# -*- coding: utf-8 -*- # Copyright 2025 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 # # http://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. # from __future__ import annotations from typing import MutableMapping, MutableSequence import proto # type: ignore from google.api import httpbody_pb2 # type: ignore from cloudsdk.google.protobuf import struct_pb2 # type: ignore from cloudsdk.google.protobuf import timestamp_pb2 # type: ignore from googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types import content as gca_content from googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types import explanation from googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types import tool from googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types import types from googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types import usage_metadata as gca_usage_metadata __protobuf__ = proto.module( package='google.cloud.aiplatform.v1beta1', manifest={ 'PredictRequest', 'PredictResponse', 'RawPredictRequest', 'StreamRawPredictRequest', 'DirectPredictRequest', 'DirectPredictResponse', 'DirectRawPredictRequest', 'DirectRawPredictResponse', 'StreamDirectPredictRequest', 'StreamDirectPredictResponse', 'StreamDirectRawPredictRequest', 'StreamDirectRawPredictResponse', 'StreamingPredictRequest', 'StreamingPredictResponse', 'StreamingRawPredictRequest', 'StreamingRawPredictResponse', 'PredictLongRunningRequest', 'FetchPredictOperationRequest', 'InvokeRequest', 'ExplainRequest', 'ExplainResponse', 'CountTokensRequest', 'CountTokensResponse', 'GenerateContentRequest', 'GenerateContentResponse', 'ChatCompletionsRequest', 'PredictLongRunningResponse', 'PredictLongRunningMetadata', 'GenerateVideoResponse', 'EmbedContentRequest', 'EmbedContentResponse', }, ) class PredictRequest(proto.Message): r"""Request message for [PredictionService.Predict][google.cloud.aiplatform.v1beta1.PredictionService.Predict]. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` instances (MutableSequence[google.protobuf.struct_pb2.Value]): Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' [Model's][google.cloud.aiplatform.v1beta1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.instance_schema_uri]. parameters (google.protobuf.struct_pb2.Value): The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1beta1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.parameters_schema_uri]. labels (MutableMapping[str, str]): Optional. The user labels for Imagen billing usage only. Only Imagen supports labels. For other use cases, it will be ignored. """ endpoint: str = proto.Field( proto.STRING, number=1, ) instances: MutableSequence[struct_pb2.Value] = proto.RepeatedField( proto.MESSAGE, number=2, message=struct_pb2.Value, ) parameters: struct_pb2.Value = proto.Field( proto.MESSAGE, number=3, message=struct_pb2.Value, ) labels: MutableMapping[str, str] = proto.MapField( proto.STRING, proto.STRING, number=4, ) class PredictResponse(proto.Message): r"""Response message for [PredictionService.Predict][google.cloud.aiplatform.v1beta1.PredictionService.Predict]. Attributes: predictions (MutableSequence[google.protobuf.struct_pb2.Value]): The predictions that are the output of the predictions call. The schema of any single prediction may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1beta1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] [prediction_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.prediction_schema_uri]. deployed_model_id (str): ID of the Endpoint's DeployedModel that served this prediction. model (str): Output only. The resource name of the Model which is deployed as the DeployedModel that this prediction hits. model_version_id (str): Output only. The version ID of the Model which is deployed as the DeployedModel that this prediction hits. model_display_name (str): Output only. The [display name][google.cloud.aiplatform.v1beta1.Model.display_name] of the Model which is deployed as the DeployedModel that this prediction hits. metadata (google.protobuf.struct_pb2.Value): Output only. Request-level metadata returned by the model. The metadata type will be dependent upon the model implementation. """ predictions: MutableSequence[struct_pb2.Value] = proto.RepeatedField( proto.MESSAGE, number=1, message=struct_pb2.Value, ) deployed_model_id: str = proto.Field( proto.STRING, number=2, ) model: str = proto.Field( proto.STRING, number=3, ) model_version_id: str = proto.Field( proto.STRING, number=5, ) model_display_name: str = proto.Field( proto.STRING, number=4, ) metadata: struct_pb2.Value = proto.Field( proto.MESSAGE, number=6, message=struct_pb2.Value, ) class RawPredictRequest(proto.Message): r"""Request message for [PredictionService.RawPredict][google.cloud.aiplatform.v1beta1.PredictionService.RawPredict]. