Evaluate a trained model | Elasticsearch API documentation (v9)

Path parameters

model_idstring Required
The unique identifier of the trained model.

Query parameters

timeoutstring
Controls the amount of time to wait for inference results.
Values are -1 or 0.

application/json

BodyRequired

docsarray[object] Required
An array of objects to pass to the model for inference. The objects should contain a fields matching your configured trained model input. Typically, for NLP models, the field name is text_field. Currently, for NLP models, only a single value is allowed.
Hide docs attribute Show docs attribute object
- *object Additional properties
inference_configobject
Hide inference_config attributes Show inference_config attributes object
- regressionobject
  Hide regression attributes Show regression attributes object
  results_fieldstring
  Path to field or array of paths. Some API's support wildcards in the path to select multiple fields.
  num_top_feature_importance_valuesnumber
  Specifies the maximum number of feature importance values per document.
- classificationobject
  Hide classification attributes Show classification attributes object
  num_top_classesnumber
  Specifies the number of top class predictions to return. Defaults to 0.
  num_top_feature_importance_valuesnumber
  Specifies the maximum number of feature importance values per document.
  prediction_field_typestring
  Specifies the type of the predicted field to write. Acceptable values are: string, number, boolean. When boolean is provided 1.0 is transformed to true and 0.0 to false.
  results_fieldstring
  The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
  top_classes_results_fieldstring
  Specifies the field to which the top classes are written. Defaults to top_classes.
- text_classificationobject
  Hide text_classification attributes Show text_classification attributes object
  num_top_classesnumber
  Specifies the number of top class predictions to return. Defaults to 0.
  tokenizationobject
  Hide tokenization attributes Show tokenization attributes object
  truncatestring
  Values are first, second, or none.
  spannumber
  Span options to apply
  results_fieldstring
  The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
  classification_labelsarray[string]
  Classification labels to apply other than the stored labels. Must have the same deminsions as the default configured labels
- zero_shot_classificationobject
  Hide zero_shot_classification attributes Show zero_shot_classification attributes object
  tokenizationobject
  Hide tokenization attributes Show tokenization attributes object
  truncatestring
  Values are first, second, or none.
  spannumber
  Span options to apply
  results_fieldstring
  The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
  multi_labelboolean
  Update the configured multi label option. Indicates if more than one true label exists. Defaults to the configured value.
  labelsarray[string] Required
  The labels to predict.
- fill_maskobject
  Hide fill_mask attributes Show fill_mask attributes object
  num_top_classesnumber
  Specifies the number of top class predictions to return. Defaults to 0.
  tokenizationobject
  Hide tokenization attributes Show tokenization attributes object
  truncatestring
  Values are first, second, or none.
  spannumber
  Span options to apply
  results_fieldstring
  The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
- nerobject
  Hide ner attributes Show ner attributes object
  tokenizationobject
  Hide tokenization attributes Show tokenization attributes object
  truncatestring
  Values are first, second, or none.
  spannumber
  Span options to apply
  results_fieldstring
  The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
- pass_throughobject
  Hide pass_through attributes Show pass_through attributes object
  tokenizationobject
  Hide tokenization attributes Show tokenization attributes object
  truncatestring
  Values are first, second, or none.
  spannumber
  Span options to apply
  results_fieldstring
  The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
- text_embeddingobject
  Hide text_embedding attributes Show text_embedding attributes object
  tokenizationobject
  Hide tokenization attributes Show tokenization attributes object
  truncatestring
  Values are first, second, or none.
  spannumber
  Span options to apply
  results_fieldstring
  The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
- text_expansionobject
  Hide text_expansion attributes Show text_expansion attributes object
  tokenizationobject
  Hide tokenization attributes Show tokenization attributes object
  truncatestring
  Values are first, second, or none.
  spannumber
  Span options to apply
  results_fieldstring
  The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
- question_answeringobject
  Hide question_answering attributes Show question_answering attributes object
  questionstring Required
  The question to answer given the inference context
  num_top_classesnumber
  Specifies the number of top class predictions to return. Defaults to 0.
  tokenizationobject
  Hide tokenization attributes Show tokenization attributes object
  truncatestring
  Values are first, second, or none.
  spannumber
  Span options to apply
  results_fieldstring
  The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
  max_answer_lengthnumber
  The maximum answer length to consider for extraction

