Class IndexDatapoint (1.30.1)

  IndexDatapoint 
 ( 
 mapping 
 = 
 None 
 , 
 * 
 , 
 ignore_unknown_fields 
 = 
 False 
 , 
 ** 
 kwargs 
 )

A datapoint of Index.

Attributes

Name
Description
datapoint_id
str
Required. Unique identifier of the datapoint.
feature_vector
MutableSequence[float]
Required. Feature embedding vector. An array of numbers with the length of [NearestNeighborSearchConfig.dimensions].
restricts
MutableSequence[ google.cloud.aiplatform_v1beta1.types.IndexDatapoint.Restriction ]
Optional. List of Restrict of the datapoint, used to perform "restricted searches" where boolean rule are used to filter the subset of the database eligible for matching. See: https://cloud.google.com/vertex-ai/docs/matching-engine/filtering
crowding_tag
google.cloud.aiplatform_v1beta1.types.IndexDatapoint.CrowdingTag
Optional. CrowdingTag of the datapoint, the number of neighbors to return in each crowding can be configured during query.

Classes

CrowdingTag

  CrowdingTag 
 ( 
 mapping 
 = 
 None 
 , 
 * 
 , 
 ignore_unknown_fields 
 = 
 False 
 , 
 ** 
 kwargs 
 )

Crowding tag is a constraint on a neighbor list produced by nearest neighbor search requiring that no more than some value k' of the k neighbors returned have the same value of crowding_attribute.

Restriction

  Restriction 
 ( 
 mapping 
 = 
 None 
 , 
 * 
 , 
 ignore_unknown_fields 
 = 
 False 
 , 
 ** 
 kwargs 
 )

Restriction of a datapoint which describe its attributes(tokens) from each of several attribute categories(namespaces).