \x01(\x0b\x32\x16.google.protobuf.Value\"\x80\x02\n\x0fPredictResponse\x12+\n\x0bpredictions\x18\x01 \x03(\x0b\x32\x16.google.protobuf.Value\x12\x19\n\x11\x64\x65ployed_model_id\x18\x02 \x01(\t\x12\x36\n\x05model\x18\x03 \x01(\tB\'\xe0\x41\x03\xfa\x41!\n\x1f\x61iplatform.googleapis.com/Model\x12\x1d\n\x10model_version_id\x18\x05 \x01(\tB\x03\xe0\x41\x03\x12\x1f\n\x12model_display_name\x18\x04 \x01(\tB\x03\xe0\x41\x03\x12-\n\x08metadata\x18\x06 \x01(\x0b\x32\x16.google.protobuf.ValueB\x03\xe0\x41\x03\"z\n\x11RawPredictRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12\'\n\thttp_body\x18\x02 \x01(\x0b\x32\x14.google.api.HttpBody\"\xc3\x01\n\x17StreamingPredictRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12\x32\n\x06inputs\x18\x02 \x03(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\x12\x36\n\nparameters\x18\x03 \x01(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\"\x87\x01\n\x18StreamingPredictResponse\x12\x33\n\x07outputs\x18\x01 \x03(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\x12\x36\n\nparameters\x18\x02 \x01(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\"\x9d\x02\n\x0e\x45xplainRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12.\n\tinstances\x18\x02 \x03(\x0b\x32\x16.google.protobuf.ValueB\x03\xe0\x41\x02\x12*\n\nparameters\x18\x04 \x01(\x0b\x32\x16.google.protobuf.Value\x12V\n\x19\x65xplanation_spec_override\x18\x05 \x01(\x0b\x32\x33.google.cloud.aiplatform.v1.ExplanationSpecOverride\x12\x19\n\x11\x64\x65ployed_model_id\x18\x03 \x01(\t\"\x98\x01\n\x0f\x45xplainResponse\x12=\n\x0c\x65xplanations\x18\x01 \x03(\x0b\x32\'.google.cloud.aiplatform.v1.Explanation\x12\x19\n\x11\x64\x65ployed_model_id\x18\x02 \x01(\t\x12+\n\x0bpredictions\x18\x03 \x03(\x0b\x32\x16.google.protobuf.Value\"\x82\x01\n\x12\x43ountTokensRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12.\n\tinstances\x18\x02 \x03(\x0b\x32\x16.google.protobuf.ValueB\x03\xe0\x41\x02\"N\n\x13\x43ountTokensResponse\x12\x14\n\x0ctotal_tokens\x18\x01 \x01(\x05\x12!\n\x19total_billable_characters\x18\x02 \x01(\x05\x32\x8f\t\n\x11PredictionService\x12\x94\x02\n\x07Predict\x12*.google.cloud.aiplatform.v1.PredictRequest\x1a+.google.cloud.aiplatform.v1.PredictResponse\"\xaf\x01\x82\xd3\xe4\x93\x02\x88\x01\"9/v1/{endpoint=projects/*/locations/*/endpoints/*}:predict:\x01*ZH\"C/v1/{endpoint=projects/*/locations/*/publishers/*/models/*}:predict:\x01*\xda\x41\x1d\x65ndpoint,instances,parameters\x12\xfe\x01\n\nRawPredict\x12-.google.cloud.aiplatform.v1.RawPredictRequest\x1a\x14.google.api.HttpBody\"\xaa\x01\x82\xd3\xe4\x93\x02\x8e\x01\"</v1/{endpoint=projects/*/locations/*/endpoints/*}:rawPredict:\x01*ZK\"F/v1/{endpoint=projects/*/locations/*/publishers/*/models/*}:rawPredict:\x01*\xda\x41\x12\x65ndpoint,http_body\x12\xb5\x02\n\x16ServerStreamingPredict\x12\x33.google.cloud.aiplatform.v1.StreamingPredictRequest\x1a\x34.google.cloud.aiplatform.v1.StreamingPredictResponse\"\xad\x01\x82\xd3\xe4\x93\x02\xa6\x01\"H/v1/{endpoint=projects/*/locations/*/endpoints/*}:serverStreamingPredict:\x01*ZW\"R/v1/{endpoint=projects/*/locations/*/publishers/*/models/*}:serverStreamingPredict:\x01*0\x01\x12\xda\x01\n\x07\x45xplain\x12*.google.cloud.aiplatform.v1.ExplainRequest\x1a+.google.cloud.aiplatform.v1.ExplainResponse\"v\x82\xd3\xe4\x93\x02>\"9/v1/{endpoint=projects/*/locations/*/endpoints/*}:explain:\x01*\xda\x41/endpoint,instances,parameters,deployed_model_id\x1aM\xca\x41\x19\x61iplatform.googleapis.com\xd2\x41.https://www.googleapis.com/auth/cloud-platformB\xd4\x01\n\x1e\x63om.google.cloud.aiplatform.v1B\x16PredictionServiceProtoP\x01Z>cloud.google.com/go/aiplatform/apiv1/aiplatformpb;aiplatformpb\xaa\x02\x1aGoogle.Cloud.AIPlatform.V1\xca\x02\x1aGoogle\\Cloud\\AIPlatform\\V1\xea\x02\x1dGoogle::Cloud::AIPlatform::V1b\x06proto3"
+descriptor_data = "\n3google/cloud/aiplatform/v1/prediction_service.proto\x12\x1agoogle.cloud.aiplatform.v1\x1a\x1cgoogle/api/annotations.proto\x1a\x17google/api/client.proto\x1a\x1fgoogle/api/field_behavior.proto\x1a\x19google/api/httpbody.proto\x1a\x19google/api/resource.proto\x1a,google/cloud/aiplatform/v1/explanation.proto\x1a&google/cloud/aiplatform/v1/types.proto\x1a\x1cgoogle/protobuf/struct.proto\"\xaa\x01\n\x0ePredictRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12.\n\tinstances\x18\x02 \x03(\x0b\x32\x16.google.protobuf.ValueB\x03\xe0\x41\x02\x12*\n\nparameters\x18\x03 \x01(\x0b\x32\x16.google.protobuf.Value\"\x80\x02\n\x0fPredictResponse\x12+\n\x0bpredictions\x18\x01 \x03(\x0b\x32\x16.google.protobuf.Value\x12\x19\n\x11\x64\x65ployed_model_id\x18\x02 \x01(\t\x12\x36\n\x05model\x18\x03 \x01(\tB\'\xe0\x41\x03\xfa\x41!