Neural query enricher processor

Introduced 2.11

The neural_query_enricher search request processor is designed to set a default machine learning (ML) model ID at the index or field level for neural and neural_sparse queries. To learn more about ML models, see Using ML models within OpenSearch and Connecting to remote models.

Request body fields

The following table lists all available request fields.

Field	Data type	Description
`default_model_id`	String	The model ID of the default model for an index. Optional. You must specify at least one `default_model_id` or `neural_field_default_id`. If both are provided, `neural_field_default_id` takes precedence.
`neural_field_default_id`	Object	A map of key-value pairs representing document field names and their associated default model IDs. Optional. You must specify at least one `default_model_id` or `neural_field_default_id`. If both are provided, `neural_field_default_id` takes precedence.
`tag`	String	The processor’s identifier. Optional.
`description`	String	A description of the processor. Optional.

Example

The following example request creates a search pipeline with a neural_query_enricher search request processor. The processor sets a default model ID at the index level and provides different default model IDs for two specific fields in the index:

PUT /_search/pipeline/default_model_pipeline 
{
  "request_processors": [
    {
      "neural_query_enricher" : {
        "tag": "tag1",
        "description": "Sets the default model ID at index and field levels",
        "default_model_id": "u5j0qYoBMtvQlfhaxOsa",
        "neural_field_default_id": {
           "my_field_1": "uZj0qYoBMtvQlfhaYeud",
           "my_field_2": "upj0qYoBMtvQlfhaZOuM"
        }
      }
    }
  ]
}