kdrant-core/dev.kdrant.dsl/PrefetchBuilder

PrefetchBuilder

DSL for a Prefetch sub-request. Like SearchBuilder but without response-shaping options (offset, with_payload, with_vector), which apply only to the outer request.

Constructors

PrefetchBuilder

constructor()

Properties

limit

var limit: Int?

Maximum number of candidates this prefetch contributes.

scoreThreshold

var scoreThreshold: Double?

Drop candidates scoring below this threshold.

using

var using: String?

Name of the vector to search when the collection has named vectors.

Functions

filter

fun filter(filter: Filter)

Restrict this prefetch to points matching an already-built Filter.

fun filter(configure: FilterBuilder.() -> Unit)

Restrict this prefetch to points matching the filter.

lookupFrom

fun lookupFrom(collection: String, vector: String? = null)

Look up query-by-id vectors from another collection.

params

fun params(configure: SearchParamsBuilder.() -> Unit)

Tune the accuracy/speed trade-off.

prefetch

fun prefetch(configure: PrefetchBuilder.() -> Unit)

Add a nested prefetch sub-request.

query

fun query(id: PointId)

Search by the stored vector of an existing point.

fun query(query: QueryInterface)

Set the query directly (e.g. a prebuilt QueryInterface).

fun query(values: List<Float>)

fun query(vararg values: Float)

Search by an explicit dense query vector.

queryDocument

fun queryDocument(text: String, model: String, options: Map<String, JsonElement>? = null)

Search by text the server embeds with model, instead of by a vector the caller computed. Needs a Qdrant with an inference provider configured. See InferenceInput.

queryMulti

fun queryMulti(vectors: List<List<Float>>)

Search by a multi-vector / late-interaction (ColBERT) query.

querySparse

fun querySparse(indices: List<Int>, values: List<Float>)

Search by a sparse query vector (set using to the sparse vector's name).