- 3.13.0 (latest)
- 3.12.0
- 3.11.0
- 3.10.0
- 3.9.0
- 3.8.0
- 3.7.0
- 3.6.0
- 3.5.0
- 3.4.0
- 3.3.0
- 3.2.0
- 3.1.0
- 3.0.0
- 2.28.0
- 2.27.0
- 2.26.0
- 2.25.0
- 2.24.0
- 2.23.0
- 2.22.0
- 2.21.0
- 2.20.0
- 2.19.0
- 2.18.0
- 2.17.0
- 2.16.0
- 2.15.0
- 2.14.0
- 2.13.0
- 2.12.0
- 2.11.0
- 2.10.0
- 2.9.0
- 2.8.0
- 2.7.0
- 2.6.0
- 2.5.0
- 2.4.0
- 2.3.0
- 2.2.0
- 2.1.0
- 2.0.0
- 1.8.0
- 1.7.0
- 1.6.0
- 1.5.0
- 1.4.0
- 1.3.0
- 1.2.0
- 1.1.0
- 1.0.0
public abstract class PredictionServiceClient
Reference documentation and code samples for the Cloud AI Platform v1 API class PredictionServiceClient.
PredictionService client wrapper, for convenient use.
Inherited Members
Derived Types
Namespace
Google.Cloud.AIPlatform.V1Assembly
Google.Cloud.AIPlatform.V1.dll
Remarks
A service for online predictions and explanations.
Properties
DefaultEndpoint
public static string DefaultEndpoint { get; }
The default endpoint for the PredictionService service, which is a host of "aiplatform.googleapis.com" and a port of 443.
Property Value | |
---|---|
Type | Description |
string |
DefaultScopes
public static IReadOnlyList<string> DefaultScopes { get; }
The default PredictionService scopes.
Property Value | |
---|---|
Type | Description |
IReadOnlyListstring |
The default PredictionService scopes are:
GrpcClient
public virtual PredictionService.PredictionServiceClient GrpcClient { get; }
The underlying gRPC PredictionService client
Property Value | |
---|---|
Type | Description |
PredictionServicePredictionServiceClient |
IAMPolicyClient
public virtual IAMPolicyClient IAMPolicyClient { get; }
The IAMPolicyClient associated with this client.
Property Value | |
---|---|
Type | Description |
IAMPolicyClient |
LocationsClient
public virtual LocationsClient LocationsClient { get; }
The LocationsClient associated with this client.
Property Value | |
---|---|
Type | Description |
LocationsClient |
ServiceMetadata
public static ServiceMetadata ServiceMetadata { get; }
The service metadata associated with this client type.
Property Value | |
---|---|
Type | Description |
ServiceMetadata |
Methods
Create()
public static PredictionServiceClient Create()
Synchronously creates a PredictionServiceClient using the default credentials, endpoint and settings. To specify custom credentials or other settings, use PredictionServiceClientBuilder.
Returns | |
---|---|
Type | Description |
PredictionServiceClient |
The created PredictionServiceClient. |
CreateAsync(CancellationToken)
public static Task<PredictionServiceClient> CreateAsync(CancellationToken cancellationToken = default)
Asynchronously creates a PredictionServiceClient using the default credentials, endpoint and settings. To specify custom credentials or other settings, use PredictionServiceClientBuilder.
Parameter | |
---|---|
Name | Description |
cancellationToken |
CancellationToken The CancellationToken to use while creating the client. |
Returns | |
---|---|
Type | Description |
TaskPredictionServiceClient |
The task representing the created PredictionServiceClient. |
DirectPredict(DirectPredictRequest, CallSettings)
public virtual DirectPredictResponse DirectPredict(DirectPredictRequest request, CallSettings callSettings = null)
Perform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks.
Parameters | |
---|---|
Name | Description |
request |
DirectPredictRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
DirectPredictResponse |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
DirectPredictRequest request = new DirectPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Inputs = { new Tensor(), },
Parameters = new Tensor(),
};
// Make the request
DirectPredictResponse response = predictionServiceClient.DirectPredict(request);
DirectPredictAsync(DirectPredictRequest, CallSettings)
public virtual Task<DirectPredictResponse> DirectPredictAsync(DirectPredictRequest request, CallSettings callSettings = null)
Perform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks.
Parameters | |
---|---|
Name | Description |
request |
DirectPredictRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
TaskDirectPredictResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
DirectPredictRequest request = new DirectPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Inputs = { new Tensor(), },
Parameters = new Tensor(),
};
// Make the request
DirectPredictResponse response = await predictionServiceClient.DirectPredictAsync(request);
DirectPredictAsync(DirectPredictRequest, CancellationToken)
public virtual Task<DirectPredictResponse> DirectPredictAsync(DirectPredictRequest request, CancellationToken cancellationToken)
Perform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks.
Parameters | |
---|---|
Name | Description |
request |
DirectPredictRequest The request object containing all of the parameters for the API call. |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
Returns | |
---|---|
Type | Description |
TaskDirectPredictResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
DirectPredictRequest request = new DirectPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Inputs = { new Tensor(), },
Parameters = new Tensor(),
};
// Make the request
DirectPredictResponse response = await predictionServiceClient.DirectPredictAsync(request);
DirectRawPredict(DirectRawPredictRequest, CallSettings)
public virtual DirectRawPredictResponse DirectRawPredict(DirectRawPredictRequest request, CallSettings callSettings = null)
Perform an unary online prediction request to a gRPC model server for custom containers.
Parameters | |
---|---|
Name | Description |
request |
DirectRawPredictRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
DirectRawPredictResponse |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
DirectRawPredictRequest request = new DirectRawPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
MethodName = "",
Input = ByteString.Empty,
};
// Make the request
DirectRawPredictResponse response = predictionServiceClient.DirectRawPredict(request);
DirectRawPredictAsync(DirectRawPredictRequest, CallSettings)
public virtual Task<DirectRawPredictResponse> DirectRawPredictAsync(DirectRawPredictRequest request, CallSettings callSettings = null)
Perform an unary online prediction request to a gRPC model server for custom containers.
