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'sPredictSchemata'sinstance_schema_uri.
If specified, overrides theexplanation_specof 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.
↳ deployed_model_id
string
If specified, this ExplainRequest will be served by the chosen DeployedModel, overridingEndpoint.traffic_split.
getEndpoint
Required. The name of the Endpoint requested to serve the explanation.
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'sPredictSchemata'sinstance_schema_uri.
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'sPredictSchemata'sinstance_schema_uri.
If specified, this ExplainRequest will be served by the chosen
DeployedModel, overridingEndpoint.traffic_split.
Returns
Type
Description
string
setDeployedModelId
If specified, this ExplainRequest will be served by the chosen
DeployedModel, overridingEndpoint.traffic_split.
Parameter
Name
Description
var
string
Returns
Type
Description
$this
static::build
Parameters
Name
Description
endpoint
string
Required. The name of the Endpoint requested to serve the explanation.
Format:projects/{project}/locations/{location}/endpoints/{endpoint}Please seePredictionServiceClient::endpointName()for help formatting this field.
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'sPredictSchemata'sinstance_schema_uri.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[],[],null,["# Google Cloud Ai Platform V1 Client - Class ExplainRequest (1.35.0)\n\nVersion latestkeyboard_arrow_down\n\n- [1.35.0 (latest)](/php/docs/reference/cloud-ai-platform/latest/V1.ExplainRequest)\n- [1.34.0](/php/docs/reference/cloud-ai-platform/1.34.0/V1.ExplainRequest)\n- [1.33.0](/php/docs/reference/cloud-ai-platform/1.33.0/V1.ExplainRequest)\n- [1.32.1](/php/docs/reference/cloud-ai-platform/1.32.1/V1.ExplainRequest)\n- [1.31.0](/php/docs/reference/cloud-ai-platform/1.31.0/V1.ExplainRequest)\n- [1.30.0](/php/docs/reference/cloud-ai-platform/1.30.0/V1.ExplainRequest)\n- [1.26.0](/php/docs/reference/cloud-ai-platform/1.26.0/V1.ExplainRequest)\n- [1.23.0](/php/docs/reference/cloud-ai-platform/1.23.0/V1.ExplainRequest)\n- [1.22.0](/php/docs/reference/cloud-ai-platform/1.22.0/V1.ExplainRequest)\n- [1.21.0](/php/docs/reference/cloud-ai-platform/1.21.0/V1.ExplainRequest)\n- [1.20.0](/php/docs/reference/cloud-ai-platform/1.20.0/V1.ExplainRequest)\n- [1.19.0](/php/docs/reference/cloud-ai-platform/1.19.0/V1.ExplainRequest)\n- [1.18.0](/php/docs/reference/cloud-ai-platform/1.18.0/V1.ExplainRequest)\n- [1.17.0](/php/docs/reference/cloud-ai-platform/1.17.0/V1.ExplainRequest)\n- [1.16.0](/php/docs/reference/cloud-ai-platform/1.16.0/V1.ExplainRequest)\n- [1.15.0](/php/docs/reference/cloud-ai-platform/1.15.0/V1.ExplainRequest)\n- [1.14.0](/php/docs/reference/cloud-ai-platform/1.14.0/V1.ExplainRequest)\n- [1.13.1](/php/docs/reference/cloud-ai-platform/1.13.1/V1.ExplainRequest)\n- [1.12.0](/php/docs/reference/cloud-ai-platform/1.12.0/V1.ExplainRequest)\n- [1.11.0](/php/docs/reference/cloud-ai-platform/1.11.0/V1.ExplainRequest)\n- [1.10.0](/php/docs/reference/cloud-ai-platform/1.10.0/V1.ExplainRequest)\n- [1.9.0](/php/docs/reference/cloud-ai-platform/1.9.0/V1.ExplainRequest)\n- [1.8.0](/php/docs/reference/cloud-ai-platform/1.8.0/V1.ExplainRequest)\n- [1.7.0](/php/docs/reference/cloud-ai-platform/1.7.0/V1.ExplainRequest)\n- [1.6.0](/php/docs/reference/cloud-ai-platform/1.6.0/V1.ExplainRequest)\n- [1.5.0](/php/docs/reference/cloud-ai-platform/1.5.0/V1.ExplainRequest)\n- [1.4.0](/php/docs/reference/cloud-ai-platform/1.4.0/V1.ExplainRequest)\n- [1.3.0](/php/docs/reference/cloud-ai-platform/1.3.0/V1.ExplainRequest)\n- [1.2.0](/php/docs/reference/cloud-ai-platform/1.2.0/V1.ExplainRequest)\n- [1.1.0](/php/docs/reference/cloud-ai