\n\x1f\x61iplatform.googleapis.com/Model\x12\x1d\n\x10model_version_id\x18\x05 \x01(\tB\x03\xe0\x41\x03\x12\x1f\n\x12model_display_name\x18\x04 \x01(\tB\x03\xe0\x41\x03\x12-\n\x08metadata\x18\x06 \x01(\x0b\x32\x16.google.protobuf.ValueB\x03\xe0\x41\x03\"z\n\x11RawPredictRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12\'\n\thttp_body\x18\x02 \x01(\x0b\x32\x14.google.api.HttpBody\"\xc0\x01\n\x14\x44irectPredictRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12\x32\n\x06inputs\x18\x02 \x03(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\x12\x36\n\nparameters\x18\x03 \x01(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\"\x84\x01\n\x15\x44irectPredictResponse\x12\x33\n\x07outputs\x18\x01 \x03(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\x12\x36\n\nparameters\x18\x02 \x01(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\"{\n\x17\x44irectRawPredictRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12\x13\n\x0bmethod_name\x18\x02 \x01(\t\x12\r\n\x05input\x18\x03 \x01(\x0c\"*\n\x18\x44irectRawPredictResponse\x12\x0e\n\x06output\x18\x01 \x01(\x0c\"\xc3\x01\n\x17StreamingPredictRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12\x32\n\x06inputs\x18\x02 \x03(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\x12\x36\n\nparameters\x18\x03 \x01(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\"\x87\x01\n\x18StreamingPredictResponse\x12\x33\n\x07outputs\x18\x01 \x03(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\x12\x36\n\nparameters\x18\x02 \x01(\x0b\x32\".google.cloud.aiplatform.v1.Tensor\"~\n\x1aStreamingRawPredictRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12\x13\n\x0bmethod_name\x18\x02 \x01(\t\x12\r\n\x05input\x18\x03 \x01(\x0c\"-\n\x1bStreamingRawPredictResponse\x12\x0e\n\x06output\x18\x01 \x01(\x0c\"\x9d\x02\n\x0e\x45xplainRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12.\n\tinstances\x18\x02 \x03(\x0b\x32\x16.google.protobuf.ValueB\x03\xe0\x41\x02\x12*\n\nparameters\x18\x04 \x01(\x0b\x32\x16.google.protobuf.Value\x12V\n\x19\x65xplanation_spec_override\x18\x05 \x01(\x0b\x32\x33.google.cloud.aiplatform.v1.ExplanationSpecOverride\x12\x19\n\x11\x64\x65ployed_model_id\x18\x03 \x01(\t\"\x98\x01\n\x0f\x45xplainResponse\x12=\n\x0c\x65xplanations\x18\x01 \x03(\x0b\x32\'.google.cloud.aiplatform.v1.Explanation\x12\x19\n\x11\x64\x65ployed_model_id\x18\x02 \x01(\t\x12+\n\x0bpredictions\x18\x03 \x03(\x0b\x32\x16.google.protobuf.Value\"\x82\x01\n\x12\x43ountTokensRequest\x12<\n\x08\x65ndpoint\x18\x01 \x01(\tB*\xe0\x41\x02\xfa\x41$\n\"aiplatform.googleapis.com/Endpoint\x12.\n\tinstances\x18\x02 \x03(\x0b\x32\x16.google.protobuf.ValueB\x03\xe0\x41\x02\"N\n\x13\x43ountTokensResponse\x12\x14\n\x0ctotal_tokens\x18\x01 \x01(\x05\x12!