Parameters | |
---|---|
Name | Description |
request |
DirectRawPredictRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
TaskDirectRawPredictResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
DirectRawPredictRequest request = new DirectRawPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
MethodName = "",
Input = ByteString.Empty,
};
// Make the request
DirectRawPredictResponse response = await predictionServiceClient.DirectRawPredictAsync(request);
DirectRawPredictAsync(DirectRawPredictRequest, CancellationToken)
public virtual Task<DirectRawPredictResponse> DirectRawPredictAsync(DirectRawPredictRequest request, CancellationToken cancellationToken)
Perform an unary online prediction request to a gRPC model server for custom containers.
Parameters | |
---|---|
Name | Description |
request |
DirectRawPredictRequest The request object containing all of the parameters for the API call. |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
Returns | |
---|---|
Type | Description |
TaskDirectRawPredictResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
DirectRawPredictRequest request = new DirectRawPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
MethodName = "",
Input = ByteString.Empty,
};
// Make the request
DirectRawPredictResponse response = await predictionServiceClient.DirectRawPredictAsync(request);
Explain(EndpointName, IEnumerable<Value>, Value, string, CallSettings)
public virtual ExplainResponse Explain(EndpointName endpoint, IEnumerable<Value> instances, Value parameters, string deployedModelId, CallSettings callSettings = null)
Perform an online explanation.
If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.
Parameters | |
---|---|
Name | Description |
endpoint |
EndpointName Required. The name of the Endpoint requested to serve the explanation.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
deployedModelId |
string If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding [Endpoint.traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split]. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
ExplainResponse |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
EndpointName endpoint = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]");
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
string deployedModelId = "";
// Make the request
ExplainResponse response = predictionServiceClient.Explain(endpoint, instances, parameters, deployedModelId);
Explain(ExplainRequest, CallSettings)
public virtual ExplainResponse Explain(ExplainRequest request, CallSettings callSettings = null)
Perform an online explanation.
If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.
Parameters | |
---|---|
Name | Description |
request |
ExplainRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
ExplainResponse |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
ExplainRequest request = new ExplainRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Instances = { new wkt::Value(), },
DeployedModelId = "",
Parameters = new wkt::Value(),
ExplanationSpecOverride = new ExplanationSpecOverride(),
};
// Make the request
ExplainResponse response = predictionServiceClient.Explain(request);
Explain(string, IEnumerable<Value>, Value, string, CallSettings)
public virtual ExplainResponse Explain(string endpoint, IEnumerable<Value> instances, Value parameters, string deployedModelId, CallSettings callSettings = null)
Perform an online explanation.
If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.
Parameters | |
---|---|
Name | Description |
endpoint |
string Required. The name of the Endpoint requested to serve the explanation.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
deployedModelId |
string If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding [Endpoint.traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split]. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
ExplainResponse |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
string endpoint = "projects/[PROJECT]/locations/[LOCATION]/endpoints/[ENDPOINT]";
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
string deployedModelId = "";
// Make the request
ExplainResponse response = predictionServiceClient.Explain(endpoint, instances, parameters, deployedModelId);
ExplainAsync(EndpointName, IEnumerable<Value>, Value, string, CallSettings)
public virtual Task<ExplainResponse> ExplainAsync(EndpointName endpoint, IEnumerable<Value> instances, Value parameters, string deployedModelId, CallSettings callSettings = null)
Perform an online explanation.
If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.
Parameters | |
---|---|
Name | Description |
endpoint |
EndpointName Required. The name of the Endpoint requested to serve the explanation.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
deployedModelId |
string If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding [Endpoint.traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split]. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
TaskExplainResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
EndpointName endpoint = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]");
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
string deployedModelId = "";
// Make the request
ExplainResponse response = await predictionServiceClient.ExplainAsync(endpoint, instances, parameters, deployedModelId);
ExplainAsync(EndpointName, IEnumerable<Value>, Value, string, CancellationToken)
public virtual Task<ExplainResponse> ExplainAsync(EndpointName endpoint, IEnumerable<Value> instances, Value parameters, string deployedModelId, CancellationToken cancellationToken)
Perform an online explanation.
If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.
Parameters | |
---|---|
Name | Description |
endpoint |
EndpointName Required. The name of the Endpoint requested to serve the explanation.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
deployedModelId |
string If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding [Endpoint.traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split]. |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
Returns | |
---|---|
Type | Description |
TaskExplainResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
EndpointName endpoint = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]");
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
string deployedModelId = "";
// Make the request
ExplainResponse response = await predictionServiceClient.ExplainAsync(endpoint, instances, parameters, deployedModelId);
ExplainAsync(ExplainRequest, CallSettings)
public virtual Task<ExplainResponse> ExplainAsync(ExplainRequest request, CallSettings callSettings = null)
Perform an online explanation.
If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.
Parameters | |
---|---|
Name | Description |
request |
ExplainRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
TaskExplainResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
ExplainRequest request = new ExplainRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Instances = { new wkt::Value(), },
DeployedModelId = "",
Parameters = new wkt::Value(),
ExplanationSpecOverride = new ExplanationSpecOverride(),
};
// Make the request
ExplainResponse response = await predictionServiceClient.ExplainAsync(request);
ExplainAsync(ExplainRequest, CancellationToken)
public virtual Task<ExplainResponse> ExplainAsync(ExplainRequest request, CancellationToken cancellationToken)
Perform an online explanation.
If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.