-platform/1.1.0/V1.ExplainRequest)\n- [1.0.0](/php/docs/reference/cloud-ai-platform/1.0.0/V1.ExplainRequest)\n- [0.39.0](/php/docs/reference/cloud-ai-platform/0.39.0/V1.ExplainRequest)\n- [0.38.0](/php/docs/reference/cloud-ai-platform/0.38.0/V1.ExplainRequest)\n- [0.37.1](/php/docs/reference/cloud-ai-platform/0.37.1/V1.ExplainRequest)\n- [0.32.0](/php/docs/reference/cloud-ai-platform/0.32.0/V1.ExplainRequest)\n- [0.31.0](/php/docs/reference/cloud-ai-platform/0.31.0/V1.ExplainRequest)\n- [0.30.0](/php/docs/reference/cloud-ai-platform/0.30.0/V1.ExplainRequest)\n- [0.29.0](/php/docs/reference/cloud-ai-platform/0.29.0/V1.ExplainRequest)\n- [0.28.0](/php/docs/reference/cloud-ai-platform/0.28.0/V1.ExplainRequest)\n- [0.27.0](/php/docs/reference/cloud-ai-platform/0.27.0/V1.ExplainRequest)\n- [0.26.2](/php/docs/reference/cloud-ai-platform/0.26.2/V1.ExplainRequest)\n- [0.25.0](/php/docs/reference/cloud-ai-platform/0.25.0/V1.ExplainRequest)\n- [0.24.0](/php/docs/reference/cloud-ai-platform/0.24.0/V1.ExplainRequest)\n- [0.23.0](/php/docs/reference/cloud-ai-platform/0.23.0/V1.ExplainRequest)\n- [0.22.0](/php/docs/reference/cloud-ai-platform/0.22.0/V1.ExplainRequest)\n- [0.21.0](/php/docs/reference/cloud-ai-platform/0.21.0/V1.ExplainRequest)\n- [0.20.0](/php/docs/reference/cloud-ai-platform/0.20.0/V1.ExplainRequest)\n- [0.19.0](/php/docs/reference/cloud-ai-platform/0.19.0/V1.ExplainRequest)\n- [0.18.0](/php/docs/reference/cloud-ai-platform/0.18.0/V1.ExplainRequest)\n- [0.17.0](/php/docs/reference/cloud-ai-platform/0.17.0/V1.ExplainRequest)\n- [0.16.0](/php/docs/reference/cloud-ai-platform/0.16.0/V1.ExplainRequest)\n- [0.15.0](/php/docs/reference/cloud-ai-platform/0.15.0/V1.ExplainRequest)\n- [0.13.0](/php/docs/reference/cloud-ai-platform/0.13.0/V1.ExplainRequest)\n- [0.12.0](/php/docs/reference/cloud-ai-platform/0.12.0/V1.ExplainRequest)\n- [0.11.1](/php/docs/reference/cloud-ai-platform/0.11.1/V1.ExplainRequest)\n- [0.10.0](/php/docs/reference/cloud-ai-platform/0.10.0/V1.ExplainRequest) \nReference documentation and code samples for the Google Cloud Ai Platform V1 Client class ExplainRequest.\n\nRequest message for\n[PredictionService.Explain](/php/docs/reference/cloud-ai-platform/latest/V1.Client.PredictionServiceClient#_Google_Cloud_AIPlatform_V1_Client_PredictionServiceClient__explain__).\n\nGenerated from protobuf message `google.cloud.aiplatform.v1.ExplainRequest`\n\nNamespace\n---------\n\nGoogle \\\\ Cloud \\\\ AIPlatform \\\\ V1\n\nMethods\n-------\n\n### __construct\n\nConstructor.\n\n### getEndpoint\n\nRequired. The name of the Endpoint requested to serve the explanation.\n\nFormat:\n`projects/{project}/locations/{location}/endpoints/{endpoint}`\n\n### setEndpoint\n\nRequired. The name of the Endpoint requested to serve the explanation.\n\nFormat:\n`projects/{project}/locations/{location}/endpoints/{endpoint}`\n\n### getInstances\n\nRequired. The instances that are the input to the explanation call.\n\nA DeployedModel may have an upper limit on the number of instances it\nsupports per request, and when it is exceeded the explanation call errors\nin case of AutoML Models, or, in case of customer created Models, the\nbehaviour is as documented by that Model.\nThe schema of any single instance may be specified via Endpoint's\nDeployedModels' [Model's](/php/docs/reference/cloud-ai-platform/latest/V1.DeployedModel#_Google_Cloud_AIPlatform_V1_DeployedModel__getModel__)\n[PredictSchemata's](/php/docs/reference/cloud-ai-platform/latest/V1.Model#_Google_Cloud_AIPlatform_V1_Model__getPredictSchemata__)\n[instance_schema_uri](/php/docs/reference/cloud-ai-platform/latest/V1.PredictSchemata#_Google_Cloud_AIPlatform_V1_PredictSchemata__getInstanceSchemaUri__).