Create a trained model

PUT /_ml/trained_models/{model_id}

Enable you to supply a trained model that is not created by data frame analytics.

Path parameters

  • model_id string Required

    The unique identifier of the trained model.

Query parameters

  • defer_definition_decompression boolean

    If set to true and a compressed_definition is provided, the request defers definition decompression and skips relevant validations.

  • wait_for_completion boolean

    Whether to wait for all child operations (e.g. model download) to complete.

application/json

Body Required

  • compressed_definition string

    The compressed (GZipped and Base64 encoded) inference definition of the model. If compressed_definition is specified, then definition cannot be specified.

  • definition object
    Hide definition attributes Show definition attributes object
  • description string

    A human-readable description of the inference trained model.

  • inference_config object

    Inference configuration provided when storing the model config

    Hide inference_config attributes Show inference_config attributes object
    • regression object
      Hide regression attributes Show regression attributes object
    • classification object
      Hide classification attributes Show classification attributes object
      • num_top_classes number

        Specifies the number of top class predictions to return. Defaults to 0.

      • num_top_feature_importance_values number

        Specifies the maximum number of feature importance values per document.

      • prediction_field_type string

        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_field string

        The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

      • top_classes_results_field string

        Specifies the field to which the top classes are written. Defaults to top_classes.

    • text_classification object
      Hide text_classification attributes Show text_classification attributes object
      • num_top_classes number

        Specifies the number of top class predictions to return. Defaults to 0.

      • tokenization object

        Tokenization options stored in inference configuration

        Hide tokenization attributes Show tokenization attributes object
        • bert object
          Hide bert attributes Show bert attributes object
        • mpnet object
          Hide mpnet attributes Show mpnet attributes object
        • roberta object
          Hide roberta attributes Show roberta attributes object
      • results_field string

        The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

      • classification_labels array[string]

        Classification labels to apply other than the stored labels. Must have the same deminsions as the default configured labels

    • zero_shot_classification object
      Hide zero_shot_classification attributes Show zero_shot_classification attributes object
      • tokenization object

        Tokenization options stored in inference configuration

        Hide tokenization attributes Show tokenization attributes object
        • bert object
          Hide bert attributes Show bert attributes object
        • mpnet object
          Hide mpnet attributes Show mpnet attributes object
        • roberta object
          Hide roberta attributes Show roberta attributes object
      • hypothesis_template string

        Hypothesis template used when tokenizing labels for prediction

      • classification_labels array[string] Required

        The zero shot classification labels indicating entailment, neutral, and contradiction Must contain exactly and only entailment, neutral, and contradiction

      • results_field string

        The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

      • multi_label boolean

        Indicates if more than one true label exists.

      • labels array[string]

        The labels to predict.

    • fill_mask object
      Hide fill_mask attributes Show fill_mask attributes object
      • mask_token string

        The string/token which will be removed from incoming documents and replaced with the inference prediction(s). In a response, this field contains the mask token for the specified model/tokenizer. Each model and tokenizer has a predefined mask token which cannot be changed. Thus, it is recommended not to set this value in requests. However, if this field is present in a request, its value must match the predefined value for that model/tokenizer, otherwise the request will fail.

      • num_top_classes number

        Specifies the number of top class predictions to return. Defaults to 0.

      • tokenization object

        Tokenization options stored in inference configuration

        Hide tokenization attributes Show tokenization attributes object
        • bert object
          Hide bert attributes Show bert attributes object
        • mpnet object
          Hide mpnet attributes Show mpnet attributes object
        • roberta object
          Hide roberta attributes Show roberta attributes object
      • results_field string

        The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

    • ner object
      Hide ner attributes Show ner attributes object
      • tokenization object

        Tokenization options stored in inference configuration

        Hide tokenization attributes Show tokenization attributes object
        • bert object
          Hide bert attributes Show bert attributes object
        • mpnet object
          Hide mpnet attributes Show mpnet attributes object
        • roberta object
          Hide roberta attributes Show roberta attributes object
      • results_field string