\n\x19total_billable_characters\x18\x02 \x01(\x05\x32\xb6\x0e\n\x11PredictionService\x12\x94\x02\n\x07Predict\x12*.google.cloud.aiplatform.v1.PredictRequest\x1a+.google.cloud.aiplatform.v1.PredictResponse\"\xaf\x01\x82\xd3\xe4\x93\x02\x88\x01\"9/v1/{endpoint=projects/*/locations/*/endpoints/*}:predict:\x01*ZH\"C/v1/{endpoint=projects/*/locations/*/publishers/*/models/*}:predict:\x01*\xda\x41\x1d\x65ndpoint,instances,parameters\x12\xfe\x01\n\nRawPredict\x12-.google.cloud.aiplatform.v1.RawPredictRequest\x1a\x14.google.api.HttpBody\"\xaa\x01\x82\xd3\xe4\x93\x02\x8e\x01\"</v1/{endpoint=projects/*/locations/*/endpoints/*}:rawPredict:\x01*ZK\"F/v1/{endpoint=projects/*/locations/*/publishers/*/models/*}:rawPredict:\x01*\xda\x41\x12\x65ndpoint,http_body\x12\xc0\x01\n\rDirectPredict\x12\x30.google.cloud.aiplatform.v1.DirectPredictRequest\x1a\x31.google.cloud.aiplatform.v1.DirectPredictResponse\"J\x82\xd3\xe4\x93\x02\x44\"?/v1/{endpoint=projects/*/locations/*/endpoints/*}:directPredict:\x01*\x12\xcc\x01\n\x10\x44irectRawPredict\x12\x33.google.cloud.aiplatform.v1.DirectRawPredictRequest\x1a\x34.google.cloud.aiplatform.v1.DirectRawPredictResponse\"M\x82\xd3\xe4\x93\x02G\"B/v1/{endpoint=projects/*/locations/*/endpoints/*}:directRawPredict:\x01*\x12\x83\x01\n\x10StreamingPredict\x12\x33.google.cloud.aiplatform.v1.StreamingPredictRequest\x1a\x34.google.cloud.aiplatform.v1.StreamingPredictResponse\"\x00(\x01\x30\x01\x12\xb5\x02\n\x16ServerStreamingPredict\x12\x33.google.cloud.aiplatform.v1.StreamingPredictRequest\x1a\x34.google.cloud.aiplatform.v1.StreamingPredictResponse\"\xad\x01\x82\xd3\xe4\x93\x02\xa6\x01\"H/v1/{endpoint=projects/*/locations/*/endpoints/*}:serverStreamingPredict:\x01*ZW\"R/v1/{endpoint=projects/*/locations/*/publishers/*/models/*}:serverStreamingPredict:\x01*0\x01\x12\x8c\x01\n\x13StreamingRawPredict\x12\x36.google.cloud.aiplatform.v1.StreamingRawPredictRequest\x1a\x37.google.cloud.aiplatform.v1.StreamingRawPredictResponse\"\x00(\x01\x30\x01\x12\xda\x01\n\x07\x45xplain\x12*.google.cloud.aiplatform.v1.ExplainRequest\x1a+.google.cloud.aiplatform.v1.ExplainResponse\"v\x82\xd3\xe4\x93\x02>\"9/v1/{endpoint=projects/*/locations/*/endpoints/*}:explain:\x01*\xda\x41/endpoint,instances,parameters,deployed_model_id\x1aM\xca\x41\x19\x61iplatform.googleapis.com\xd2\x41.https://www.googleapis.com/auth/cloud-platformB\xd4\x01\n\x1e\x63om.google.cloud.aiplatform.v1B\x16PredictionServiceProtoP\x01Z>cloud.google.com/go/aiplatform/apiv1/aiplatformpb;aiplatformpb\xaa\x02\x1aGoogle.Cloud.AIPlatform.V1\xca\x02\x1aGoogle\\Cloud\\AIPlatform\\V1\xea\x02\x1dGoogle::Cloud::AIPlatform::V1b\x06proto3"
 
