class Qdrant::Api::SparseIndexParams

Overview

Configuration for sparse inverted index.

Included Modules

Defined in:

qdrant-api/models/sparse_index_params.cr

Constructors

Instance Method Summary

Macros inherited from module Qdrant::Api::Validation

validates(name, klass, nilable, **rules) validates

Instance methods inherited from module Qdrant::Api::Serializable

eql?(other) eql?, to_body : Hash(String, JSON::Any) to_body, to_h : Hash(String, JSON::Any) to_h, to_s(io : IO) : Nil to_s

Constructor Detail

def self.new(ctx : YAML::ParseContext, node : YAML::Nodes::Node) #

[View source]
def self.new(pull : JSON::PullParser) #

[View source]
def self.new(full_scan_threshold : Int32 | Nil = nil, on_disk : Bool | Nil = nil, datatype : Datatype | Nil = nil) #

Initializes the object @param [Hash] attributes Model attributes in the form of hash


[View source]
def self.new(*, __pull_for_json_serializable pull : JSON::PullParser) #

[View source]
def self.new(*, __context_for_yaml_serializable ctx : YAML::ParseContext, __node_for_yaml_serializable node : YAML::Nodes::Node) #

[View source]

Instance Method Detail

def ==(other : self) #
Description copied from class Reference

Returns true if this reference is the same as other. Invokes same?.


def datatype : Datatype | Nil #

Defines which datatype should be used for the index. Choosing different datatypes allows to optimize memory usage and performance vs accuracy. - For float32 datatype - vectors are stored as single-precision floating point numbers, 4 bytes. - For float16 datatype - vectors are stored as half-precision floating point numbers, 2 bytes. - For uint8 datatype - vectors are quantized to unsigned 8-bit integers, 1 byte. Quantization to fit byte range [0, 255] happens during indexing automatically, so the actual vector data does not need to conform to this range.


[View source]
def datatype=(datatype : Datatype | Nil) #

Defines which datatype should be used for the index. Choosing different datatypes allows to optimize memory usage and performance vs accuracy. - For float32 datatype - vectors are stored as single-precision floating point numbers, 4 bytes. - For float16 datatype - vectors are stored as half-precision floating point numbers, 2 bytes. - For uint8 datatype - vectors are quantized to unsigned 8-bit integers, 1 byte. Quantization to fit byte range [0, 255] happens during indexing automatically, so the actual vector data does not need to conform to this range.


[View source]
def full_scan_threshold : Int32 | Nil #

Optional properties We prefer a full scan search upto (excluding) this number of vectors. Note: this is number of vectors, not KiloBytes.


[View source]
def full_scan_threshold=(value : Int32 | Nil) #

Optional properties We prefer a full scan search upto (excluding) this number of vectors. Note: this is number of vectors, not KiloBytes.


[View source]
def full_scan_threshold_validation_error(value) : String | Nil #

[View source]
def hash(hasher) #
Description copied from class Reference

See Object#hash(hasher)


def list_invalid_properties #

Show invalid properties with the reasons. Usually used together with valid? @return Array for valid properties with the reasons


[View source]
def on_disk : Bool | Nil #

Store index on disk. If set to false, the index will be stored in RAM. Default: false


[View source]
def on_disk=(on_disk : Bool | Nil) #

Store index on disk. If set to false, the index will be stored in RAM. Default: false


[View source]
def valid? #

Check to see if the all the properties in the model are valid @return true if the model is valid


[View source]