Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see Model versions and lifecycle.
Specify a field name in the prediction to look for the display name.
Use this if the prediction contains the display names for the outputs.
The display names in the prediction must have the same shape of the
outputs, so that it can be located by
Attribution.output_index
for a specific output.
Specify a field name in the prediction to look for the display name.
Use this if the prediction contains the display names for the outputs.
The display names in the prediction must have the same shape of the
outputs, so that it can be located by
Attribution.output_index
for a specific output.
Static mapping between the index and display name.
Use this if the outputs are a deterministic n-dimensional array, e.g. a
list of scores of all the classes in a pre-defined order for a
multi-classification Model. It's not feasible if the outputs are
non-deterministic, e.g. the Model produces top-k classes or sort the
outputs by their values.
The shape of the value must be an n-dimensional array of strings. The
number of dimensions must match that of the outputs to be explained.
The
Attribution.output_display_name
is populated by locating in the mapping with
Attribution.output_index.
Static mapping between the index and display name.
Use this if the outputs are a deterministic n-dimensional array, e.g. a
list of scores of all the classes in a pre-defined order for a
multi-classification Model. It's not feasible if the outputs are
non-deterministic, e.g. the Model produces top-k classes or sort the
outputs by their values.
The shape of the value must be an n-dimensional array of strings. The
number of dimensions must match that of the outputs to be explained.
The
Attribution.output_display_name
is populated by locating in the mapping with
Attribution.output_index.
Specify a field name in the prediction to look for the display name.
Use this if the prediction contains the display names for the outputs.
The display names in the prediction must have the same shape of the
outputs, so that it can be located by
Attribution.output_index
for a specific output.
Static mapping between the index and display name.
Use this if the outputs are a deterministic n-dimensional array, e.g. a
list of scores of all the classes in a pre-defined order for a
multi-classification Model. It's not feasible if the outputs are
non-deterministic, e.g. the Model produces top-k classes or sort the
outputs by their values.
The shape of the value must be an n-dimensional array of strings. The
number of dimensions must match that of the outputs to be explained.
The
Attribution.output_display_name
is populated by locating in the mapping with
Attribution.output_index.
[[["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 2025-09-03 UTC."],[],[],null,["# Interface ExplanationMetadata.OutputMetadataOrBuilder (1.32.0)\n\n public static interface ExplanationMetadata.OutputMetadataOrBuilder extends MessageOrBuilder\n\nImplements\n----------\n\n[MessageOrBuilder](https://cloud.google.com/java/docs/reference/protobuf/latest/com.google.protobuf.MessageOrBuilder.html)\n\nMethods\n-------\n\n### getDisplayNameMappingCase()\n\n public abstract ExplanationMetadata.OutputMetadata.DisplayNameMappingCase getDisplayNameMappingCase()\n\n### getDisplayNameMappingKey()\n\n public abstract String getDisplayNameMappingKey()\n\nSpecify a field name in the prediction to look for the display name.\n\nUse this if the prediction contains the display names for the outputs.\n\nThe display names in the prediction must have the same shape of the\noutputs, so that it can be located by\nAttribution.output_index\nfor a specific output.\n\n`string display_name_mapping_key = 2;`\n\n### getDisplayNameMappingKeyBytes()\n\n public abstract ByteString getDisplayNameMappingKeyBytes()\n\nSpecify a field name in the prediction to look for the display name.\n\nUse this if the prediction contains the display names for the outputs.\n\nThe display names in the prediction must have the same shape of the\noutputs, so that it can be located by\nAttribution.output_index\nfor a specific output.\n\n`string display_name_mapping_key = 2;`\n\n### getIndexDisplayNameMapping()\n\n public abstract Value getIndexDisplayNameMapping()\n\nStatic mapping between the index and display name.\n\nUse this if the outputs are a deterministic n-dimensional array, e.g. a\nlist of scores of all the classes in a pre-defined order for a\nmulti-classification Model. It's not feasible if the outputs are\nnon-deterministic, e.g. the Model produces top-k classes or sort the\noutputs by their values.\n\nThe shape of the value must be an n-dimensional array of strings. The\nnumber of dimensions must match that of the outputs to be explained.\nThe\nAttribution.output_display_name\nis populated by locating in the mapping with\nAttribution.output_index.\n\n`.google.protobuf.Value index_display_name_mapping = 1;`\n\n### getIndexDisplayNameMappingOrBuilder()\n\n public abstract ValueOrBuilder getIndexDisplayNameMappingOrBuilder()\n\nStatic mapping between the index and display name.\n\nUse this if the outputs are a deterministic n-dimensional array, e.g. a\nlist of scores of all the classes in a pre-defined order for a\nmulti-classification Model. It's not feasible if the outputs are\nnon-deterministic, e.g. the Model produces top-k classes or sort the\noutputs by their values.\n\nThe shape of the value must be an n-dimensional array of strings. The\nnumber of dimensions must match that of the outputs to be explained.\nThe\nAttribution.output_display_name\nis populated by locating in the mapping with\nAttribution.output_index.\n\n`.google.protobuf.Value index_display_name_mapping = 1;`\n\n### getOutputTensorName()\n\n public abstract String getOutputTensorName()\n\nName of the output tensor. Required and is only applicable to Vertex\nAI provided images for Tensorflow.\n\n`string output_tensor_name = 3;`\n\n### getOutputTensorNameBytes()\n\n public abstract ByteString getOutputTensorNameBytes()\n\nName of the output tensor. Required and is only applicable to Vertex\nAI provided images for Tensorflow.\n\n`string output_tensor_name = 3;`\n\n### hasDisplayNameMappingKey()\n\n public abstract boolean hasDisplayNameMappingKey()\n\nSpecify a field name in the prediction to look for the display name.\n\nUse this if the prediction contains the display names for the outputs.\n\nThe display names in the prediction must have the same shape of the\noutputs, so that it can be located by\nAttribution.output_index\nfor a specific output.\n\n`string display_name_mapping_key = 2;`\n\n### hasIndexDisplayNameMapping()\n\n public abstract boolean hasIndexDisplayNameMapping()\n\nStatic mapping between the index and display name.\n\nUse this if the outputs are a deterministic n-dimensional array, e.g. a\nlist of scores of all the classes in a pre-defined order for a\nmulti-classification Model. It's not feasible if the outputs are\nnon-deterministic, e.g. the Model produces top-k classes or sort the\noutputs by their values.\n\nThe shape of the value must be an n-dimensional array of strings. The\nnumber of dimensions must match that of the outputs to be explained.\nThe\nAttribution.output_display_name\nis populated by locating in the mapping with\nAttribution.output_index.\n\n`.google.protobuf.Value index_display_name_mapping = 1;`"]]