Parameters | |
---|---|
Name | Description |
request |
ExplainRequest The request object containing all of the parameters for the API call. |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
Returns | |
---|---|
Type | Description |
TaskExplainResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
ExplainRequest request = new ExplainRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Instances = { new wkt::Value(), },
DeployedModelId = "",
Parameters = new wkt::Value(),
ExplanationSpecOverride = new ExplanationSpecOverride(),
};
// Make the request
ExplainResponse response = await predictionServiceClient.ExplainAsync(request);
ExplainAsync(string, IEnumerable<Value>, Value, string, CallSettings)
public virtual Task<ExplainResponse> ExplainAsync(string endpoint, IEnumerable<Value> instances, Value parameters, string deployedModelId, CallSettings callSettings = null)
Perform an online explanation.
If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.
Parameters | |
---|---|
Name | Description |
endpoint |
string Required. The name of the Endpoint requested to serve the explanation.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
deployedModelId |
string If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding [Endpoint.traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split]. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
TaskExplainResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
string endpoint = "projects/[PROJECT]/locations/[LOCATION]/endpoints/[ENDPOINT]";
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
string deployedModelId = "";
// Make the request
ExplainResponse response = await predictionServiceClient.ExplainAsync(endpoint, instances, parameters, deployedModelId);
ExplainAsync(string, IEnumerable<Value>, Value, string, CancellationToken)
public virtual Task<ExplainResponse> ExplainAsync(string endpoint, IEnumerable<Value> instances, Value parameters, string deployedModelId, CancellationToken cancellationToken)
Perform an online explanation.
If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.
Parameters | |
---|---|
Name | Description |
endpoint |
string Required. The name of the Endpoint requested to serve the explanation.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
deployedModelId |
string If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding [Endpoint.traffic_split][google.cloud.aiplatform.v1.Endpoint.traffic_split]. |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
Returns | |
---|---|
Type | Description |
TaskExplainResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
string endpoint = "projects/[PROJECT]/locations/[LOCATION]/endpoints/[ENDPOINT]";
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
string deployedModelId = "";
// Make the request
ExplainResponse response = await predictionServiceClient.ExplainAsync(endpoint, instances, parameters, deployedModelId);
GenerateContent(GenerateContentRequest, CallSettings)
public virtual GenerateContentResponse GenerateContent(GenerateContentRequest request, CallSettings callSettings = null)
Generate content with multimodal inputs.
Parameters | |
---|---|
Name | Description |
request |
GenerateContentRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
GenerateContentResponse |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
GenerateContentRequest request = new GenerateContentRequest
{
Contents = { new Content(), },
SafetySettings =
{
new SafetySetting(),
},
GenerationConfig = new GenerationConfig(),
Model = "",
Tools = { new Tool(), },
ToolConfig = new ToolConfig(),
SystemInstruction = new Content(),
Labels = { { "", "" }, },
};
// Make the request
GenerateContentResponse response = predictionServiceClient.GenerateContent(request);
GenerateContent(string, IEnumerable<Content>, CallSettings)
public virtual GenerateContentResponse GenerateContent(string model, IEnumerable<Content> contents, CallSettings callSettings = null)
Generate content with multimodal inputs.
Parameters | |
---|---|
Name | Description |
model |
string Required. The fully qualified name of the publisher model or tuned model endpoint to use. Publisher model format:
Tuned model endpoint format:
|
contents |
IEnumerableContent 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. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
GenerateContentResponse |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
string model = "";
IEnumerable<Content> contents = new Content[] { new Content(), };
// Make the request
GenerateContentResponse response = predictionServiceClient.GenerateContent(model, contents);
GenerateContentAsync(GenerateContentRequest, CallSettings)
public virtual Task<GenerateContentResponse> GenerateContentAsync(GenerateContentRequest request, CallSettings callSettings = null)
Generate content with multimodal inputs.
Parameters | |
---|---|
Name | Description |
request |
GenerateContentRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
TaskGenerateContentResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
GenerateContentRequest request = new GenerateContentRequest
{
Contents = { new Content(), },
SafetySettings =
{
new SafetySetting(),
},
GenerationConfig = new GenerationConfig(),
Model = "",
Tools = { new Tool(), },
ToolConfig = new ToolConfig(),
SystemInstruction = new Content(),
Labels = { { "", "" }, },
};
// Make the request
GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(request);
GenerateContentAsync(GenerateContentRequest, CancellationToken)
public virtual Task<GenerateContentResponse> GenerateContentAsync(GenerateContentRequest request, CancellationToken cancellationToken)
Generate content with multimodal inputs.
Parameters | |
---|---|
Name | Description |
request |
GenerateContentRequest The request object containing all of the parameters for the API call. |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
Returns | |
---|---|
Type | Description |
TaskGenerateContentResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
GenerateContentRequest request = new GenerateContentRequest
{
Contents = { new Content(), },
SafetySettings =
{
new SafetySetting(),
},
GenerationConfig = new GenerationConfig(),
Model = "",
Tools = { new Tool(), },
ToolConfig = new ToolConfig(),
SystemInstruction = new Content(),
Labels = { { "", "" }, },
};
// Make the request
GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(request);
GenerateContentAsync(string, IEnumerable<Content>, CallSettings)
public virtual Task<GenerateContentResponse> GenerateContentAsync(string model, IEnumerable<Content> contents, CallSettings callSettings = null)
Generate content with multimodal inputs.
Parameters | |
---|---|
Name | Description |
model |
string Required. The fully qualified name of the publisher model or tuned model endpoint to use. Publisher model format:
Tuned model endpoint format:
|
contents |
IEnumerableContent 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. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
TaskGenerateContentResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
string model = "";
IEnumerable<Content> contents = new Content[] { new Content(), };
// Make the request
GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(model, contents);
GenerateContentAsync(string, IEnumerable<Content>, CancellationToken)
public virtual Task<GenerateContentResponse> GenerateContentAsync(string model, IEnumerable<Content> contents, CancellationToken cancellationToken)
Generate content with multimodal inputs.
