public sealed class ExplanationMetadata : IMessage<ExplanationMetadata>, IEquatable<ExplanationMetadata>, IDeepCloneable<ExplanationMetadata>, IBufferMessage, IMessage
Reference documentation and code samples for the Vertex AI v1beta1 API class ExplanationMetadata.
Metadata describing the Model's input and output for explanation.
public string FeatureAttributionsSchemaUri { get; set; }
Points to a YAML file stored on Google Cloud Storage describing the format
of the [feature
attributions][google.cloud.aiplatform.v1beta1.Attribution.feature_attributions].
The schema is defined as an OpenAPI 3.0.2 Schema
Object.
AutoML tabular Models always have this field populated by Vertex AI.
Note: The URI given on output may be different, including the URI scheme,
than the one given on input. The output URI will point to a location where
the user only has a read access.
public MapField<string, ExplanationMetadata.Types.InputMetadata> Inputs { get; }
Required. Map from feature names to feature input metadata. Keys are the
name of the features. Values are the specification of the feature.
An empty InputMetadata is valid. It describes a text feature which has the
name specified as the key in
[ExplanationMetadata.inputs][google.cloud.aiplatform.v1beta1.ExplanationMetadata.inputs].
The baseline of the empty feature is chosen by Vertex AI.
For Vertex AI-provided Tensorflow images, the key can be any friendly
name of the feature. Once specified,
[featureAttributions][google.cloud.aiplatform.v1beta1.Attribution.feature_attributions]
are keyed by this key (if not grouped with another feature).
For custom images, the key must match with the key in
[instance][google.cloud.aiplatform.v1beta1.ExplainRequest.instances].
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-28 UTC."],[[["\u003cp\u003e\u003ccode\u003eExplanationMetadata\u003c/code\u003e is a class within the Vertex AI v1beta1 API that describes the input and output metadata for model explanations.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eExplanationMetadata\u003c/code\u003e class implements interfaces such as \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e, and inherits from the base \u003ccode\u003eobject\u003c/code\u003e class.\u003c/p\u003e\n"],["\u003cp\u003eKey properties of this class include \u003ccode\u003eInputs\u003c/code\u003e and \u003ccode\u003eOutputs\u003c/code\u003e, which are maps detailing the input and output feature metadata respectively, as well as \u003ccode\u003eFeatureAttributionsSchemaUri\u003c/code\u003e which defines the format for feature attributions, and \u003ccode\u003eLatentSpaceSource\u003c/code\u003e for defining the source of embeddings for example based explanations.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eInputs\u003c/code\u003e property is a required map where keys represent feature names, and values are of type \u003ccode\u003eInputMetadata\u003c/code\u003e, specifying the features, while \u003ccode\u003eOutputs\u003c/code\u003e is a required map where keys represent the output names, and the values are of type \u003ccode\u003eOutputMetadata\u003c/code\u003e that defines the output field's metadata.\u003c/p\u003e\n"],["\u003cp\u003eThere are two constructors, the first being a parameterless constructor, and the second taking in an \u003ccode\u003eExplanationMetadata\u003c/code\u003e object.\u003c/p\u003e\n"]]],[],null,["# Vertex AI v1beta1 API - Class ExplanationMetadata (1.0.0-beta47)\n\nVersion latestkeyboard_arrow_down\n\n- [1.0.0-beta47 (latest)](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.ExplanationMetadata)\n- [1.0.0-beta46](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/1.0.0-beta46/Google.Cloud.AIPlatform.V1Beta1.ExplanationMetadata) \n\n public sealed class ExplanationMetadata : IMessage\u003cExplanationMetadata\u003e, IEquatable\u003cExplanationMetadata\u003e, IDeepCloneable\u003cExplanationMetadata\u003e, IBufferMessage, IMessage\n\nReference documentation and code samples for the Vertex AI v1beta1 API class ExplanationMetadata.\n\nMetadata describing the Model's input and output for explanation. \n\nInheritance\n-----------\n\n[object](https://learn.microsoft.com/dotnet/api/system.object) \\\u003e ExplanationMetadata \n\nImplements\n----------\n\n[IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage-1.html)[ExplanationMetadata](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.ExplanationMetadata), [IEquatable](https://learn.microsoft.com/dotnet/api/system.iequatable-1)[ExplanationMetadata](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.ExplanationMetadata), [IDeepCloneable](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IDeepCloneable-1.html)[ExplanationMetadata](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.ExplanationMetadata), [IBufferMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IBufferMessage.html), [IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage.html) \n\nInherited Members\n-----------------\n\n[object.GetHashCode()](https://learn.microsoft.com/dotnet/api/system.object.gethashcode) \n[object.GetType()](https://learn.microsoft.com/dotnet/api/system.object.gettype) \n[object.ToString()](https://learn.microsoft.com/dotnet/api/system.object.tostring)\n\nNamespace\n---------\n\n[Google.Cloud.AIPlatform.V1Beta1](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1)\n\nAssembly\n--------\n\nGoogle.Cloud.AIPlatform.V1Beta1.dll\n\nConstructors\n------------\n\n### ExplanationMetadata()\n\n public ExplanationMetadata()\n\n### ExplanationMetadata(ExplanationMetadata)\n\n public ExplanationMetadata(ExplanationMetadata other)\n\nProperties\n----------\n\n### FeatureAttributionsSchemaUri\n\n public string FeatureAttributionsSchemaUri { get; set; }\n\nPoints to a YAML file stored on Google Cloud Storage describing the format\nof the \\[feature\nattributions\\]\\[google.cloud.aiplatform.v1beta1.Attribution.feature_attributions\\].\nThe schema is defined as an OpenAPI 3.0.2 [Schema\nObject](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject).\nAutoML tabular Models always have this field populated by Vertex AI.\nNote: The URI given on output may be different, including the URI scheme,\nthan the one given on input. The output URI will point to a location where\nthe user only has a read access.\n\n### Inputs\n\n public MapField\u003cstring, ExplanationMetadata.Types.InputMetadata\u003e Inputs { get; }\n\nRequired. Map from feature names to feature input metadata. Keys are the\nname of the features. Values are the specification of the feature.\n\nAn empty InputMetadata is valid. It describes a text feature which has the\nname specified as the key in\n\\[ExplanationMetadata.inputs\\]\\[google.cloud.aiplatform.v1beta1.ExplanationMetadata.inputs\\].\nThe baseline of the empty feature is chosen by Vertex AI.\n\nFor Vertex AI-provided Tensorflow images, the key can be any friendly\nname of the feature. Once specified,\n\\[featureAttributions\\]\\[google.cloud.aiplatform.v1beta1.Attribution.feature_attributions\\]\nare keyed by this key (if not grouped with another feature).\n\nFor custom images, the key must match with the key in\n\\[instance\\]\\[google.cloud.aiplatform.v1beta1.ExplainRequest.instances\\].\n\n### LatentSpaceSource\n\n public string LatentSpaceSource { get; set; }\n\nName of the source to generate embeddings for example based explanations.\n\n### Outputs\n\n public MapField\u003cstring, ExplanationMetadata.Types.OutputMetadata\u003e Outputs { get; }\n\nRequired. Map from output names to output metadata.\n\nFor Vertex AI-provided Tensorflow images, keys can be any user defined\nstring that consists of any UTF-8 characters.\n\nFor custom images, keys are the name of the output field in the prediction\nto be explained.\n\nCurrently only one key is allowed."]]
