Class DenseVectorIndexOptions
java.lang.Object
co.elastic.clients.elasticsearch._types.mapping.DenseVectorIndexOptions
- All Implemented Interfaces:
JsonpSerializable
@JsonpDeserializable
public class DenseVectorIndexOptions
extends Object
implements JsonpSerializable
- See Also:
-
Nested Class Summary
Nested Classes -
Field Summary
FieldsModifier and TypeFieldDescriptionstatic final JsonpDeserializer<DenseVectorIndexOptions>Json deserializer forDenseVectorIndexOptions -
Method Summary
Modifier and TypeMethodDescriptionfinal FloatThe confidence interval to use when quantizing the vectors.final IntegerThe number of candidates to track while assembling the list of nearest neighbors for each new node.final Integerm()The number of neighbors each node will be connected to in the HNSW graph.static DenseVectorIndexOptionsvoidserialize(jakarta.json.stream.JsonGenerator generator, JsonpMapper mapper) Serialize this object to JSON.protected voidserializeInternal(jakarta.json.stream.JsonGenerator generator, JsonpMapper mapper) protected static voidtoString()type()Required - The type of kNN algorithm to use.
-
Field Details
-
_DESERIALIZER
Json deserializer forDenseVectorIndexOptions
-
-
Method Details
-
of
public static DenseVectorIndexOptions of(Function<DenseVectorIndexOptions.Builder, ObjectBuilder<DenseVectorIndexOptions>> fn) -
confidenceInterval
The confidence interval to use when quantizing the vectors. Can be any value between and including0.90and1.0or exactly0. When the value is0, this indicates that dynamic quantiles should be calculated for optimized quantization. When between0.90and1.0, this value restricts the values used when calculating the quantization thresholds.For example, a value of
0.95will only use the middle95%of the values when calculating the quantization thresholds (e.g. the highest and lowest2.5%of values will be ignored).Defaults to
1/(dims + 1)forint8quantized vectors and0forint4for dynamic quantile calculation.Only applicable to
int8_hnsw,int4_hnsw,int8_flat, andint4_flatindex types.API name:
confidence_interval -
efConstruction
The number of candidates to track while assembling the list of nearest neighbors for each new node.Only applicable to
hnsw,int8_hnsw,bbq_hnsw, andint4_hnswindex types.API name:
ef_construction -
m
The number of neighbors each node will be connected to in the HNSW graph.Only applicable to
hnsw,int8_hnsw,bbq_hnsw, andint4_hnswindex types.API name:
m -
type
Required - The type of kNN algorithm to use.API name:
type -
serialize
Serialize this object to JSON.- Specified by:
serializein interfaceJsonpSerializable
-
serializeInternal
-
toString
-
setupDenseVectorIndexOptionsDeserializer
protected static void setupDenseVectorIndexOptionsDeserializer(ObjectDeserializer<DenseVectorIndexOptions.Builder> op)
-