class
Qdrant::Api::QuantizationSearchParams
- Qdrant::Api::QuantizationSearchParams
- Reference
- Object
Overview
Additional parameters of the search
Included Modules
- JSON::Serializable
- Qdrant::Api::Serializable
- Qdrant::Api::Validation
- YAML::Serializable
Defined in:
qdrant-api/models/quantization_search_params.crConstructors
- .new(ctx : YAML::ParseContext, node : YAML::Nodes::Node)
- .new(pull : JSON::PullParser)
-
.new(ignore : Bool | Nil = false, rescore : Bool | Nil = nil, oversampling : Float64 | Nil = nil)
Initializes the object @param [Hash] attributes Model attributes in the form of hash
- .new(*, __pull_for_json_serializable pull : JSON::PullParser)
- .new(*, __context_for_yaml_serializable ctx : YAML::ParseContext, __node_for_yaml_serializable node : YAML::Nodes::Node)
Instance Method Summary
-
#==(other : self)
Returns
trueif this reference is the same as other. -
#hash(hasher)
See
Object#hash(hasher) -
#ignore : Bool | Nil
Optional properties If true, quantized vectors are ignored.
-
#ignore=(ignore : Bool | Nil)
Optional properties If true, quantized vectors are ignored.
-
#list_invalid_properties
Show invalid properties with the reasons.
-
#oversampling : Float64 | Nil
Oversampling factor for quantization.
-
#oversampling=(value : Float64 | Nil)
Oversampling factor for quantization.
- #oversampling_validation_error(value) : String | Nil
-
#rescore : Bool | Nil
If true, use original vectors to re-score top-k results.
-
#rescore=(rescore : Bool | Nil)
If true, use original vectors to re-score top-k results.
-
#valid?
Check to see if the all the properties in the model are valid @return true if the model is valid
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
Initializes the object @param [Hash] attributes Model attributes in the form of hash
Instance Method Detail
Returns true if this reference is the same as other. Invokes same?.
Optional properties If true, quantized vectors are ignored. Default is false.
Optional properties If true, quantized vectors are ignored. Default is false.
Show invalid properties with the reasons. Usually used together with valid? @return Array for valid properties with the reasons
Oversampling factor for quantization. Default is 1.0. Defines how many extra vectors should be preselected using quantized index, and then re-scored using original vectors. For example, if #oversampling is 2.4 and limit is 100, then 240 vectors will be preselected using quantized index, and then top-100 will be returned after re-scoring.
Oversampling factor for quantization. Default is 1.0. Defines how many extra vectors should be preselected using quantized index, and then re-scored using original vectors. For example, if #oversampling is 2.4 and limit is 100, then 240 vectors will be preselected using quantized index, and then top-100 will be returned after re-scoring.
If true, use original vectors to re-score top-k results. Might require more time in case if original vectors are stored on disk. If not set, qdrant decides automatically apply rescoring or not.
If true, use original vectors to re-score top-k results. Might require more time in case if original vectors are stored on disk. If not set, qdrant decides automatically apply rescoring or not.
Check to see if the all the properties in the model are valid @return true if the model is valid