Class: Turbopuffer::Models::AttributeSchemaConfig::SparseKnn

Inherits:

Internal::Type::BaseModel

• Object
• Internal::Type::BaseModel
• Turbopuffer::Models::AttributeSchemaConfig::SparseKnn

Defined in:

lib/turbopuffer/models/attribute_schema_config.rb

Overview

See Also:

• #sparse_knn

Instance Attribute Summary

• #distance_metric ⇒ Symbol, :dot_product

  A function used to calculate sparse vector similarity.

Instance Method Summary

• #initialize(distance_metric: :dot_product) ⇒ Object constructor

  Whether to create a sparse kNN index for the attribute.

Methods inherited from Internal::Type::BaseModel

==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, inspect, #inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

#coerce, coerce, #dump, dump, #inspect, inspect, meta_info, new_coerce_state, type_info

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Constructor Details

#initialize(distance_metric: :dot_product) ⇒ Object

Whether to create a sparse kNN index for the attribute. Requires the ‘{}f16` type.

Parameters:

• distance_metric (Symbol, :dot_product) (defaults to: :dot_product) —

  A function used to calculate sparse vector similarity.

# File 'lib/turbopuffer/models/attribute_schema_config.rb', line 119

Instance Attribute Details

#distance_metric ⇒ Symbol, :dot_product

A function used to calculate sparse vector similarity.

Returns:

• (Symbol, :dot_product)

# File 'lib/turbopuffer/models/attribute_schema_config.rb', line 117

required :distance_metric, const: :dot_product