Parameters | |
---|---|
Name | Description |
model |
string Required. The fully qualified name of the publisher model or tuned model endpoint to use. Publisher model format:
Tuned model endpoint format:
|
contents |
IEnumerableContent 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. |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
Returns | |
---|---|
Type | Description |
TaskGenerateContentResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
string model = "";
IEnumerable<Content> contents = new Content[] { new Content(), };
// Make the request
GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(model, contents);
Predict(EndpointName, IEnumerable<Value>, Value, CallSettings)
public virtual PredictResponse Predict(EndpointName endpoint, IEnumerable<Value> instances, Value parameters, CallSettings callSettings = null)
Perform an online prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
EndpointName Required. The name of the Endpoint requested to serve the prediction.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictResponse |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
EndpointName endpoint = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]");
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
// Make the request
PredictResponse response = predictionServiceClient.Predict(endpoint, instances, parameters);
Predict(PredictRequest, CallSettings)
public virtual PredictResponse Predict(PredictRequest request, CallSettings callSettings = null)
Perform an online prediction.
Parameters | |
---|---|
Name | Description |
request |
PredictRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictResponse |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
PredictRequest request = new PredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Instances = { new wkt::Value(), },
Parameters = new wkt::Value(),
};
// Make the request
PredictResponse response = predictionServiceClient.Predict(request);
Predict(string, IEnumerable<Value>, Value, CallSettings)
public virtual PredictResponse Predict(string endpoint, IEnumerable<Value> instances, Value parameters, CallSettings callSettings = null)
Perform an online prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
string Required. The name of the Endpoint requested to serve the prediction.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictResponse |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
string endpoint = "projects/[PROJECT]/locations/[LOCATION]/endpoints/[ENDPOINT]";
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
// Make the request
PredictResponse response = predictionServiceClient.Predict(endpoint, instances, parameters);
PredictAsync(EndpointName, IEnumerable<Value>, Value, CallSettings)
public virtual Task<PredictResponse> PredictAsync(EndpointName endpoint, IEnumerable<Value> instances, Value parameters, CallSettings callSettings = null)
Perform an online prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
EndpointName Required. The name of the Endpoint requested to serve the prediction.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
TaskPredictResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
EndpointName endpoint = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]");
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
// Make the request
PredictResponse response = await predictionServiceClient.PredictAsync(endpoint, instances, parameters);
PredictAsync(EndpointName, IEnumerable<Value>, Value, CancellationToken)
public virtual Task<PredictResponse> PredictAsync(EndpointName endpoint, IEnumerable<Value> instances, Value parameters, CancellationToken cancellationToken)
Perform an online prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
EndpointName Required. The name of the Endpoint requested to serve the prediction.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
Returns | |
---|---|
Type | Description |
TaskPredictResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
EndpointName endpoint = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]");
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
// Make the request
PredictResponse response = await predictionServiceClient.PredictAsync(endpoint, instances, parameters);
PredictAsync(PredictRequest, CallSettings)
public virtual Task<PredictResponse> PredictAsync(PredictRequest request, CallSettings callSettings = null)
Perform an online prediction.
Parameters | |
---|---|
Name | Description |
request |
PredictRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
TaskPredictResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
PredictRequest request = new PredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Instances = { new wkt::Value(), },
Parameters = new wkt::Value(),
};
// Make the request
PredictResponse response = await predictionServiceClient.PredictAsync(request);
PredictAsync(PredictRequest, CancellationToken)
public virtual Task<PredictResponse> PredictAsync(PredictRequest request, CancellationToken cancellationToken)
Perform an online prediction.
Parameters | |
---|---|
Name | Description |
request |
PredictRequest The request object containing all of the parameters for the API call. |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
Returns | |
---|---|
Type | Description |
TaskPredictResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
PredictRequest request = new PredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Instances = { new wkt::Value(), },
Parameters = new wkt::Value(),
};
// Make the request
PredictResponse response = await predictionServiceClient.PredictAsync(request);
PredictAsync(string, IEnumerable<Value>, Value, CallSettings)
public virtual Task<PredictResponse> PredictAsync(string endpoint, IEnumerable<Value> instances, Value parameters, CallSettings callSettings = null)
Perform an online prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
string Required. The name of the Endpoint requested to serve the prediction.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
TaskPredictResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
string endpoint = "projects/[PROJECT]/locations/[LOCATION]/endpoints/[ENDPOINT]";
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
// Make the request
PredictResponse response = await predictionServiceClient.PredictAsync(endpoint, instances, parameters);
PredictAsync(string, IEnumerable<Value>, Value, CancellationToken)
public virtual Task<PredictResponse> PredictAsync(string endpoint, IEnumerable<Value> instances, Value parameters, CancellationToken cancellationToken)
Perform an online prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
string Required. The name of the Endpoint requested to serve the prediction.
Format:
|
instances |
IEnumerableValue 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.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]. |
parameters |
Value The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]. |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
Returns | |
---|---|
Type | Description |
TaskPredictResponse |
A Task containing the RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
string endpoint = "projects/[PROJECT]/locations/[LOCATION]/endpoints/[ENDPOINT]";
IEnumerable<wkt::Value> instances = new wkt::Value[] { new wkt::Value(), };
wkt::Value parameters = new wkt::Value();
// Make the request
PredictResponse response = await predictionServiceClient.PredictAsync(endpoint, instances, parameters);
RawPredict(EndpointName, HttpBody, CallSettings)
public virtual HttpBody RawPredict(EndpointName endpoint, HttpBody httpBody, CallSettings callSettings = null)
Perform an online prediction with an arbitrary HTTP payload.