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` http_body (google.api.httpbody_pb2.HttpBody): The prediction input. Supports HTTP headers and arbitrary data payload. A [DeployedModel][google.cloud.aiplatform.v1beta1.DeployedModel] may have an upper limit on the number of instances it supports per request. When this limit it is exceeded for an AutoML model, the [RawPredict][google.cloud.aiplatform.v1beta1.PredictionService.RawPredict] method returns an error. When this limit is exceeded for a custom-trained model, the behavior varies depending on the model. You can specify the schema for each instance in the [predict_schemata.instance_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.instance_schema_uri] field when you create a [Model][google.cloud.aiplatform.v1beta1.Model]. This schema applies when you deploy the ``Model`` as a ``DeployedModel`` to an [Endpoint][google.cloud.aiplatform.v1beta1.Endpoint] and use the ``RawPredict`` method. """ endpoint: str = proto.Field( proto.STRING, number=1, ) http_body: httpbody_pb2.HttpBody = proto.Field( proto.MESSAGE, number=2, message=httpbody_pb2.HttpBody, ) class StreamRawPredictRequest(proto.Message): r"""Request message for [PredictionService.StreamRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamRawPredict]. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` or ``projects/{project}/locations/{location}/publishers/{publisher}/models/{model}`` http_body (google.api.httpbody_pb2.HttpBody): The prediction input. Supports HTTP headers and arbitrary data payload. """ endpoint: str = proto.Field( proto.STRING, number=1, ) http_body: httpbody_pb2.HttpBody = proto.Field( proto.MESSAGE, number=2, message=httpbody_pb2.HttpBody, ) class DirectPredictRequest(proto.Message): r"""Request message for [PredictionService.DirectPredict][google.cloud.aiplatform.v1beta1.PredictionService.DirectPredict]. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` inputs (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor]): The prediction input. parameters (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor): The parameters that govern the prediction. """ endpoint: str = proto.Field( proto.STRING, number=1, ) inputs: MutableSequence[types.Tensor] = proto.RepeatedField( proto.MESSAGE, number=2, message=types.Tensor, ) parameters: types.Tensor = proto.Field( proto.MESSAGE, number=3, message=types.Tensor, ) class DirectPredictResponse(proto.Message): r"""Response message for [PredictionService.DirectPredict][google.cloud.aiplatform.v1beta1.PredictionService.DirectPredict]. Attributes: outputs (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor]): The prediction output. parameters (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor): The parameters that govern the prediction. """ outputs: MutableSequence[types.Tensor] = proto.RepeatedField( proto.MESSAGE, number=1, message=types.Tensor, ) parameters: types.Tensor = proto.Field( proto.MESSAGE, number=2, message=types.Tensor, ) class DirectRawPredictRequest(proto.Message): r"""Request message for [PredictionService.DirectRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.DirectRawPredict]. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` method_name (str): Fully qualified name of the API method being invoked to perform predictions. Format: ``/namespace.Service/Method/`` Example: ``/tensorflow.serving.PredictionService/Predict`` input (bytes): The prediction input. """ endpoint: str = proto.Field( proto.STRING, number=1, ) method_name: str = proto.Field( proto.STRING, number=2, ) input: bytes = proto.Field( proto.BYTES, number=3, ) class DirectRawPredictResponse(proto.Message): r"""Response message for [PredictionService.DirectRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.DirectRawPredict]. Attributes: output (bytes): The prediction output. """ output: bytes = proto.Field( proto.BYTES, number=1, ) class StreamDirectPredictRequest(proto.Message): r"""Request message for [PredictionService.StreamDirectPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamDirectPredict]. The first message must contain [endpoint][google.cloud.aiplatform.v1beta1.StreamDirectPredictRequest.endpoint] field and optionally [input][]. The subsequent messages must contain [input][]. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` inputs (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor]): Optional. The prediction input. parameters (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor): Optional. The parameters that govern the prediction. """ endpoint: str = proto.Field( proto.STRING, number=1, ) inputs: MutableSequence[types.Tensor] = proto.RepeatedField( proto.MESSAGE, number=2, message=types.Tensor, ) parameters: types.Tensor = proto.Field( proto.MESSAGE, number=3, message=types.Tensor, ) class StreamDirectPredictResponse(proto.Message): r"""Response message for [PredictionService.StreamDirectPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamDirectPredict]. Attributes: outputs (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor]): The prediction output. parameters (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor): The parameters that govern the prediction. """ outputs: MutableSequence[types.Tensor] = proto.RepeatedField( proto.MESSAGE, number=1, message=types.Tensor, ) parameters: types.Tensor = proto.Field( proto.MESSAGE, number=2, message=types.Tensor, ) class StreamDirectRawPredictRequest(proto.Message): r"""Request message for [PredictionService.StreamDirectRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamDirectRawPredict]. The first message must contain [endpoint][google.cloud.aiplatform.v1beta1.StreamDirectRawPredictRequest.endpoint] and [method_name][google.cloud.aiplatform.v1beta1.StreamDirectRawPredictRequest.method_name] fields and optionally [input][google.cloud.aiplatform.v1beta1.StreamDirectRawPredictRequest.input]. The subsequent messages must contain [input][google.cloud.aiplatform.v1beta1.StreamDirectRawPredictRequest.input]. [method_name][google.cloud.aiplatform.v1beta1.StreamDirectRawPredictRequest.method_name] in the subsequent messages have no effect. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` method_name (str): Optional. Fully qualified name of the API method being invoked to perform predictions. Format: ``/namespace.Service/Method/`` Example: ``/tensorflow.serving.PredictionService/Predict`` input (bytes): Optional. The prediction input. """ endpoint: str = proto.Field( proto.STRING, number=1, ) method_name: str = proto.Field( proto.STRING, number=2, ) input: bytes = proto.Field( proto.BYTES, number=3, ) class StreamDirectRawPredictResponse(proto.Message): r"""Response message for [PredictionService.StreamDirectRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamDirectRawPredict]. Attributes: output (bytes): The prediction output. """ output: bytes = proto.Field( proto.BYTES, number=1, ) class StreamingPredictRequest(proto.Message): r"""Request message for [PredictionService.StreamingPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamingPredict]. The first message must contain [endpoint][google.cloud.aiplatform.v1beta1.StreamingPredictRequest.endpoint] field and optionally [input][]. The subsequent messages must contain [input][]. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` inputs (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor]): The prediction input. parameters (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor): The parameters that govern the prediction. """ endpoint: str = proto.Field( proto.STRING, number=1, ) inputs: MutableSequence[types.Tensor] = proto.RepeatedField( proto.MESSAGE, number=2, message=types.Tensor, ) parameters: types.Tensor = proto.Field( proto.MESSAGE, number=3, message=types.Tensor, ) class StreamingPredictResponse(proto.Message): r"""Response message for [PredictionService.StreamingPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamingPredict]. Attributes: outputs (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor]): The prediction output. parameters (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tensor): The parameters that govern the prediction. """ outputs: MutableSequence[types.Tensor] = proto.RepeatedField( proto.MESSAGE, number=1, message=types.Tensor, ) parameters: types.Tensor = proto.Field( proto.MESSAGE, number=2, message=types.Tensor, ) class StreamingRawPredictRequest(proto.Message): r"""Request message for [PredictionService.StreamingRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamingRawPredict]. The first message must contain [endpoint][google.cloud.aiplatform.v1beta1.StreamingRawPredictRequest.endpoint] and [method_name][google.cloud.aiplatform.v1beta1.StreamingRawPredictRequest.method_name] fields and optionally [input][google.cloud.aiplatform.v1beta1.StreamingRawPredictRequest.input]. The subsequent messages must contain [input][google.cloud.aiplatform.v1beta1.StreamingRawPredictRequest.input]. [method_name][google.cloud.aiplatform.v1beta1.StreamingRawPredictRequest.method_name] in the subsequent messages have no effect. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` method_name (str): Fully qualified name of the API method being invoked to perform predictions. Format: ``/namespace.Service/Method/`` Example: ``/tensorflow.serving.PredictionService/Predict`` input (bytes): The prediction input. """ endpoint: str = proto.Field( proto.STRING, number=1, ) method_name: str = proto.Field( proto.STRING, number=2, ) input: bytes = proto.Field( proto.BYTES, number=3, ) class StreamingRawPredictResponse(proto.Message): r"""Response message for [PredictionService.StreamingRawPredict][google.cloud.aiplatform.v1beta1.PredictionService.StreamingRawPredict]. Attributes: output (bytes): The prediction output. """ output: bytes = proto.Field( proto.BYTES, number=1, ) class PredictLongRunningRequest(proto.Message): r"""Request message for [PredictionService.PredictLongRunning][google.cloud.aiplatform.v1beta1.PredictionService.PredictLongRunning]. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` or ``projects/{project}/locations/{location}/publishers/{publisher}/models/{model}`` instances (MutableSequence[google.protobuf.struct_pb2.Value]): Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' [Model's][google.cloud.aiplatform.v1beta1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.instance_schema_uri]. parameters (google.protobuf.struct_pb2.Value): Optional. The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1beta1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.parameters_schema_uri]. """ endpoint: str = proto.Field( proto.STRING, number=1, ) instances: MutableSequence[struct_pb2.Value] = proto.RepeatedField( proto.MESSAGE, number=2, message=struct_pb2.Value, ) parameters: struct_pb2.Value = proto.Field( proto.MESSAGE, number=3, message=struct_pb2.Value, ) class FetchPredictOperationRequest(proto.Message): r"""Request message for [PredictionService.FetchPredictOperation][google.cloud.aiplatform.v1beta1.PredictionService.FetchPredictOperation]. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` or ``projects/{project}/locations/{location}/publishers/{publisher}/models/{model}`` operation_name (str): Required. The server-assigned name for the operation. """ endpoint: str = proto.Field( proto.STRING, number=1, ) operation_name: str = proto.Field( proto.STRING, number=2, ) class InvokeRequest(proto.Message): r"""Request message for [PredictionService.Invoke][google.cloud.aiplatform.v1beta1.PredictionService.Invoke]. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` deployed_model_id (str): ID of the DeployedModel that serves the invoke request. http_body (google.api.httpbody_pb2.HttpBody): The invoke method input. Supports HTTP headers and arbitrary data payload. """ endpoint: str = proto.Field( proto.STRING, number=1, ) deployed_model_id: str = proto.Field( proto.STRING, number=3, ) http_body: httpbody_pb2.HttpBody = proto.Field( proto.MESSAGE, number=2, message=httpbody_pb2.HttpBody, ) class ExplainRequest(proto.Message): r"""Request message for [PredictionService.Explain][google.cloud.aiplatform.v1beta1.PredictionService.Explain]. Attributes: endpoint (str): Required. The name of the Endpoint requested to serve the explanation. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` instances (MutableSequence[google.protobuf.struct_pb2.Value]): Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' [Model's][google.cloud.aiplatform.v1beta1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.instance_schema_uri]. parameters (google.protobuf.struct_pb2.Value): The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1beta1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.parameters_schema_uri]. explanation_spec_override (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.ExplanationSpecOverride): If specified, overrides the [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec] of the DeployedModel. Can be used for explaining prediction results with different configurations, such as: - Explaining top-5 predictions results as opposed to top-1; - Increasing path count or step count of the attribution methods to reduce approximate errors; - Using different baselines for explaining the prediction results. concurrent_explanation_spec_override (MutableMapping[str, googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.ExplanationSpecOverride]): Optional. This field is the same as the one above, but supports multiple explanations to occur in parallel. The key can be any string. Each override will be run against the model, then its explanations will be grouped together. Note - these explanations are run **In Addition** to the default Explanation in the deployed model. deployed_model_id (str): If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding [Endpoint.traffic_split][google.cloud.aiplatform.v1beta1.Endpoint.traffic_split]. """ endpoint: str = proto.Field( proto.STRING, number=1, ) instances: MutableSequence[struct_pb2.Value] = proto.RepeatedField( proto.MESSAGE, number=2, message=struct_pb2.Value, ) parameters: struct_pb2.Value = proto.Field( proto.MESSAGE, number=4, message=struct_pb2.Value, ) explanation_spec_override: explanation.ExplanationSpecOverride = proto.Field( proto.MESSAGE, number=5, message=explanation.ExplanationSpecOverride, ) concurrent_explanation_spec_override: MutableMapping[str, explanation.ExplanationSpecOverride] = proto.MapField( proto.STRING, proto.MESSAGE, number=6, message=explanation.ExplanationSpecOverride, ) deployed_model_id: str = proto.Field( proto.STRING, number=3, ) class ExplainResponse(proto.Message): r"""Response message for [PredictionService.Explain][google.cloud.aiplatform.v1beta1.PredictionService.Explain]. Attributes: explanations (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Explanation]): The explanations of the Model's [PredictResponse.predictions][google.cloud.aiplatform.v1beta1.PredictResponse.predictions]. It has the same number of elements as [instances][google.cloud.aiplatform.v1beta1.ExplainRequest.instances] to be explained. concurrent_explanations (MutableMapping[str, googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.ExplainResponse.ConcurrentExplanation]): This field stores the results of the explanations run in parallel with The default explanation strategy/method. deployed_model_id (str): ID of the Endpoint's DeployedModel that served this explanation. predictions (MutableSequence[google.protobuf.struct_pb2.Value]): The predictions that are the output of the predictions call. Same as [PredictResponse.predictions][google.cloud.aiplatform.v1beta1.PredictResponse.predictions]. """ class ConcurrentExplanation(proto.Message): r"""This message is a wrapper grouping Concurrent Explanations. Attributes: explanations (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Explanation]): The explanations of the Model's [PredictResponse.predictions][google.cloud.aiplatform.v1beta1.PredictResponse.predictions]. It has the same number of elements as [instances][google.cloud.aiplatform.v1beta1.ExplainRequest.instances] to be explained. """ explanations: MutableSequence[explanation.Explanation] = proto.RepeatedField( proto.MESSAGE, number=1, message=explanation.Explanation, ) explanations: MutableSequence[explanation.Explanation] = proto.RepeatedField( proto.MESSAGE, number=1, message=explanation.Explanation, ) concurrent_explanations: MutableMapping[str, ConcurrentExplanation] = proto.MapField( proto.STRING, proto.MESSAGE, number=4, message=ConcurrentExplanation, ) deployed_model_id: str = proto.Field( proto.STRING, number=2, ) predictions: MutableSequence[struct_pb2.Value] = proto.RepeatedField( proto.MESSAGE, number=3, message=struct_pb2.Value, ) class CountTokensRequest(proto.Message): r"""Request message for [PredictionService.CountTokens][google.cloud.aiplatform.v1beta1.PredictionService.CountTokens]. .. