stack es ml put-trained-model cli command

elastic stack es ml put-trained-model --model-id <model-id> [options]

Create a trained model.

Behaviour flags:

--dry-run — validate all inputs and exit without performing any action

--model-id string required

The unique identifier of the trained model.

--defer-definition-decompression

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

--wait-for-completion

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

--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 string

The inference definition for the model. If definition is specified, then compressed_definition cannot be specified.

--description string

A human-readable description of the inference trained model.

--inference-config string

The default configuration for inference. This can be either a regression or classification configuration. It must match the underlying definition.trained_model's target_type. For pre-packaged models such as ELSER the config is not required.

--input string

The input field names for the model definition.

--metadata string

An object map that contains metadata about the model.

--model-type enum

The model type.

Values: tree_ensemble, lang_ident, 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-aarch64, or windows-x86_64. For portable models (those that work independent of processor architecture or OS features), leave this field unset.

--tags string[]

An array of tags to organize the model.

Repeatable: pass --tags multiple times to supply more than one value

--prefix-strings string

Optional prefix strings applied at inference

--error-trace

When set to true Elasticsearch will include the full stack trace of errors when they occur.

--filter-path string

Comma-separated list of filters in dot notation which reduce the response returned by Elasticsearch.

Repeatable: pass --filter-path multiple times to supply more than one value

--human

When set to true will return statistics in a format suitable for humans. For example "exists_time": "1h" for humans and "exists_time_in_millis": 3600000 for computers. When disabled the human readable values will be omitted. This makes sense for responses being consumed only by machines.

--pretty

If set to true the returned JSON will be "pretty-formatted". Only use this option for debugging only.

--input-file string

path to a JSON file to use as command input

--dry-run

validate all inputs and exit without performing any action (preview changes without applying them)

--no-validate

skip input validation and send the request as-is

--output-fields string

comma-separated list of fields to include in output (dot-notation supported)

--output-template string

Mustache-like template for custom text output (e.g. "{{id}}: {{name}}")

--json

output as JSON