The response includes the following HTTP headers:
X-Vertex-AI-Endpoint-Id
: ID of the [Endpoint][google.cloud.aiplatform.v1.Endpoint] that served this prediction.X-Vertex-AI-Deployed-Model-Id
: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
EndpointName Required. The name of the Endpoint requested to serve the prediction.
Format:
|
httpBody |
HttpBody The prediction input. Supports HTTP headers and arbitrary data payload. A [DeployedModel][google.cloud.aiplatform.v1.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.v1.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.v1.PredictSchemata.instance_schema_uri]
field when you create a [Model][google.cloud.aiplatform.v1.Model]. This
schema applies when you deploy the |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
HttpBody |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
EndpointName endpoint = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]");
HttpBody httpBody = new HttpBody();
// Make the request
HttpBody response = predictionServiceClient.RawPredict(endpoint, httpBody);
RawPredict(RawPredictRequest, CallSettings)
public virtual HttpBody RawPredict(RawPredictRequest request, CallSettings callSettings = null)
Perform an online prediction with an arbitrary HTTP payload.
The response includes the following HTTP headers:
X-Vertex-AI-Endpoint-Id
: ID of the [Endpoint][google.cloud.aiplatform.v1.Endpoint] that served this prediction.X-Vertex-AI-Deployed-Model-Id
: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.
Parameters | |
---|---|
Name | Description |
request |
RawPredictRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
HttpBody |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
RawPredictRequest request = new RawPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
HttpBody = new HttpBody(),
};
// Make the request
HttpBody response = predictionServiceClient.RawPredict(request);
RawPredict(string, HttpBody, CallSettings)
public virtual HttpBody RawPredict(string endpoint, HttpBody httpBody, CallSettings callSettings = null)
Perform an online prediction with an arbitrary HTTP payload.
The response includes the following HTTP headers:
X-Vertex-AI-Endpoint-Id
: ID of the [Endpoint][google.cloud.aiplatform.v1.Endpoint] that served this prediction.X-Vertex-AI-Deployed-Model-Id
: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
string Required. The name of the Endpoint requested to serve the prediction.
Format:
|
httpBody |
HttpBody The prediction input. Supports HTTP headers and arbitrary data payload. A [DeployedModel][google.cloud.aiplatform.v1.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.v1.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.v1.PredictSchemata.instance_schema_uri]
field when you create a [Model][google.cloud.aiplatform.v1.Model]. This
schema applies when you deploy the |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
HttpBody |
The RPC response. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
string endpoint = "projects/[PROJECT]/locations/[LOCATION]/endpoints/[ENDPOINT]";
HttpBody httpBody = new HttpBody();
// Make the request
HttpBody response = predictionServiceClient.RawPredict(endpoint, httpBody);
RawPredictAsync(EndpointName, HttpBody, CallSettings)
public virtual Task<HttpBody> RawPredictAsync(EndpointName endpoint, HttpBody httpBody, CallSettings callSettings = null)
Perform an online prediction with an arbitrary HTTP payload.
The response includes the following HTTP headers:
X-Vertex-AI-Endpoint-Id
: ID of the [Endpoint][google.cloud.aiplatform.v1.Endpoint] that served this prediction.X-Vertex-AI-Deployed-Model-Id
: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
EndpointName Required. The name of the Endpoint requested to serve the prediction.
Format:
|
httpBody |
HttpBody The prediction input. Supports HTTP headers and arbitrary data payload. A [DeployedModel][google.cloud.aiplatform.v1.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.v1.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.v1.PredictSchemata.instance_schema_uri]
field when you create a [Model][google.cloud.aiplatform.v1.Model]. This
schema applies when you deploy the |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
EndpointName endpoint = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]");
HttpBody httpBody = new HttpBody();
// Make the request
HttpBody response = await predictionServiceClient.RawPredictAsync(endpoint, httpBody);
RawPredictAsync(EndpointName, HttpBody, CancellationToken)
public virtual Task<HttpBody> RawPredictAsync(EndpointName endpoint, HttpBody httpBody, CancellationToken cancellationToken)
Perform an online prediction with an arbitrary HTTP payload.
The response includes the following HTTP headers:
X-Vertex-AI-Endpoint-Id
: ID of the [Endpoint][google.cloud.aiplatform.v1.Endpoint] that served this prediction.X-Vertex-AI-Deployed-Model-Id
: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
EndpointName Required. The name of the Endpoint requested to serve the prediction.
Format:
|
httpBody |
HttpBody The prediction input. Supports HTTP headers and arbitrary data payload. A [DeployedModel][google.cloud.aiplatform.v1.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.v1.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.v1.PredictSchemata.instance_schema_uri]
field when you create a [Model][google.cloud.aiplatform.v1.Model]. This
schema applies when you deploy the |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
EndpointName endpoint = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]");
HttpBody httpBody = new HttpBody();
// Make the request
HttpBody response = await predictionServiceClient.RawPredictAsync(endpoint, httpBody);
RawPredictAsync(RawPredictRequest, CallSettings)
public virtual Task<HttpBody> RawPredictAsync(RawPredictRequest request, CallSettings callSettings = null)
Perform an online prediction with an arbitrary HTTP payload.
The response includes the following HTTP headers:
X-Vertex-AI-Endpoint-Id
: ID of the [Endpoint][google.cloud.aiplatform.v1.Endpoint] that served this prediction.X-Vertex-AI-Deployed-Model-Id
: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.
Parameters | |
---|---|
Name | Description |
request |
RawPredictRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
RawPredictRequest request = new RawPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
HttpBody = new HttpBody(),
};
// Make the request
HttpBody response = await predictionServiceClient.RawPredictAsync(request);
RawPredictAsync(RawPredictRequest, CancellationToken)
public virtual Task<HttpBody> RawPredictAsync(RawPredictRequest request, CancellationToken cancellationToken)
Perform an online prediction with an arbitrary HTTP payload.