        The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

      • classification_labels array[string]

        The token classification labels. Must be IOB formatted tags

      • vocabulary object
        Hide vocabulary attribute Show vocabulary attribute object
    • pass_through object
      Hide pass_through attributes Show pass_through attributes object
      • tokenization object

        Tokenization options stored in inference configuration

        Hide tokenization attributes Show tokenization attributes object
        • bert object
          Hide bert attributes Show bert attributes object
        • mpnet object
          Hide mpnet attributes Show mpnet attributes object
        • roberta object
          Hide roberta attributes Show roberta attributes object
      • results_field string

        The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

      • vocabulary object
        Hide vocabulary attribute Show vocabulary attribute object
    • text_embedding object
      Hide text_embedding attributes Show text_embedding attributes object
      • embedding_size number

        The number of dimensions in the embedding output

      • tokenization object

        Tokenization options stored in inference configuration

        Hide tokenization attributes Show tokenization attributes object
        • bert object
          Hide bert attributes Show bert attributes object
        • mpnet object
          Hide mpnet attributes Show mpnet attributes object
        • roberta object
          Hide roberta attributes Show roberta attributes object
      • results_field string

        The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

    • text_expansion object
      Hide text_expansion attributes Show text_expansion attributes object
      • tokenization object

        Tokenization options stored in inference configuration

        Hide tokenization attributes Show tokenization attributes object
        • bert object
          Hide bert attributes Show bert attributes object
        • mpnet object
          Hide mpnet attributes Show mpnet attributes object
        • roberta object
          Hide roberta attributes Show roberta attributes object
      • results_field string

        The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

    • question_answering object
      Hide question_answering attributes Show question_answering attributes object
      • num_top_classes number

        Specifies the number of top class predictions to return. Defaults to 0.

      • tokenization object

        Tokenization options stored in inference configuration

        Hide tokenization attributes Show tokenization attributes object
        • bert object
          Hide bert attributes Show bert attributes object
        • mpnet object
          Hide mpnet attributes Show mpnet attributes object
        • roberta object
          Hide roberta attributes Show roberta attributes object
      • results_field string

        The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

      • max_answer_length number

        The maximum answer length to consider

  • input object
    Hide input attribute Show input attribute object
  • metadata object

    An object map that contains metadata about the model.

  • model_type string

    Values are tree_ensemble, lang_ident, or pytorch.

  • model_size_bytes number

    The estimated memory usage in bytes to keep the trained model in memory. This property is supported only if defer_definition_decompression is true or the model definition is not supplied.

  • platform_architecture string

    The platform architecture (if applicable) of the trained mode. If the model only works on one platform, because it is heavily optimized for a particular processor architecture and OS combination, then this field specifies which. The format of the string must match the platform identifiers used by Elasticsearch, so one of, linux-x86_64, linux-aarch64, darwin-x86_64, darwin-aarch64, or windows-x86_64. For portable models (those that work independent of processor architecture or OS features), leave this field unset.

  • tags array[string]

    An array of tags to organize the model.

  • prefix_strings object
    Hide prefix_strings attributes Show prefix_strings attributes object
    • ingest string

      String prepended to input at ingest

    • search string

      String prepended to input at search

Responses

  • 200 application/json
    Hide response attributes Show response attributes object
    • model_id string Required
    • model_type string

      Values are tree_ensemble, lang_ident, or pytorch.

    • tags array[string] Required

      A comma delimited string of tags. A trained model can have many tags, or none.

    • version string
    • compressed_definition string
    • created_by string

      Information on the creator of the trained model.

    • create_time string | number

      A date and time, either as a string whose format can depend on the context (defaulting to ISO 8601), or a number of milliseconds since the Epoch. Elasticsearch accepts both as input, but will generally output a string representation.

      One of:
      _types:DateTime string _types:UnitMillis number

      Time unit for milliseconds

    • default_field_map object

      Any field map described in the inference configuration takes precedence.

      Hide default_field_map attributes Show default_field_map attributes object
    • description string

      The free-text description of the trained model.

    • estimated_heap_memory_usage_bytes number

      The estimated heap usage in bytes to keep the trained model in memory.

    • estimated_operations number

      The estimated number of operations to use the trained model.

    • fully_defined boolean

      True if the full model definition is present.

    • inference_config object

      Inference configuration provided when storing the model config

      Hide inference_config attributes Show inference_config attributes object
      • regression object
        Hide regression attributes Show regression attributes object
      • classification object
        Hide classification attributes Show classification attributes object
        • num_top_classes number

          Specifies the number of top class predictions to return. Defaults to 0.

        • num_top_feature_importance_values number

          Specifies the maximum number of feature importance values per document.

        • prediction_field_type string

          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_field string

          The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

        • top_classes_results_field string

          Specifies the field to which the top classes are written. Defaults to top_classes.

      • text_classification object
        Hide text_classification attributes Show text_classification attributes object
        • num_top_classes number

          Specifies the number of top class predictions to return. Defaults to 0.

        • tokenization object

          Tokenization options stored in inference configuration

          Hide tokenization attributes Show tokenization attributes object
          • bert object
            Hide bert attributes Show bert attributes object
          • mpnet object
            Hide mpnet attributes Show mpnet attributes object
          • roberta object
            Hide roberta attributes Show roberta attributes object
        • results_field string

          The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

        • classification_labels array[string]

          Classification labels to apply other than the stored labels. Must have the same deminsions as the default configured labels

      • zero_shot_classification object
        Hide zero_shot_classification attributes Show zero_shot_classification attributes object
        • tokenization object

          Tokenization options stored in inference configuration

          Hide tokenization attributes Show tokenization attributes object
          • bert object
            Hide bert attributes Show bert attributes object
          • mpnet object
            Hide mpnet attributes Show mpnet attributes object
          • roberta object
            Hide roberta attributes Show roberta attributes object
        • hypothesis_template string

          Hypothesis template used when tokenizing labels for prediction

        • classification_labels array[string] Required

          The zero shot classification labels indicating entailment, neutral, and contradiction Must contain exactly and only entailment, neutral, and contradiction

        • results_field string

          The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

        • multi_label boolean

          Indicates if more than one true label exists.

        • labels array[string]

          The labels to predict.

      • fill_mask object
        Hide fill_mask attributes Show fill_mask attributes object
        • mask_token string

          The string/token which will be removed from incoming documents and replaced with the inference prediction(s). In a response, this field contains the mask token for the specified model/tokenizer. Each model and tokenizer has a predefined mask token which cannot be changed. Thus, it is recommended not to set this value in requests. However, if this field is present in a request, its value must match the predefined value for that model/tokenizer, otherwise the request will fail.

        • num_top_classes number

          Specifies the number of top class predictions to return. Defaults to 0.

        • tokenization object

          Tokenization options stored in inference configuration

          Hide tokenization attributes Show tokenization attributes object
          • bert object
            Hide bert attributes Show bert attributes object
          • mpnet object
            Hide mpnet attributes Show mpnet attributes object
          • roberta object
            Hide roberta attributes Show roberta attributes object
        • results_field string

          The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

      • ner object
        Hide ner attributes Show ner attributes object
        • tokenization object

          Tokenization options stored in inference configuration

          Hide tokenization attributes Show tokenization attributes object
          • bert object
            Hide bert attributes Show bert attributes object
          • mpnet object
            Hide mpnet attributes Show mpnet attributes object
          • roberta object
            Hide roberta attributes Show roberta attributes object
        • results_field string

          The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

        • classification_labels array[string]

          The token classification labels. Must be IOB formatted tags

        • vocabulary object
          Hide vocabulary attribute Show vocabulary attribute object
      • pass_through object
        Hide pass_through attributes Show pass_through attributes object
        • tokenization object

