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

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/aiplatform/v1/vertex_rag_data.rb

Overview

The config for the default RAG-managed Vector DB.

Defined Under Namespace

Classes: ANN, KNN

Instance Attribute Summary collapse

Instance Attribute Details

#ann ⇒ ::Google::Cloud::AIPlatform::V1::RagVectorDbConfig::RagManagedDb::ANN

Returns Performs an ANN search on RagCorpus. Use this if you have a lot of files (> 10K) in your RagCorpus and want to reduce the search latency.

Note: The following fields are mutually exclusive: ann, knn. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns:

  • (::Google::Cloud::AIPlatform::V1::RagVectorDbConfig::RagManagedDb::ANN) —

    Performs an ANN search on RagCorpus. Use this if you have a lot of files (> 10K) in your RagCorpus and want to reduce the search latency.

    Note: The following fields are mutually exclusive: ann, knn. If a field in that set is populated, all other fields in the set will automatically be cleared.



99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
 
# File 'proto_docs/google/cloud/aiplatform/v1/vertex_rag_data.rb', line 99

class RagManagedDb
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Config for KNN search.
  class KNN
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # 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.
  # @!attribute [rw] tree_depth
  #   @return [::Integer]
  #     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.
  # @!attribute [rw] leaf_count
  #   @return [::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.
  class ANN
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#knn ⇒ ::Google::Cloud::AIPlatform::V1::RagVectorDbConfig::RagManagedDb::KNN

Returns Performs a KNN search on RagCorpus. Default choice if not specified.

Note: The following fields are mutually exclusive: knn, ann. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns:



99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
 
# File 'proto_docs/google/cloud/aiplatform/v1/vertex_rag_data.rb', line 99

class RagManagedDb
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Config for KNN search.
  class KNN
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # 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.
  # @!attribute [rw] tree_depth
  #   @return [::Integer]
  #     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.
  # @!attribute [rw] leaf_count
  #   @return [::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.
  class ANN
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end