 pool = Google::Protobuf::DescriptorPool.generated_pool
 
@@ -51,8 +51,14 @@ module Google
         PredictRequest = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.PredictRequest").msgclass
         PredictResponse = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.PredictResponse").msgclass
         RawPredictRequest = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.RawPredictRequest").msgclass
+        DirectPredictRequest = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.DirectPredictRequest").msgclass
+        DirectPredictResponse = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.DirectPredictResponse").msgclass
+        DirectRawPredictRequest = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.DirectRawPredictRequest").msgclass
+        DirectRawPredictResponse = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.DirectRawPredictResponse").msgclass
         StreamingPredictRequest = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.StreamingPredictRequest").msgclass
         StreamingPredictResponse = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.StreamingPredictResponse").msgclass
+        StreamingRawPredictRequest = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.StreamingRawPredictRequest").msgclass
+        StreamingRawPredictResponse = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.StreamingRawPredictResponse").msgclass
         ExplainRequest = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.ExplainRequest").msgclass
         ExplainResponse = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.ExplainResponse").msgclass
         CountTokensRequest = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.aiplatform.v1.CountTokensRequest").msgclass

data/lib/google/cloud/aiplatform/v1/prediction_service_services_pb.rb

@@ -47,9 +47,19 @@ module Google
             # [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this
             # prediction.
             rpc :RawPredict, ::Google::Cloud::AIPlatform::V1::RawPredictRequest, ::Google::Api::HttpBody
+            # Perform an unary online prediction request for Vertex first-party products
+            # and frameworks.
+            rpc :DirectPredict, ::Google::Cloud::AIPlatform::V1::DirectPredictRequest, ::Google::Cloud::AIPlatform::V1::DirectPredictResponse
+            # Perform an online prediction request through gRPC.
+            rpc :DirectRawPredict, ::Google::Cloud::AIPlatform::V1::DirectRawPredictRequest, ::Google::Cloud::AIPlatform::V1::DirectRawPredictResponse
+            # Perform a streaming online prediction request for Vertex first-party
+            # products and frameworks.
+            rpc :StreamingPredict, stream(::Google::Cloud::AIPlatform::V1::StreamingPredictRequest), stream(::Google::Cloud::AIPlatform::V1::StreamingPredictResponse)
             # Perform a server-side streaming online prediction request for Vertex
             # LLM streaming.
             rpc :ServerStreamingPredict, ::Google::Cloud::AIPlatform::V1::StreamingPredictRequest, stream(::Google::Cloud::AIPlatform::V1::StreamingPredictResponse)
+            # Perform a streaming online prediction request through gRPC.
+            rpc :StreamingRawPredict, stream(::Google::Cloud::AIPlatform::V1::StreamingRawPredictRequest), stream(::Google::Cloud::AIPlatform::V1::StreamingRawPredictResponse)
             # Perform an online explanation.
             #
             # If

data/proto_docs/google/api/client.rb

@@ -304,6 +304,19 @@ module Google
     #                seconds: 360 # 6 minutes
     #              total_poll_timeout:
     #                 seconds: 54000 # 90 minutes
+    # @!attribute [rw] auto_populated_fields
+    #   @return [::Array<::String>]
+    #     List of top-level fields of the request message, that should be
+    #     automatically populated by the client libraries based on their
+    #     (google.api.field_info).format. Currently supported format: UUID4.
+    #
+    #     Example of a YAML configuration:
+    #
+    #      publishing:
+    #        method_settings:
+    #          - selector: google.example.v1.ExampleService.CreateExample
+    #            auto_populated_fields:
+    #            - request_id
     class MethodSettings
       include ::Google::Protobuf::MessageExts
       extend ::Google::Protobuf::MessageExts::ClassMethods

data/proto_docs/google/cloud/aiplatform/v1/llm_utility_service.rb

@@ -0,0 +1,64 @@
+# frozen_string_literal: true
+
+# Copyright 2023 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Auto-generated by gapic-generator-ruby. DO NOT EDIT!
+
+
+module Google
+  module Cloud
+    module AIPlatform
+      module V1
+        # Request message for ComputeTokens RPC call.
+        # @!attribute [rw] endpoint
+        #   @return [::String]
+        #     Required. The name of the Endpoint requested to get lists of tokens and
+        #     token ids.
+        # @!attribute [rw] instances
+        #   @return [::Array<::Google::Protobuf::Value>]
+        #     Required. 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.
+        class ComputeTokensRequest
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # Tokens info with a list of tokens and the corresponding list of token ids.
+        # @!attribute [rw] tokens
+        #   @return [::Array<::String>]
+        #     A list of tokens from the input.
+        # @!attribute [rw] token_ids
+        #   @return [::Array<::Integer>]
+        #     A list of token ids from the input.
+        class TokensInfo
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # Response message for ComputeTokens RPC call.
+        # @!attribute [rw] tokens_info
+        #   @return [::Array<::Google::Cloud::AIPlatform::V1::TokensInfo>]
+        #     Lists of tokens info from the input. A ComputeTokensRequest could have
+        #     multiple instances with a prompt in each instance. We also need to return
+        #     lists of tokens info for the request with multiple instances.
+        class ComputeTokensResponse
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+      end
+    end
+  end
+end

