public sealed class RagVectorDbConfig.Types.RagManagedDb.Types.ANN : IMessage<RagVectorDbConfig.Types.RagManagedDb.Types.ANN>, IEquatable<RagVectorDbConfig.Types.RagManagedDb.Types.ANN>, IDeepCloneable<RagVectorDbConfig.Types.RagManagedDb.Types.ANN>, IBufferMessage, IMessageReference documentation and code samples for the Vertex AI v1beta1 API class RagVectorDbConfig.Types.RagManagedDb.Types.ANN.
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.
Implements
IMessageRagVectorDbConfigTypesRagManagedDbTypesANN, IEquatableRagVectorDbConfigTypesRagManagedDbTypesANN, IDeepCloneableRagVectorDbConfigTypesRagManagedDbTypesANN, IBufferMessage, IMessageNamespace
Google.Cloud.AIPlatform.V1Beta1Assembly
Google.Cloud.AIPlatform.V1Beta1.dll
Constructors
ANN()
public ANN()ANN(ANN)
public ANN(RagVectorDbConfig.Types.RagManagedDb.Types.ANN other)| Parameter | |
|---|---|
| Name | Description |
other |
RagVectorDbConfigTypesRagManagedDbTypesANN |
Properties
LeafCount
public int LeafCount { get; set; }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.
| Property Value | |
|---|---|
| Type | Description |
int |
|
TreeDepth
public int TreeDepth { get; set; }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.
| Property Value | |
|---|---|
| Type | Description |
int |
|