The response includes the following HTTP headers:
X-Vertex-AI-Endpoint-Id
: ID of the [Endpoint][google.cloud.aiplatform.v1.Endpoint] that served this prediction.X-Vertex-AI-Deployed-Model-Id
: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.
Parameters | |
---|---|
Name | Description |
request |
RawPredictRequest The request object containing all of the parameters for the API call. |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
RawPredictRequest request = new RawPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
HttpBody = new HttpBody(),
};
// Make the request
HttpBody response = await predictionServiceClient.RawPredictAsync(request);
RawPredictAsync(string, HttpBody, CallSettings)
public virtual Task<HttpBody> RawPredictAsync(string endpoint, HttpBody httpBody, CallSettings callSettings = null)
Perform an online prediction with an arbitrary HTTP payload.
The response includes the following HTTP headers:
X-Vertex-AI-Endpoint-Id
: ID of the [Endpoint][google.cloud.aiplatform.v1.Endpoint] that served this prediction.X-Vertex-AI-Deployed-Model-Id
: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
string Required. The name of the Endpoint requested to serve the prediction.
Format:
|
httpBody |
HttpBody The prediction input. Supports HTTP headers and arbitrary data payload. A [DeployedModel][google.cloud.aiplatform.v1.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.v1.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.v1.PredictSchemata.instance_schema_uri]
field when you create a [Model][google.cloud.aiplatform.v1.Model]. This
schema applies when you deploy the |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
string endpoint = "projects/[PROJECT]/locations/[LOCATION]/endpoints/[ENDPOINT]";
HttpBody httpBody = new HttpBody();
// Make the request
HttpBody response = await predictionServiceClient.RawPredictAsync(endpoint, httpBody);
RawPredictAsync(string, HttpBody, CancellationToken)
public virtual Task<HttpBody> RawPredictAsync(string endpoint, HttpBody httpBody, CancellationToken cancellationToken)
Perform an online prediction with an arbitrary HTTP payload.
The response includes the following HTTP headers:
X-Vertex-AI-Endpoint-Id
: ID of the [Endpoint][google.cloud.aiplatform.v1.Endpoint] that served this prediction.X-Vertex-AI-Deployed-Model-Id
: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.
Parameters | |
---|---|
Name | Description |
endpoint |
string Required. The name of the Endpoint requested to serve the prediction.
Format:
|
httpBody |
HttpBody The prediction input. Supports HTTP headers and arbitrary data payload. A [DeployedModel][google.cloud.aiplatform.v1.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.v1.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.v1.PredictSchemata.instance_schema_uri]
field when you create a [Model][google.cloud.aiplatform.v1.Model]. This
schema applies when you deploy the |
cancellationToken |
CancellationToken A CancellationToken to use for this RPC. |
// Create client
PredictionServiceClient predictionServiceClient = await PredictionServiceClient.CreateAsync();
// Initialize request argument(s)
string endpoint = "projects/[PROJECT]/locations/[LOCATION]/endpoints/[ENDPOINT]";
HttpBody httpBody = new HttpBody();
// Make the request
HttpBody response = await predictionServiceClient.RawPredictAsync(endpoint, httpBody);
ServerStreamingPredict(StreamingPredictRequest, CallSettings)
public virtual PredictionServiceClient.ServerStreamingPredictStream ServerStreamingPredict(StreamingPredictRequest request, CallSettings callSettings = null)
Perform a server-side streaming online prediction request for Vertex LLM streaming.
Parameters | |
---|---|
Name | Description |
request |
StreamingPredictRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictionServiceClientServerStreamingPredictStream |
The server stream. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
StreamingPredictRequest request = new StreamingPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Inputs = { new Tensor(), },
Parameters = new Tensor(),
};
// Make the request, returning a streaming response
using PredictionServiceClient.ServerStreamingPredictStream response = predictionServiceClient.ServerStreamingPredict(request);
// Read streaming responses from server until complete
// Note that C# 8 code can use await foreach
AsyncResponseStream<StreamingPredictResponse> responseStream = response.GetResponseStream();
while (await responseStream.MoveNextAsync())
{
StreamingPredictResponse responseItem = responseStream.Current;
// Do something with streamed response
}
// The response stream has completed
ShutdownDefaultChannelsAsync()
public static Task ShutdownDefaultChannelsAsync()
Shuts down any channels automatically created by Create() and CreateAsync(CancellationToken). Channels which weren't automatically created are not affected.
Returns | |
---|---|
Type | Description |
Task |
A task representing the asynchronous shutdown operation. |
After calling this method, further calls to Create() and CreateAsync(CancellationToken) will create new channels, which could in turn be shut down by another call to this method.
StreamDirectPredict(CallSettings, BidirectionalStreamingSettings)
public virtual PredictionServiceClient.StreamDirectPredictStream StreamDirectPredict(CallSettings callSettings = null, BidirectionalStreamingSettings streamingSettings = null)
Perform a streaming online prediction request to a gRPC model server for Vertex first-party products and frameworks.
Parameters | |
---|---|
Name | Description |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
streamingSettings |
BidirectionalStreamingSettings If not null, applies streaming overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictionServiceClientStreamDirectPredictStream |
The client-server stream. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize streaming call, retrieving the stream object
using PredictionServiceClient.StreamDirectPredictStream response = predictionServiceClient.StreamDirectPredict();
// Sending requests and retrieving responses can be arbitrarily interleaved
// Exact sequence will depend on client/server behavior
// Create task to do something with responses from server
Task responseHandlerTask = Task.Run(async () =>
{
// Note that C# 8 code can use await foreach
AsyncResponseStream<StreamDirectPredictResponse> responseStream = response.GetResponseStream();
while (await responseStream.MoveNextAsync())
{
StreamDirectPredictResponse responseItem = responseStream.Current;
// Do something with streamed response
}
// The response stream has completed
});
// Send requests to the server
bool done = false;
while (!done)
{
// Initialize a request
StreamDirectPredictRequest request = new StreamDirectPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Inputs = { new Tensor(), },
Parameters = new Tensor(),
};
// Stream a request to the server
await response.WriteAsync(request);
// Set "done" to true when sending requests is complete
}
// Complete writing requests to the stream
await response.WriteCompleteAsync();
// Await the response handler
// This will complete once all server responses have been processed
await responseHandlerTask;
StreamDirectRawPredict(CallSettings, BidirectionalStreamingSettings)
public virtual PredictionServiceClient.StreamDirectRawPredictStream StreamDirectRawPredict(CallSettings callSettings = null, BidirectionalStreamingSettings streamingSettings = null)
Perform a streaming online prediction request to a gRPC model server for custom containers.