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields Attributes: endpoint (str): Required. The name of the Endpoint requested to perform token counting. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` model (str): Optional. The name of the publisher model requested to serve the prediction. Format: ``projects/{project}/locations/{location}/publishers/*/models/*`` instances (MutableSequence[google.protobuf.struct_pb2.Value]): Optional. The instances that are the input to token counting call. Schema is identical to the prediction schema of the underlying model. contents (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Content]): Optional. Input content. system_instruction (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Content): Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. This field is a member of `oneof`_ ``_system_instruction``. tools (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tool]): Optional. A list of ``Tools`` the model may use to generate the next response. A ``Tool`` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. generation_config (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.GenerationConfig): Optional. Generation config that the model will use to generate the response. This field is a member of `oneof`_ ``_generation_config``. """ endpoint: str = proto.Field( proto.STRING, number=1, ) model: str = proto.Field( proto.STRING, number=3, ) instances: MutableSequence[struct_pb2.Value] = proto.RepeatedField( proto.MESSAGE, number=2, message=struct_pb2.Value, ) contents: MutableSequence[gca_content.Content] = proto.RepeatedField( proto.MESSAGE, number=4, message=gca_content.Content, ) system_instruction: gca_content.Content = proto.Field( proto.MESSAGE, number=5, optional=True, message=gca_content.Content, ) tools: MutableSequence[tool.Tool] = proto.RepeatedField( proto.MESSAGE, number=6, message=tool.Tool, ) generation_config: gca_content.GenerationConfig = proto.Field( proto.MESSAGE, number=7, optional=True, message=gca_content.GenerationConfig, ) class CountTokensResponse(proto.Message): r"""Response message for [PredictionService.CountTokens][google.cloud.aiplatform.v1beta1.PredictionService.CountTokens]. Attributes: total_tokens (int): The total number of tokens counted across all instances from the request. total_billable_characters (int): The total number of billable characters counted across all instances from the request. prompt_tokens_details (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.ModalityTokenCount]): Output only. List of modalities that were processed in the request input. """ total_tokens: int = proto.Field( proto.INT32, number=1, ) total_billable_characters: int = proto.Field( proto.INT32, number=2, ) prompt_tokens_details: MutableSequence[gca_content.ModalityTokenCount] = proto.RepeatedField( proto.MESSAGE, number=3, message=gca_content.ModalityTokenCount, ) class GenerateContentRequest(proto.Message): r"""Request message for [PredictionService.GenerateContent]. .. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields Attributes: model (str): Required. The fully qualified name of the publisher model or tuned model endpoint to use. Publisher model format: ``projects/{project}/locations/{location}/publishers/*/models/*`` Tuned model endpoint format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` contents (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Content]): Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request. system_instruction (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Content): Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. This field is a member of `oneof`_ ``_system_instruction``. cached_content (str): Optional. The name of the cached content used as context to serve the prediction. Note: only used in explicit caching, where users can have control over caching (e.g. what content to cache) and enjoy guaranteed cost savings. Format: ``projects/{project}/locations/{location}/cachedContents/{cachedContent}`` tools (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Tool]): Optional. A list of ``Tools`` the model may use to generate the next response. A ``Tool`` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. tool_config (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.ToolConfig): Optional. Tool config. This config is shared for all tools provided in the request. labels (MutableMapping[str, str]): Optional. The labels with user-defined metadata for the request. It is used for billing and reporting only. Label keys and values can be no longer than 63 characters (Unicode codepoints) and can only contain lowercase letters, numeric characters, underscores, and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter. safety_settings (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.SafetySetting]): Optional. Per request settings for blocking unsafe content. Enforced on GenerateContentResponse.candidates. model_armor_config (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.ModelArmorConfig): Optional. Settings for prompt and response sanitization using the Model Armor service. If supplied, safety_settings must not be supplied. generation_config (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.GenerationConfig): Optional. Generation config. """ model: str = proto.Field( proto.STRING, number=5, ) contents: MutableSequence[gca_content.Content] = proto.RepeatedField( proto.MESSAGE, number=2, message=gca_content.Content, ) system_instruction: gca_content.Content = proto.Field( proto.MESSAGE, number=8, optional=True, message=gca_content.Content, ) cached_content: str = proto.Field( proto.STRING, number=9, ) tools: MutableSequence[tool.Tool] = proto.RepeatedField( proto.MESSAGE, number=6, message=tool.Tool, ) tool_config: tool.ToolConfig = proto.Field( proto.MESSAGE, number=7, message=tool.ToolConfig, ) labels: MutableMapping[str, str] = proto.MapField( proto.STRING, proto.STRING, number=10, ) safety_settings: MutableSequence[gca_content.SafetySetting] = proto.RepeatedField( proto.MESSAGE, number=3, message=gca_content.SafetySetting, ) model_armor_config: gca_content.ModelArmorConfig = proto.Field( proto.MESSAGE, number=11, message=gca_content.ModelArmorConfig, ) generation_config: gca_content.GenerationConfig = proto.Field( proto.MESSAGE, number=4, message=gca_content.GenerationConfig, ) class GenerateContentResponse(proto.Message): r"""Response message for [PredictionService.GenerateContent]. Attributes: candidates (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Candidate]): Output only. Generated candidates. model_version (str): Output only. The model version used to generate the response. create_time (google.protobuf.timestamp_pb2.Timestamp): Output only. Timestamp when the request is made to the server. response_id (str): Output only. response_id is used to identify each response. It is the encoding of the event_id. prompt_feedback (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.GenerateContentResponse.PromptFeedback): Output only. Content filter results for a prompt sent in the request. Note: Sent only in the first stream chunk. Only happens when no candidates were generated due to content violations. usage_metadata (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.GenerateContentResponse.UsageMetadata): Usage metadata about the response(s). """ class PromptFeedback(proto.Message): r"""Content filter results for a prompt sent in the request. Note: This is sent only in the first stream chunk and only if no candidates were generated due to content violations. Attributes: block_reason (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.GenerateContentResponse.PromptFeedback.BlockedReason): Output only. The reason why the prompt was blocked. safety_ratings (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.SafetyRating]): Output only. A list of safety ratings for the prompt. There is one rating per category. block_reason_message (str): Output only. A readable message that explains the reason why the prompt was blocked. """ class BlockedReason(proto.Enum): r"""The reason why the prompt was blocked. Values: BLOCKED_REASON_UNSPECIFIED (0): The blocked reason is unspecified. SAFETY (1): The prompt was blocked for safety reasons. OTHER (2): The prompt was blocked for other reasons. For example, it may be due to the prompt's language, or because it contains other harmful content. BLOCKLIST (3): The prompt was blocked because it contains a term from the terminology blocklist. PROHIBITED_CONTENT (4): The prompt was blocked because it contains prohibited content. MODEL_ARMOR (5): The prompt was blocked by Model Armor. IMAGE_SAFETY (6): The prompt was blocked because it contains content that is unsafe for image generation. JAILBREAK (7): The prompt was blocked as a jailbreak attempt. """ BLOCKED_REASON_UNSPECIFIED = 0 SAFETY = 1 OTHER = 2 BLOCKLIST = 3 PROHIBITED_CONTENT = 4 MODEL_ARMOR = 5 IMAGE_SAFETY = 6 JAILBREAK = 7 block_reason: 'GenerateContentResponse.PromptFeedback.BlockedReason' = proto.Field( proto.ENUM, number=1, enum='GenerateContentResponse.PromptFeedback.BlockedReason', ) safety_ratings: MutableSequence[gca_content.SafetyRating] = proto.RepeatedField( proto.MESSAGE, number=2, message=gca_content.SafetyRating, ) block_reason_message: str = proto.Field( proto.STRING, number=3, ) class UsageMetadata(proto.Message): r"""Usage metadata about the content generation request and response. This message provides a detailed breakdown of token usage and other relevant metrics. Attributes: prompt_token_count (int): The total number of tokens in the prompt. This includes any text, images, or other media provided in the request. When ``cached_content`` is set, this also includes the number of tokens in the cached content. candidates_token_count (int): The total number of tokens in the generated candidates. total_token_count (int): The total number of tokens for the entire request. This is the sum of ``prompt_token_count``, ``candidates_token_count``, ``tool_use_prompt_token_count``, and ``thoughts_token_count``. tool_use_prompt_token_count (int): Output only. The number of tokens in the results from tool executions, which are provided back to the model as input, if applicable. thoughts_token_count (int): Output only. The number of tokens that were part of the model's generated "thoughts" output, if applicable. cached_content_token_count (int): Output only. The number of tokens in the cached content that was used for this request. prompt_tokens_details (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.ModalityTokenCount]): Output only. A detailed breakdown of the token count for each modality in the prompt. cache_tokens_details (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.ModalityTokenCount]): Output only. A detailed breakdown of the token count for each modality in the cached content. candidates_tokens_details (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.ModalityTokenCount]): Output only. A detailed breakdown of the token count for each modality in the generated candidates. tool_use_prompt_tokens_details (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.ModalityTokenCount]): Output only. A detailed breakdown by modality of the token counts from the results of tool executions, which are provided back to the model as input. traffic_type (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.GenerateContentResponse.UsageMetadata.TrafficType): Output only. The traffic type for this request. """ class TrafficType(proto.Enum): r"""The type of traffic that this request was processed with, indicating which quota is consumed. Values: TRAFFIC_TYPE_UNSPECIFIED (0): Unspecified request traffic type. ON_DEMAND (1): The request was processed using Pay-As-You-Go quota. PROVISIONED_THROUGHPUT (2): Type for Provisioned Throughput traffic. """ TRAFFIC_TYPE_UNSPECIFIED = 0 ON_DEMAND = 1 PROVISIONED_THROUGHPUT = 2 prompt_token_count: int = proto.Field( proto.INT32, number=1, ) candidates_token_count: int = proto.Field( proto.INT32, number=2, ) total_token_count: int = proto.Field( proto.INT32, number=3, ) tool_use_prompt_token_count: int = proto.Field( proto.INT32, number=13, ) thoughts_token_count: int = proto.Field( proto.INT32, number=14, ) cached_content_token_count: int = proto.Field( proto.INT32, number=5, ) prompt_tokens_details: MutableSequence[gca_content.ModalityTokenCount] = proto.RepeatedField( proto.MESSAGE, number=9, message=gca_content.ModalityTokenCount, ) cache_tokens_details: MutableSequence[gca_content.ModalityTokenCount] = proto.RepeatedField( proto.MESSAGE, number=10, message=gca_content.ModalityTokenCount, ) candidates_tokens_details: MutableSequence[gca_content.ModalityTokenCount] = proto.RepeatedField( proto.MESSAGE, number=11, message=gca_content.ModalityTokenCount, ) tool_use_prompt_tokens_details: MutableSequence[gca_content.ModalityTokenCount] = proto.RepeatedField( proto.MESSAGE, number=12, message=gca_content.ModalityTokenCount, ) traffic_type: 'GenerateContentResponse.UsageMetadata.TrafficType' = proto.Field( proto.ENUM, number=8, enum='GenerateContentResponse.UsageMetadata.TrafficType', ) candidates: MutableSequence[gca_content.Candidate] = proto.RepeatedField( proto.MESSAGE, number=2, message=gca_content.Candidate, ) model_version: str = proto.Field( proto.STRING, number=11, ) create_time: timestamp_pb2.Timestamp = proto.Field( proto.MESSAGE, number=12, message=timestamp_pb2.Timestamp, ) response_id: str = proto.Field( proto.STRING, number=13, ) prompt_feedback: PromptFeedback = proto.Field( proto.MESSAGE, number=3, message=PromptFeedback, ) usage_metadata: UsageMetadata = proto.Field( proto.MESSAGE, number=4, message=UsageMetadata, ) class ChatCompletionsRequest(proto.Message): r"""Request message for [PredictionService.ChatCompletions] Attributes: endpoint (str): Required. The name of the endpoint requested to serve the prediction. Format: ``projects/{project}/locations/{location}/endpoints/{endpoint}`` http_body (google.api.httpbody_pb2.HttpBody): Optional. The prediction input. Supports HTTP headers and arbitrary data payload. """ endpoint: str = proto.Field( proto.STRING, number=1, ) http_body: httpbody_pb2.HttpBody = proto.Field( proto.MESSAGE, number=2, message=httpbody_pb2.HttpBody, ) class PredictLongRunningResponse(proto.Message): r"""Response message for [PredictionService.PredictLongRunning] .. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields Attributes: generate_video_response (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.GenerateVideoResponse): The response of the video generation prediction. This field is a member of `oneof`_ ``response``. """ generate_video_response: 'GenerateVideoResponse' = proto.Field( proto.MESSAGE, number=1, oneof='response', message='GenerateVideoResponse', ) class PredictLongRunningMetadata(proto.Message): r"""Metadata for PredictLongRunning long running operations. """ class GenerateVideoResponse(proto.Message): r"""Generate video response. .. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields Attributes: generated_samples (MutableSequence[str]): The cloud storage uris of the generated videos. rai_media_filtered_count (int): Returns if any videos were filtered due to RAI policies. This field is a member of `oneof`_ ``_rai_media_filtered_count``. rai_media_filtered_reasons (MutableSequence[str]): Returns rai failure reasons if any. videos (MutableSequence[googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.GenerateVideoResponse.Video]): List of video bytes or Cloud Storage URIs of the generated videos. """ class Video(proto.Message): r"""A generated video. This message has `oneof`_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members. .. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields Attributes: gcs_uri (str): Cloud Storage URI where the generated video is written. This field is a member of `oneof`_ ``data``. bytes_base64_encoded (str): Base64 encoded bytes string representing the video. This field is a member of `oneof`_ ``data``. mime_type (str): The MIME type of the content of the video. - video/mp4 """ gcs_uri: str = proto.Field( proto.STRING, number=1, oneof='data', ) bytes_base64_encoded: str = proto.Field( proto.STRING, number=2, oneof='data', ) mime_type: str = proto.Field( proto.STRING, number=3, ) generated_samples: MutableSequence[str] = proto.RepeatedField( proto.STRING, number=1, ) rai_media_filtered_count: int = proto.Field( proto.INT32, number=2, optional=True, ) rai_media_filtered_reasons: MutableSequence[str] = proto.RepeatedField( proto.STRING, number=3, ) videos: MutableSequence[Video] = proto.RepeatedField( proto.MESSAGE, number=4, message=Video, ) class EmbedContentRequest(proto.Message): r"""Request message for [PredictionService.EmbedContent][google.cloud.aiplatform.v1beta1.PredictionService.EmbedContent]. .. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields Attributes: model (str): Required. The name of the publisher model requested to serve the prediction. Format: ``projects/{project}/locations/{location}/publishers/*/models/*`` This field is a member of `oneof`_ ``_model``. content (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.Content): Required. Input content to be embedded. Required. This field is a member of `oneof`_ ``_content``. title (str): Optional. An optional title for the text. This field is a member of `oneof`_ ``_title``. task_type (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.EmbedContentRequest.EmbeddingTaskType): Optional. The task type of the embedding. This field is a member of `oneof`_ ``_task_type``. output_dimensionality (int): Optional. Optional reduced dimension for the output embedding. If set, excessive values in the output embedding are truncated from the end. This field is a member of `oneof`_ ``_output_dimensionality``. auto_truncate (bool): Optional. Whether to silently truncate the input content if it's longer than the maximum sequence length. This field is a member of `oneof`_ ``_auto_truncate``. """ class EmbeddingTaskType(proto.Enum): r"""Represents a downstream task the embeddings will be used for. Values: UNSPECIFIED (0): Unset value, which will default to one of the other enum values. RETRIEVAL_QUERY (2): Specifies the given text is a query in a search/retrieval setting. RETRIEVAL_DOCUMENT (3): Specifies the given text is a document from the corpus being searched. SEMANTIC_SIMILARITY (4): Specifies the given text will be used for STS. CLASSIFICATION (5): Specifies that the given text will be classified. CLUSTERING (6): Specifies that the embeddings will be used for clustering. QUESTION_ANSWERING (7): Specifies that the embeddings will be used for question answering. FACT_VERIFICATION (8): Specifies that the embeddings will be used for fact verification. CODE_RETRIEVAL_QUERY (9): Specifies that the embeddings will be used for code retrieval. """ UNSPECIFIED = 0 RETRIEVAL_QUERY = 2 RETRIEVAL_DOCUMENT = 3 SEMANTIC_SIMILARITY = 4 CLASSIFICATION = 5 CLUSTERING = 6 QUESTION_ANSWERING = 7 FACT_VERIFICATION = 8 CODE_RETRIEVAL_QUERY = 9 model: str = proto.Field( proto.STRING, number=1, optional=True, ) content: gca_content.Content = proto.Field( proto.MESSAGE, number=2, optional=True, message=gca_content.Content, ) title: str = proto.Field( proto.STRING, number=4, optional=True, ) task_type: EmbeddingTaskType = proto.Field( proto.ENUM, number=5, optional=True, enum=EmbeddingTaskType, ) output_dimensionality: int = proto.Field( proto.INT32, number=6, optional=True, ) auto_truncate: bool = proto.Field( proto.BOOL, number=7, optional=True, ) class EmbedContentResponse(proto.Message): r"""Response message for [PredictionService.EmbedContent][google.cloud.aiplatform.v1beta1.PredictionService.EmbedContent]. Attributes: embedding (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.EmbedContentResponse.Embedding): The embedding generated from the input content. usage_metadata (googlecloudsdk.generated_clients.gapic_clients.aiplatform_v1beta1.types.UsageMetadata): Metadata about the response(s). truncated (bool): Whether the input content was truncated before generating the embedding. """ class Embedding(proto.Message): r"""A list of floats representing an embedding. Attributes: values (MutableSequence[float]): Embedding vector values. """ values: MutableSequence[float] = proto.RepeatedField( proto.FLOAT, number=1, ) embedding: Embedding = proto.Field( proto.MESSAGE, number=1, message=Embedding, ) usage_metadata: gca_usage_metadata.UsageMetadata = proto.Field( proto.MESSAGE, number=2, message=gca_usage_metadata.UsageMetadata, ) truncated: bool = proto.Field( proto.BOOL, number=4, ) __all__ = tuple(sorted(__protobuf__.manifest))