          Tokenization options stored in inference configuration

          Hide tokenization attributes Show tokenization attributes object
          • bert object
            Hide bert attributes Show bert attributes object
          • mpnet object
            Hide mpnet attributes Show mpnet attributes object
          • roberta object
            Hide roberta attributes Show roberta attributes object
        • results_field string

          The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

        • vocabulary object
          Hide vocabulary attribute Show vocabulary attribute object
      • text_embedding object
        Hide text_embedding attributes Show text_embedding attributes object
        • embedding_size number

          The number of dimensions in the embedding output

        • tokenization object

          Tokenization options stored in inference configuration

          Hide tokenization attributes Show tokenization attributes object
          • bert object
            Hide bert attributes Show bert attributes object
          • mpnet object
            Hide mpnet attributes Show mpnet attributes object
          • roberta object
            Hide roberta attributes Show roberta attributes object
        • results_field string

          The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

      • text_expansion object
        Hide text_expansion attributes Show text_expansion attributes object
        • tokenization object

          Tokenization options stored in inference configuration

          Hide tokenization attributes Show tokenization attributes object
          • bert object
            Hide bert attributes Show bert attributes object
          • mpnet object
            Hide mpnet attributes Show mpnet attributes object
          • roberta object
            Hide roberta attributes Show roberta attributes object
        • results_field string

          The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

      • question_answering object
        Hide question_answering attributes Show question_answering attributes object
        • num_top_classes number

          Specifies the number of top class predictions to return. Defaults to 0.

        • tokenization object

          Tokenization options stored in inference configuration

          Hide tokenization attributes Show tokenization attributes object
          • bert object
            Hide bert attributes Show bert attributes object
          • mpnet object
            Hide mpnet attributes Show mpnet attributes object
          • roberta object
            Hide roberta attributes Show roberta attributes object
        • results_field string

          The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.

        • max_answer_length number

          The maximum answer length to consider

    • input object Required
      Hide input attribute Show input attribute object
      • field_names array[string] Required

        Path to field or array of paths. Some API's support wildcards in the path to select multiple fields.

    • license_level string

      The license level of the trained model.

    • metadata object
      Hide metadata attributes Show metadata attributes object
      • model_aliases array[string]
      • feature_importance_baseline object

        An object that contains the baseline for feature importance values. For regression analysis, it is a single value. For classification analysis, there is a value for each class.

        Hide feature_importance_baseline attributes Show feature_importance_baseline attributes object
      • hyperparameters array[object]

        List of the available hyperparameters optimized during the fine_parameter_tuning phase as well as specified by the user.

        Hide hyperparameters attributes Show hyperparameters attributes object
        • absolute_importance number

          A positive number showing how much the parameter influences the variation of the loss function. For hyperparameters with values that are not specified by the user but tuned during hyperparameter optimization.

        • name string Required
        • relative_importance number

          A number between 0 and 1 showing the proportion of influence on the variation of the loss function among all tuned hyperparameters. For hyperparameters with values that are not specified by the user but tuned during hyperparameter optimization.

        • supplied boolean Required

          Indicates if the hyperparameter is specified by the user (true) or optimized (false).

        • value number Required

          The value of the hyperparameter, either optimized or specified by the user.

      • total_feature_importance array[object]

        An array of the total feature importance for each feature used from the training data set. This array of objects is returned if data frame analytics trained the model and the request includes total_feature_importance in the include request parameter.

        Hide total_feature_importance attributes Show total_feature_importance attributes object
        • feature_name string Required
        • importance array[object] Required

          A collection of feature importance statistics related to the training data set for this particular feature.

          Hide importance attributes Show importance attributes object
          • mean_magnitude number Required

            The average magnitude of this feature across all the training data. This value is the average of the absolute values of the importance for this feature.

          • max number Required

            The maximum importance value across all the training data for this feature.