Parameters | |
---|---|
Name | Description |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
streamingSettings |
BidirectionalStreamingSettings If not null, applies streaming overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictionServiceClientStreamDirectRawPredictStream |
The client-server stream. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize streaming call, retrieving the stream object
using PredictionServiceClient.StreamDirectRawPredictStream response = predictionServiceClient.StreamDirectRawPredict();
// Sending requests and retrieving responses can be arbitrarily interleaved
// Exact sequence will depend on client/server behavior
// Create task to do something with responses from server
Task responseHandlerTask = Task.Run(async () =>
{
// Note that C# 8 code can use await foreach
AsyncResponseStream<StreamDirectRawPredictResponse> responseStream = response.GetResponseStream();
while (await responseStream.MoveNextAsync())
{
StreamDirectRawPredictResponse responseItem = responseStream.Current;
// Do something with streamed response
}
// The response stream has completed
});
// Send requests to the server
bool done = false;
while (!done)
{
// Initialize a request
StreamDirectRawPredictRequest request = new StreamDirectRawPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
MethodName = "",
Input = ByteString.Empty,
};
// Stream a request to the server
await response.WriteAsync(request);
// Set "done" to true when sending requests is complete
}
// Complete writing requests to the stream
await response.WriteCompleteAsync();
// Await the response handler
// This will complete once all server responses have been processed
await responseHandlerTask;
StreamGenerateContent(GenerateContentRequest, CallSettings)
public virtual PredictionServiceClient.StreamGenerateContentStream StreamGenerateContent(GenerateContentRequest request, CallSettings callSettings = null)
Generate content with multimodal inputs with streaming support.
Parameters | |
---|---|
Name | Description |
request |
GenerateContentRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictionServiceClientStreamGenerateContentStream |
The server stream. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
GenerateContentRequest request = new GenerateContentRequest
{
Contents = { new Content(), },
SafetySettings =
{
new SafetySetting(),
},
GenerationConfig = new GenerationConfig(),
Model = "",
Tools = { new Tool(), },
ToolConfig = new ToolConfig(),
SystemInstruction = new Content(),
Labels = { { "", "" }, },
};
// Make the request, returning a streaming response
using PredictionServiceClient.StreamGenerateContentStream response = predictionServiceClient.StreamGenerateContent(request);
// Read streaming responses from server until complete
// Note that C# 8 code can use await foreach
AsyncResponseStream<GenerateContentResponse> responseStream = response.GetResponseStream();
while (await responseStream.MoveNextAsync())
{
GenerateContentResponse responseItem = responseStream.Current;
// Do something with streamed response
}
// The response stream has completed
StreamGenerateContent(string, IEnumerable<Content>, CallSettings)
public virtual PredictionServiceClient.StreamGenerateContentStream StreamGenerateContent(string model, IEnumerable<Content> contents, CallSettings callSettings = null)
Generate content with multimodal inputs with streaming support.
Parameters | |
---|---|
Name | Description |
model |
string Required. The fully qualified name of the publisher model or tuned model endpoint to use. Publisher model format:
Tuned model endpoint format:
|
contents |
IEnumerableContent 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. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictionServiceClientStreamGenerateContentStream |
The server stream. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
string model = "";
IEnumerable<Content> contents = new Content[] { new Content(), };
// Make the request, returning a streaming response
using PredictionServiceClient.StreamGenerateContentStream response = predictionServiceClient.StreamGenerateContent(model, contents);
// Read streaming responses from server until complete
// Note that C# 8 code can use await foreach
AsyncResponseStream<GenerateContentResponse> responseStream = response.GetResponseStream();
while (await responseStream.MoveNextAsync())
{
GenerateContentResponse responseItem = responseStream.Current;
// Do something with streamed response
}
// The response stream has completed
StreamRawPredict(EndpointName, HttpBody, CallSettings)
public virtual PredictionServiceClient.StreamRawPredictStream StreamRawPredict(EndpointName endpoint, HttpBody httpBody, CallSettings callSettings = null)
Perform a streaming online prediction with an arbitrary HTTP payload.
Parameters | |
---|---|
Name | Description |
endpoint |
EndpointName Required. The name of the Endpoint requested to serve the prediction.
Format:
|
httpBody |
HttpBody The prediction input. Supports HTTP headers and arbitrary data payload. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictionServiceClientStreamRawPredictStream |
The server stream. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
EndpointName endpoint = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]");
HttpBody httpBody = new HttpBody();
// Make the request, returning a streaming response
using PredictionServiceClient.StreamRawPredictStream response = predictionServiceClient.StreamRawPredict(endpoint, httpBody);
// Read streaming responses from server until complete
// Note that C# 8 code can use await foreach
AsyncResponseStream<HttpBody> responseStream = response.GetResponseStream();
while (await responseStream.MoveNextAsync())
{
HttpBody responseItem = responseStream.Current;
// Do something with streamed response
}
// The response stream has completed
StreamRawPredict(StreamRawPredictRequest, CallSettings)
public virtual PredictionServiceClient.StreamRawPredictStream StreamRawPredict(StreamRawPredictRequest request, CallSettings callSettings = null)
Perform a streaming online prediction with an arbitrary HTTP payload.