data/proto_docs/google/cloud/aiplatform/v1/model.rb

@@ -663,6 +663,31 @@ module Google
         #       (Vertex AI makes this value available to your container code as the
         #       [`AIP_DEPLOYED_MODEL_ID` environment
         #       variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
+        # @!attribute [rw] grpc_ports
+        #   @return [::Array<::Google::Cloud::AIPlatform::V1::Port>]
+        #     Immutable. List of ports to expose from the container. Vertex AI sends gRPC
+        #     prediction requests that it receives to the first port on this list. Vertex
+        #     AI also sends liveness and health checks to this port.
+        #
+        #     If you do not specify this field, gRPC requests to the container will be
+        #     disabled.
+        #
+        #     Vertex AI does not use ports other than the first one listed. This field
+        #     corresponds to the `ports` field of the Kubernetes Containers v1 core API.
+        # @!attribute [rw] deployment_timeout
+        #   @return [::Google::Protobuf::Duration]
+        #     Immutable. Deployment timeout.
+        #     Limit for deployment timeout is 2 hours.
+        # @!attribute [rw] shared_memory_size_mb
+        #   @return [::Integer]
+        #     Immutable. The amount of the VM memory to reserve as the shared memory for
+        #     the model in megabytes.
+        # @!attribute [rw] startup_probe
+        #   @return [::Google::Cloud::AIPlatform::V1::Probe]
+        #     Immutable. Specification for Kubernetes startup probe.
+        # @!attribute [rw] health_probe
+        #   @return [::Google::Cloud::AIPlatform::V1::Probe]
+        #     Immutable. Specification for Kubernetes readiness probe.
         class ModelContainerSpec
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -712,6 +737,42 @@ module Google
             GENIE = 5
           end
         end
+
+        # Probe describes a health check to be performed against a container to
+        # determine whether it is alive or ready to receive traffic.
+        # @!attribute [rw] exec
+        #   @return [::Google::Cloud::AIPlatform::V1::Probe::ExecAction]
+        #     Exec specifies the action to take.
+        # @!attribute [rw] period_seconds
+        #   @return [::Integer]
+        #     How often (in seconds) to perform the probe. Default to 10 seconds.
+        #     Minimum value is 1. Must be less than timeout_seconds.
+        #
+        #     Maps to Kubernetes probe argument 'periodSeconds'.
+        # @!attribute [rw] timeout_seconds
+        #   @return [::Integer]
+        #     Number of seconds after which the probe times out. Defaults to 1 second.
+        #     Minimum value is 1. Must be greater or equal to period_seconds.
+        #
+        #     Maps to Kubernetes probe argument 'timeoutSeconds'.
+        class Probe
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+
+          # ExecAction specifies a command to execute.
+          # @!attribute [rw] command
+          #   @return [::Array<::String>]
+          #     Command is the command line to execute inside the container, the working
+          #     directory for the command is root ('/') in the container's filesystem.
+          #     The command is simply exec'd, it is not run inside a shell, so
+          #     traditional shell instructions ('|', etc) won't work. To use a shell, you
+          #     need to explicitly call out to that shell. Exit status of 0 is treated as
+          #     live/healthy and non-zero is unhealthy.
+          class ExecAction
+            include ::Google::Protobuf::MessageExts
+            extend ::Google::Protobuf::MessageExts::ClassMethods
+          end
+        end
       end
     end
   end