Responses

200 application/json
Hide response attribute Show response attribute object
- inference_resultsarray[object] Required
  Hide inference_results attributes Show inference_results attributes object
  entitiesarray[object]
  If the model is trained for named entity recognition (NER) tasks, the response contains the recognized entities.
  Hide entities attributes Show entities attributes object
  class_namestring Required
  class_probabilitynumber Required
  entitystring Required
  start_posnumber Required
  end_posnumber Required
  is_truncatedboolean
  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_valuenumber | string | boolean | null | array[number | string | boolean | null] | array[number | string | boolean | null | array]
  If the model is trained for a text classification or zero shot classification task, the response is the predicted class. For named entity recognition (NER) tasks, it contains the annotated text output. For fill mask tasks, it contains the top prediction for replacing the mask token. For text embedding tasks, it contains the raw numerical text embedding values. For regression models, its a numerical value For classification models, it may be an integer, double, boolean or string depending on prediction type
  One of:
  ScalarValuenumber ScalarValuenumber ScalarValuestring ScalarValueboolean ScalarValuestring | null PredictedValuearray[number | string | boolean | null]array-2array[number | string | boolean | null | array]
  A scalar value.
  A scalar value.
  predicted_value_sequencestring
  For fill mask tasks, the response contains the input text sequence with the mask token replaced by the predicted value. Additionally
  prediction_probabilitynumber
  Specifies a probability for the predicted value.
  prediction_scorenumber
  Specifies a confidence score for the predicted value.
  top_classesarray[object]
  For fill mask, text classification, and zero shot classification tasks, the response contains a list of top class entries.
  Hide top_classes attributes Show top_classes attributes object
  class_namestring Required
  class_probabilitynumber Required
  class_scorenumber Required
  warningstring
  If the request failed, the response contains the reason for the failure.
  feature_importancearray[object]
  The feature importance for the inference results. Relevant only for classification or regression models
  Hide feature_importance attributes Show feature_importance attributes object
  feature_namestring Required
  importancenumber
  classesarray[object]

POST /_ml/trained_models/{model_id}/_infer

curl \
 --request POST 'http://api.example.com/_ml/trained_models/{model_id}/_infer' \
 --header "Authorization: $API_KEY" \
 --header "Content-Type: application/json" \
 --data '{"docs":[{"additionalProperty1":{},"additionalProperty2":{}}],"inference_config":{"regression":{"results_field":"string","num_top_feature_importance_values":42.0},"classification":{"num_top_classes":42.0,"num_top_feature_importance_values":42.0,"prediction_field_type":"string","results_field":"string","top_classes_results_field":"string"},"text_classification":{"num_top_classes":42.0,"tokenization":{"truncate":"first","span":42.0},"results_field":"string","classification_labels":["string"]},"zero_shot_classification":{"tokenization":{"truncate":"first","span":42.0},"results_field":"string","multi_label":true,"labels":["string"]},"fill_mask":{"num_top_classes":42.0,"tokenization":{"truncate":"first","span":42.0},"results_field":"string"},"ner":{"tokenization":{"truncate":"first","span":42.0},"results_field":"string"},"pass_through":{"tokenization":{"truncate":"first","span":42.0},"results_field":"string"},"text_embedding":{"tokenization":{"truncate":"first","span":42.0},"results_field":"string"},"text_expansion":{"tokenization":{"truncate":"first","span":42.0},"results_field":"string"},"question_answering":{"question":"string","num_top_classes":42.0,"tokenization":{"truncate":"first","span":42.0},"results_field":"string","max_answer_length":42.0}}}'

Path parameters

Query parameters

BodyRequired

Responses

predicted_valuenumber | string | boolean | null | array[number | string | boolean | null] | array[number | string | boolean | null | array]