Parameters | |
---|---|
Name | Description |
request |
StreamRawPredictRequest The request object containing all of the parameters for the API call. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictionServiceClientStreamRawPredictStream |
The server stream. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
StreamRawPredictRequest request = new StreamRawPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
HttpBody = new HttpBody(),
};
// Make the request, returning a streaming response
using PredictionServiceClient.StreamRawPredictStream response = predictionServiceClient.StreamRawPredict(request);
// Read streaming responses from server until complete
// Note that C# 8 code can use await foreach
AsyncResponseStream<HttpBody> responseStream = response.GetResponseStream();
while (await responseStream.MoveNextAsync())
{
HttpBody responseItem = responseStream.Current;
// Do something with streamed response
}
// The response stream has completed
StreamRawPredict(string, HttpBody, CallSettings)
public virtual PredictionServiceClient.StreamRawPredictStream StreamRawPredict(string endpoint, HttpBody httpBody, CallSettings callSettings = null)
Perform a streaming online prediction with an arbitrary HTTP payload.
Parameters | |
---|---|
Name | Description |
endpoint |
string Required. The name of the Endpoint requested to serve the prediction.
Format:
|
httpBody |
HttpBody The prediction input. Supports HTTP headers and arbitrary data payload. |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictionServiceClientStreamRawPredictStream |
The server stream. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize request argument(s)
string endpoint = "projects/[PROJECT]/locations/[LOCATION]/endpoints/[ENDPOINT]";
HttpBody httpBody = new HttpBody();
// Make the request, returning a streaming response
using PredictionServiceClient.StreamRawPredictStream response = predictionServiceClient.StreamRawPredict(endpoint, httpBody);
// Read streaming responses from server until complete
// Note that C# 8 code can use await foreach
AsyncResponseStream<HttpBody> responseStream = response.GetResponseStream();
while (await responseStream.MoveNextAsync())
{
HttpBody responseItem = responseStream.Current;
// Do something with streamed response
}
// The response stream has completed
StreamingPredict(CallSettings, BidirectionalStreamingSettings)
public virtual PredictionServiceClient.StreamingPredictStream StreamingPredict(CallSettings callSettings = null, BidirectionalStreamingSettings streamingSettings = null)
Perform a streaming online prediction request for Vertex first-party products and frameworks.
Parameters | |
---|---|
Name | Description |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
streamingSettings |
BidirectionalStreamingSettings If not null, applies streaming overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictionServiceClientStreamingPredictStream |
The client-server stream. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize streaming call, retrieving the stream object
using PredictionServiceClient.StreamingPredictStream response = predictionServiceClient.StreamingPredict();
// Sending requests and retrieving responses can be arbitrarily interleaved
// Exact sequence will depend on client/server behavior
// Create task to do something with responses from server
Task responseHandlerTask = Task.Run(async () =>
{
// Note that C# 8 code can use await foreach
AsyncResponseStream<StreamingPredictResponse> responseStream = response.GetResponseStream();
while (await responseStream.MoveNextAsync())
{
StreamingPredictResponse responseItem = responseStream.Current;
// Do something with streamed response
}
// The response stream has completed
});
// Send requests to the server
bool done = false;
while (!done)
{
// Initialize a request
StreamingPredictRequest request = new StreamingPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
Inputs = { new Tensor(), },
Parameters = new Tensor(),
};
// Stream a request to the server
await response.WriteAsync(request);
// Set "done" to true when sending requests is complete
}
// Complete writing requests to the stream
await response.WriteCompleteAsync();
// Await the response handler
// This will complete once all server responses have been processed
await responseHandlerTask;
StreamingRawPredict(CallSettings, BidirectionalStreamingSettings)
public virtual PredictionServiceClient.StreamingRawPredictStream StreamingRawPredict(CallSettings callSettings = null, BidirectionalStreamingSettings streamingSettings = null)
Perform a streaming online prediction request through gRPC.
Parameters | |
---|---|
Name | Description |
callSettings |
CallSettings If not null, applies overrides to this RPC call. |
streamingSettings |
BidirectionalStreamingSettings If not null, applies streaming overrides to this RPC call. |
Returns | |
---|---|
Type | Description |
PredictionServiceClientStreamingRawPredictStream |
The client-server stream. |
// Create client
PredictionServiceClient predictionServiceClient = PredictionServiceClient.Create();
// Initialize streaming call, retrieving the stream object
using PredictionServiceClient.StreamingRawPredictStream response = predictionServiceClient.StreamingRawPredict();
// Sending requests and retrieving responses can be arbitrarily interleaved
// Exact sequence will depend on client/server behavior
// Create task to do something with responses from server
Task responseHandlerTask = Task.Run(async () =>
{
// Note that C# 8 code can use await foreach
AsyncResponseStream<StreamingRawPredictResponse> responseStream = response.GetResponseStream();
while (await responseStream.MoveNextAsync())
{
StreamingRawPredictResponse responseItem = responseStream.Current;
// Do something with streamed response
}
// The response stream has completed
});
// Send requests to the server
bool done = false;
while (!done)
{
// Initialize a request
StreamingRawPredictRequest request = new StreamingRawPredictRequest
{
EndpointAsEndpointName = EndpointName.FromProjectLocationEndpoint("[PROJECT]", "[LOCATION]", "[ENDPOINT]"),
MethodName = "",
Input = ByteString.Empty,
};
// Stream a request to the server
await response.WriteAsync(request);
// Set "done" to true when sending requests is complete
}
// Complete writing requests to the stream
await response.WriteCompleteAsync();
// Await the response handler
// This will complete once all server responses have been processed
await responseHandlerTask;