data/proto_docs/google/cloud/aiplatform/v1/prediction_service.rb

@@ -115,7 +115,72 @@ module Google
         end
 
         # Request message for
-        # [PredictionService.StreamingPredict][google.cloud.aiplatform.v1.PredictionService.StreamingPredict].
+        # {::Google::Cloud::AIPlatform::V1::PredictionService::Client#direct_predict PredictionService.DirectPredict}.
+        # @!attribute [rw] endpoint
+        #   @return [::String]
+        #     Required. The name of the Endpoint requested to serve the prediction.
+        #     Format:
+        #     `projects/{project}/locations/{location}/endpoints/{endpoint}`
+        # @!attribute [rw] inputs
+        #   @return [::Array<::Google::Cloud::AIPlatform::V1::Tensor>]
+        #     The prediction input.
+        # @!attribute [rw] parameters
+        #   @return [::Google::Cloud::AIPlatform::V1::Tensor]
+        #     The parameters that govern the prediction.
+        class DirectPredictRequest
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # Response message for
+        # {::Google::Cloud::AIPlatform::V1::PredictionService::Client#direct_predict PredictionService.DirectPredict}.
+        # @!attribute [rw] outputs
+        #   @return [::Array<::Google::Cloud::AIPlatform::V1::Tensor>]
+        #     The prediction output.
+        # @!attribute [rw] parameters
+        #   @return [::Google::Cloud::AIPlatform::V1::Tensor]
+        #     The parameters that govern the prediction.
+        class DirectPredictResponse
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # Request message for
+        # {::Google::Cloud::AIPlatform::V1::PredictionService::Client#direct_raw_predict PredictionService.DirectRawPredict}.
+        # @!attribute [rw] endpoint
+        #   @return [::String]
+        #     Required. The name of the Endpoint requested to serve the prediction.
+        #     Format:
+        #     `projects/{project}/locations/{location}/endpoints/{endpoint}`
+        # @!attribute [rw] method_name
+        #   @return [::String]
+        #     Fully qualified name of the API method being invoked to perform
+        #     predictions.
+        #
+        #     Format:
+        #     `/namespace.Service/Method/`
+        #     Example:
+        #     `/tensorflow.serving.PredictionService/Predict`
+        # @!attribute [rw] input
+        #   @return [::String]
+        #     The prediction input.
+        class DirectRawPredictRequest
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # Response message for
+        # {::Google::Cloud::AIPlatform::V1::PredictionService::Client#direct_raw_predict PredictionService.DirectRawPredict}.
+        # @!attribute [rw] output
+        #   @return [::String]
+        #     The prediction output.
+        class DirectRawPredictResponse
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # Request message for
+        # {::Google::Cloud::AIPlatform::V1::PredictionService::Client#streaming_predict PredictionService.StreamingPredict}.
         #
         # The first message must contain
         # {::Google::Cloud::AIPlatform::V1::StreamingPredictRequest#endpoint endpoint} field
@@ -137,7 +202,7 @@ module Google
         end
 
         # Response message for
-        # [PredictionService.StreamingPredict][google.cloud.aiplatform.v1.PredictionService.StreamingPredict].
+        # {::Google::Cloud::AIPlatform::V1::PredictionService::Client#streaming_predict PredictionService.StreamingPredict}.
         # @!attribute [rw] outputs
         #   @return [::Array<::Google::Cloud::AIPlatform::V1::Tensor>]
         #     The prediction output.
@@ -149,6 +214,51 @@ module Google
           extend ::Google::Protobuf::MessageExts::ClassMethods
         end
 
