1.9 KiB
1.9 KiB
MlInferenceResponseResult [interface-MlInferenceResponseResult]
| Name | Type | Description |
|---|---|---|
entities |
MlTrainedModelEntities[] | If the model is trained for named entity recognition (NER) tasks, the response contains the recognized entities. |
feature_importance |
MlTrainedModelInferenceFeatureImportance[] | The feature importance for the inference results. Relevant only for classification or regression models |
is_truncated |
boolean | Indicates whether the input text was truncated to meet the model's maximum sequence length limit. This property is present only when it is true. |
predicted_value_sequence |
string | For fill mask tasks, the response contains the input text sequence with the mask token replaced by the predicted value. Additionally |
predicted_value |
MlPredictedValue | MlPredictedValue[] |
prediction_probability |
double | Specifies a probability for the predicted value. |
prediction_score |
double | Specifies a confidence score for the predicted value. |
top_classes |
MlTopClassEntry[] | For fill mask, text classification, and zero shot classification tasks, the response contains a list of top class entries. |
warning |
string | If the request failed, the response contains the reason for the failure. |