\n\n### setInstances\n\nRequired. The instances that are the input to the explanation call.\n\nA DeployedModel may have an upper limit on the number of instances it\nsupports per request, and when it is exceeded the explanation call errors\nin case of AutoML Models, or, in case of customer created Models, the\nbehaviour is as documented by that Model.\nThe schema of any single instance may be specified via Endpoint's\nDeployedModels' [Model's](/php/docs/reference/cloud-ai-platform/latest/V1.DeployedModel#_Google_Cloud_AIPlatform_V1_DeployedModel__getModel__)\n[PredictSchemata's](/php/docs/reference/cloud-ai-platform/latest/V1.Model#_Google_Cloud_AIPlatform_V1_Model__getPredictSchemata__)\n[instance_schema_uri](/php/docs/reference/cloud-ai-platform/latest/V1.PredictSchemata#_Google_Cloud_AIPlatform_V1_PredictSchemata__getInstanceSchemaUri__).\n\n### getParameters\n\nThe parameters that govern the prediction. The schema of the parameters may\nbe specified via Endpoint's DeployedModels' [Model's](/php/docs/reference/cloud-ai-platform/latest/V1.DeployedModel#_Google_Cloud_AIPlatform_V1_DeployedModel__getModel__)\n[PredictSchemata's](/php/docs/reference/cloud-ai-platform/latest/V1.Model#_Google_Cloud_AIPlatform_V1_Model__getPredictSchemata__)\n[parameters_schema_uri](/php/docs/reference/cloud-ai-platform/latest/V1.PredictSchemata#_Google_Cloud_AIPlatform_V1_PredictSchemata__getParametersSchemaUri__).\n\n### hasParameters\n\n### clearParameters\n\n### setParameters\n\nThe parameters that govern the prediction. The schema of the parameters may\nbe specified via Endpoint's DeployedModels' [Model's](/php/docs/reference/cloud-ai-platform/latest/V1.DeployedModel#_Google_Cloud_AIPlatform_V1_DeployedModel__getModel__)\n[PredictSchemata's](/php/docs/reference/cloud-ai-platform/latest/V1.Model#_Google_Cloud_AIPlatform_V1_Model__getPredictSchemata__)\n[parameters_schema_uri](/php/docs/reference/cloud-ai-platform/latest/V1.PredictSchemata#_Google_Cloud_AIPlatform_V1_PredictSchemata__getParametersSchemaUri__).\n\n### getExplanationSpecOverride\n\nIf specified, overrides the\n[explanation_spec](/php/docs/reference/cloud-ai-platform/latest/V1.DeployedModel#_Google_Cloud_AIPlatform_V1_DeployedModel__getExplanationSpec__)\nof the DeployedModel. Can be used for explaining prediction results with\ndifferent configurations, such as:\n\n- Explaining top-5 predictions results as opposed to top-1;\n- Increasing path count or step count of the attribution methods to reduce approximate errors;\n- Using different baselines for explaining the prediction results.\n\n### hasExplanationSpecOverride\n\n### clearExplanationSpecOverride\n\n### setExplanationSpecOverride\n\nIf specified, overrides the\n[explanation_spec](/php/docs/reference/cloud-ai-platform/latest/V1.DeployedModel#_Google_Cloud_AIPlatform_V1_DeployedModel__getExplanationSpec__)\nof the DeployedModel. Can be used for explaining prediction results with\ndifferent configurations, such as:\n\n- Explaining top-5 predictions results as opposed to top-1;\n- Increasing path count or step count of the attribution methods to reduce approximate errors;\n- Using different baselines for explaining the prediction results.\n\n### getDeployedModelId\n\nIf specified, this ExplainRequest will be served by the chosen\nDeployedModel, overriding\n[Endpoint.traffic_split](/php/docs/reference/cloud-ai-platform/latest/V1.Endpoint#_Google_Cloud_AIPlatform_V1_Endpoint__getTrafficSplit__).\n\n### setDeployedModelId\n\nIf specified, this ExplainRequest will be served by the chosen\nDeployedModel, overriding\n[Endpoint.traffic_split](/php/docs/reference/cloud-ai-platform/latest/V1.Endpoint#_Google_Cloud_AIPlatform_V1_Endpoint__getTrafficSplit__).\n\n### static::build"]]