+        # Request message for
+        # {::Google::Cloud::AIPlatform::V1::PredictionService::Client#streaming_raw_predict PredictionService.StreamingRawPredict}.
+        #
+        # The first message must contain
+        # {::Google::Cloud::AIPlatform::V1::StreamingRawPredictRequest#endpoint endpoint}
+        # and
+        # {::Google::Cloud::AIPlatform::V1::StreamingRawPredictRequest#method_name method_name}
+        # fields and optionally
+        # {::Google::Cloud::AIPlatform::V1::StreamingRawPredictRequest#input input}. The
+        # subsequent messages must contain
+        # {::Google::Cloud::AIPlatform::V1::StreamingRawPredictRequest#input input}.
+        # {::Google::Cloud::AIPlatform::V1::StreamingRawPredictRequest#method_name method_name}
+        # in the subsequent messages have no effect.
+        # @!attribute [rw] endpoint
+        #   @return [::String]
+        #     Required. The name of the Endpoint requested to serve the prediction.
+        #     Format:
+        #     `projects/{project}/locations/{location}/endpoints/{endpoint}`
+        # @!attribute [rw] method_name
+        #   @return [::String]
+        #     Fully qualified name of the API method being invoked to perform
+        #     predictions.
+        #
+        #     Format:
+        #     `/namespace.Service/Method/`
+        #     Example:
+        #     `/tensorflow.serving.PredictionService/Predict`
+        # @!attribute [rw] input
+        #   @return [::String]
+        #     The prediction input.
+        class StreamingRawPredictRequest
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # Response message for
+        # {::Google::Cloud::AIPlatform::V1::PredictionService::Client#streaming_raw_predict PredictionService.StreamingRawPredict}.
+        # @!attribute [rw] output
+        #   @return [::String]
+        #     The prediction output.
+        class StreamingRawPredictResponse
+          include ::Google::Protobuf::MessageExts
+          extend ::Google::Protobuf::MessageExts::ClassMethods
+        end
+
         # Request message for
         # {::Google::Cloud::AIPlatform::V1::PredictionService::Client#explain PredictionService.Explain}.
         # @!attribute [rw] endpoint

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: google-cloud-ai_platform-v1
 version: !ruby/object:Gem::Version
-  version: 0.34.0
+  version: 0.35.0
 platform: ruby
 authors:
 - Google LLC
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-11-20 00:00:00.000000000 Z
+date: 2023-12-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: gapic-common
@@ -260,6 +260,10 @@ files:
 - lib/google/cloud/ai_platform/v1/job_service/credentials.rb
 - lib/google/cloud/ai_platform/v1/job_service/operations.rb
 - lib/google/cloud/ai_platform/v1/job_service/paths.rb
+- lib/google/cloud/ai_platform/v1/llm_utility_service.rb
+- lib/google/cloud/ai_platform/v1/llm_utility_service/client.rb
+- lib/google/cloud/ai_platform/v1/llm_utility_service/credentials.rb
+- lib/google/cloud/ai_platform/v1/llm_utility_service/paths.rb
 - lib/google/cloud/ai_platform/v1/match_service.rb
 - lib/google/cloud/ai_platform/v1/match_service/client.rb
 - lib/google/cloud/ai_platform/v1/match_service/credentials.rb
@@ -371,6 +375,8 @@ files:
 - lib/google/cloud/aiplatform/v1/job_service_services_pb.rb
 - lib/google/cloud/aiplatform/v1/job_state_pb.rb
 - lib/google/cloud/aiplatform/v1/lineage_subgraph_pb.rb
+- lib/google/cloud/aiplatform/v1/llm_utility_service_pb.rb
+- lib/google/cloud/aiplatform/v1/llm_utility_service_services_pb.rb
 - lib/google/cloud/aiplatform/v1/machine_resources_pb.rb
 - lib/google/cloud/aiplatform/v1/manual_batch_tuning_parameters_pb.rb
 - lib/google/cloud/aiplatform/v1/match_service_pb.rb
@@ -478,6 +484,7 @@ files:
 - proto_docs/google/cloud/aiplatform/v1/job_service.rb
 - proto_docs/google/cloud/aiplatform/v1/job_state.rb
 - proto_docs/google/cloud/aiplatform/v1/lineage_subgraph.rb
+- proto_docs/google/cloud/aiplatform/v1/llm_utility_service.rb
 - proto_docs/google/cloud/aiplatform/v1/machine_resources.rb
 - proto_docs/google/cloud/aiplatform/v1/manual_batch_tuning_parameters.rb
 - proto_docs/google/cloud/aiplatform/v1/match_service.rb