Class: Google::Cloud::AIPlatform::V1::RagVectorDbConfig::RagManagedDb::ANN

Inherits:

Object

Object
Google::Cloud::AIPlatform::V1::RagVectorDbConfig::RagManagedDb::ANN

show all

Extended by:: Protobuf::MessageExts::ClassMethods

Includes:: Protobuf::MessageExts

Defined in:: proto_docs/google/cloud/aiplatform/v1/vertex_rag_data.rb

Overview

Config for ANN search.

RagManagedDb uses a tree-based structure to partition data and facilitate faster searches. As a tradeoff, it requires longer indexing time and manual triggering of index rebuild via the ImportRagFiles and UpdateRagCorpus API.

Instance Attribute Summary collapse

#leaf_count ⇒ ::Integer
Number of leaf nodes in the tree-based structure.
#tree_depth ⇒ ::Integer
The depth of the tree-based structure.

Instance Attribute Details

#leaf_count ⇒ `::Integer`

Returns Number of leaf nodes in the tree-based structure. Each leaf node contains groups of closely related vectors along with their corresponding centroid.

Recommended value is 10 * sqrt(num of RagFiles in your RagCorpus).

Default value is 500.

Returns:

(::Integer) —
Number of leaf nodes in the tree-based structure. Each leaf node contains groups of closely related vectors along with their corresponding centroid.

Recommended value is 10 * sqrt(num of RagFiles in your RagCorpus).

Default value is 500.

# File 'proto_docs/google/cloud/aiplatform/v1/vertex_rag_data.rb', line 133

class ANN
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#tree_depth ⇒ `::Integer`

Returns The depth of the tree-based structure. Only depth values of 2 and 3 are supported.

Recommended value is 2 if you have if you have O(10K) files in the RagCorpus and set this to 3 if more than that.

Default value is 2.