MetaFieldRanker Parameters

Learn what parameters you can set for MetaFieldRanker.

YAML Init Parameters

These are the parameters you can pass to this component in the pipeline YAML configuration:

Parameter

Type

Possible values

Description

meta_field

String

The name of the meta field to rank by.
Required.

weight

Float

Default: 1.0

Determines how to rank documents. It's a value in the range "h-1, where:

  • 0 disables ranking by a meta field
  • 0.5 ranking from the previous component and based on the meta field have the same weight
  • 1 ranks by a meta field only.
    Required.

top_k

Integer

Default: None

The maximum number of documents to return per query. If not provided, the ranker returns all documents it receives in the new ranking order.
Optional.

ranking_mode

Literal

reciprocal_rank_fusion
linear_score
Default: reciprocal_rank_fusion

The mode used to combine the retriever's and ranker's scores. Use the linear_score mode only with Retrievers or Rankers that return a score in range ield`.
Required.

sort_order

Literal

ascending
descending
Default: descending

Whether to sort the meta field by ascending or descending order.
Required.

meta_value_type

Optional

float
int
date
Default: None

Parse the meta value into the data type specified before sorting. This will only work if all meta values stored under meta_field in the provided documents are strings.
Optional.

missing_meta

Required

drop
top
bottom
Default: bottom

Specifies what to do with documents that are missing the sorting metadata field. Possible values:

  • drop: Drops the documents entirely.
  • top: Places the documents at the top of the metadata list.
  • bottom: Places the documents at the bottom of the list.
    Required.

REST API Runtime Parameters

There are no runtime parameters you can pass to this component when making a request to the Search REST API endpoint.