          • min number Required

            The minimum importance value across all the training data for this feature.

        • classes array[object] Required

          If the trained model is a classification model, feature importance statistics are gathered per target class value.

          Hide classes attributes Show classes attributes object
          • class_name string Required
          • importance array[object] Required

            A collection of feature importance statistics related to the training data set for this particular feature.

    • model_size_bytes number | string

      One of:
      _types:ByteSize number _types:ByteSize string
    • location object
      Hide location attribute Show location attribute object
      • index object Required
        Hide index attribute Show index attribute object
    • prefix_strings object
      Hide prefix_strings attributes Show prefix_strings attributes object
      • ingest string

        String prepended to input at ingest

      • search string

        String prepended to input at search
PUT /_ml/trained_models/{model_id} 
curl \
 -X PUT http://api.example.com/_ml/trained_models/{model_id} \
 -H "Content-Type: application/json" \
 -d '{"compressed_definition":"string","definition":{"preprocessors":[{"frequency_encoding":{"field":"string","feature_name":"string","frequency_map":{"key":42.0}},"one_hot_encoding":{"field":"string","hot_map":{"key":"string"}},"target_mean_encoding":{"field":"string","feature_name":"string","target_map":{"key":42.0},"default_value":42.0}}],"trained_model":{"tree":{"classification_labels":["string"],"feature_names":["string"],"target_type":"string","tree_structure":[{"decision_type":"string","default_left":true,"leaf_value":42.0,"left_child":42.0,"node_index":42.0,"right_child":42.0,"split_feature":42.0,"split_gain":42.0,"threshold":42.0}]},"tree_node":{"decision_type":"string","default_left":true,"leaf_value":42.0,"left_child":42.0,"node_index":42.0,"right_child":42.0,"split_feature":42.0,"split_gain":42.0,"threshold":42.0},"ensemble":{"aggregate_output":{"logistic_regression":{"weights":42.0},"weighted_sum":{"weights":42.0},"weighted_mode":{"weights":42.0},"exponent":{"weights":42.0}},"classification_labels":["string"],"feature_names":["string"],"target_type":"string","trained_models":[{}]}}},"description":"string","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":{"bert":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"mpnet":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"roberta":{"add_prefix_space":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0}},"results_field":"string","classification_labels":["string"]},"zero_shot_classification":{"tokenization":{"bert":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"mpnet":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"roberta":{"add_prefix_space":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0}},"hypothesis_template":"string","classification_labels":["string"],"results_field":"string","multi_label":true,"labels":["string"]},"fill_mask":{"mask_token":"string","num_top_classes":42.0,"tokenization":{"bert":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"mpnet":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"roberta":{"add_prefix_space":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0}},"results_field":"string"},"ner":{"tokenization":{"bert":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"mpnet":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"roberta":{"add_prefix_space":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0}},"results_field":"string","classification_labels":["string"],"vocabulary":{"index":"string"}},"pass_through":{"tokenization":{"bert":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"mpnet":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"roberta":{"add_prefix_space":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0}},"results_field":"string","vocabulary":{"index":"string"}},"text_embedding":{"embedding_size":42.0,"tokenization":{"bert":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"mpnet":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"roberta":{"add_prefix_space":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0}},"results_field":"string"},"text_expansion":{"tokenization":{"bert":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"mpnet":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"roberta":{"add_prefix_space":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0}},"results_field":"string"},"question_answering":{"num_top_classes":42.0,"tokenization":{"bert":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"mpnet":{"do_lower_case":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0},"roberta":{"add_prefix_space":true,"with_special_tokens":true,"max_sequence_length":42.0,"truncate":"first","span":42.0}},"results_field":"string","max_answer_length":42.0}},"input":{"field_names":"string"},"metadata":{},"model_type":"tree_ensemble","model_size_bytes":42.0,"platform_architecture":"string","tags":["string"],"prefix_strings":{"ingest":"string","search":"string"}}'