stack es inference put-elasticsearch cli command

elastic stack es inference put-elasticsearch \
  --service <service> \
  --service-settings <service-settings> \
  --task-type <task-type> \
  --elasticsearch-inference-id <elasticsearch-inference-id> \
  [options]

Create an Elasticsearch inference endpoint.

Behaviour flags:

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

--service enum required

The type of service supported for the specified task type. In this case, elasticsearch.

Values: elasticsearch

--service-settings string required

Settings used to install the inference model. These settings are specific to the elasticsearch service.

--task-type enum required

The type of the inference task that the model will perform.

Values: rerank, sparse_embedding, text_embedding

--elasticsearch-inference-id string required

The unique identifier of the inference endpoint. The must not match the model_id.

--timeout string

Specifies the amount of time to wait for the inference endpoint to be created.

--chunking-settings string

The chunking configuration object. Applies only to the sparse_embedding and text_embedding task types. Not applicable to the rerank task type.

--task-settings string

Settings to configure the inference task. These settings are specific to the task type you specified.

--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