stack es inference put-watsonx cli command

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

Create a Watsonx inference endpoint.

--task-type enum required

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

Values: text_embedding, rerank, chat_completion, completion

--watsonx-inference-id string required

The unique identifier of the inference endpoint.

--service enum required

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

Values: watsonxai

--service-settings string required

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

--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 text_embedding task type. Not applicable to the rerank, completion or chat_completion task types.

--input-file string

path to a JSON file to use as command input

-V --[no-]version

Print the Elastic CLI version

--config-file string

path to a config file (default: ~/.elasticrc.yml)

--use-context string

override the active context from the config file

--command-profile string

restrict available commands to a deployment profile (serverless, stack, default)

--[no-]json

output as JSON

--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}}")

--[no-]dry-run

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