Hybrid and Multi-Stage Queries

Available as of v1.10.0

With the introduction of multiple named vectors per point, there are use-cases when the best search is obtained by combining multiple queries, or by performing the search in more than one stage.

Qdrant has a flexible and universal interface to make this possible, called Query API (API reference).

The main component for making the combinations of queries possible is the prefetch parameter, which enables making sub-requests.

Specifically, whenever a query has at least one prefetch, Qdrant will:

Perform the prefetch query (or queries),
Apply the main query over the results of its prefetch(es).

Additionally, prefetches can have prefetches themselves, so you can have nested prefetches.

Using offset parameter only affects the main query. This means that the prefetches must have a limit of at least limit + offset of the main query, otherwise you can get an empty result.

Hybrid Search

One of the most common problems when you have different representations of the same data is to combine the queried points for each representation into a single result.

For example, in text search, it is often useful to combine dense and sparse vectors to get the best of both worlds: semantic understanding from dense vectors and precise word matching from sparse vectors.

Qdrant has a few ways of fusing the results from different queries: rrf and dbsf

Reciprocal Rank Fusion (RRF)

RRF considers the positions of results within each query and boosts those that appear closer to the top in multiple sets of results. The score of a document is calculated using its rank in each result set:

$s c o r e (d \in D) = \sum_{r_{d} \in R (d)} \frac{1}{k + \frac{r_{d} + 1}{w_{r}} - 1}$

Where:

$D$ the set of points across all results
$R (d)$ is the set of rankings for a particular document
$k$ is a constant (set to 2 by default)
$r$ is an ordered set of results from one source
$r_{d}$ is the rank of document $d$ in ranking $r$
$w_{r}$ is the weight of ranking $r$ (set to 1 by default)

Qdrant uses zero-based rank positions; the top result has $r_{d} = 0$ .

Because $w_{r}$ defaults to 1, without setting explicit weights, the formula can be simplified to the original RRF function:

$s c o r e (d \in D) = \sum_{r_{d} \in R (d)} \frac{1}{k + r_{d}}$

Here is an example of RRF for a query containing two prefetches against different named vectors configured to hold sparse and dense vectors, respectively.

httppythontypescriptrustjavacsharpgo

POST /collections/{collection_name}/points/query
{
    "prefetch": [
        {
            "query": { 
                "indices": [1, 42],    // <┐
                "values": [0.22, 0.8]  // <┴─sparse vector
             },
            "using": "sparse",
            "limit": 20
        },
        {
            "query": [0.01, 0.45, 0.67, ...], // <-- dense vector
            "using": "dense",
            "limit": 20
        }
    ],
    "query": { "rrf": {} }, // <--- reciprocal rank fusion with defaults
    "limit": 10
}

from qdrant_client import QdrantClient, models

client = QdrantClient(url="http://localhost:6333")

client.query_points(
    collection_name="{collection_name}",
    prefetch=[
        models.Prefetch(
            query=models.SparseVector(indices=[1, 42], values=[0.22, 0.8]),
            using="sparse",
            limit=20,
        ),
        models.Prefetch(
            query=[0.01, 0.45, 0.67],  # <-- dense vector
            using="dense",
            limit=20,
        ),
    ],
    query=models.RrfQuery(rrf=models.Rrf()),
)

import { QdrantClient } from "@qdrant/js-client-rest";

const client = new QdrantClient({ host: "localhost", port: 6333 });

client.query("{collection_name}", {
    prefetch: [
        {
            query: {
                values: [0.22, 0.8],
                indices: [1, 42],
            },
            using: 'sparse',
            limit: 20,
        },
        {
            query: [0.01, 0.45, 0.67],
            using: 'dense',
            limit: 20,
        },
    ],
    query: {
        rrf: {},
    },
});

use qdrant_client::Qdrant;
use qdrant_client::qdrant::{PrefetchQueryBuilder, Query, QueryPointsBuilder, RrfBuilder};

let client = Qdrant::from_url("http://localhost:6334").build()?;

client.query(
    QueryPointsBuilder::new("{collection_name}")
        .add_prefetch(PrefetchQueryBuilder::default()
            .query(Query::new_nearest([(1, 0.22), (42, 0.8)].as_slice()))
            .using("sparse")
            .limit(20u64)
        )
        .add_prefetch(PrefetchQueryBuilder::default()
            .query(Query::new_nearest(vec![0.01, 0.45, 0.67]))
            .using("dense")
            .limit(20u64)
        )
        .query(Query::new_rrf(RrfBuilder::default()))
).await?;

import static io.qdrant.client.QueryFactory.nearest;
import static io.qdrant.client.QueryFactory.rrf;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Points.PrefetchQuery;
import io.qdrant.client.grpc.Points.QueryPoints;
import io.qdrant.client.grpc.Points.Rrf;
import java.util.List;

QdrantClient client = new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client.queryAsync(
    QueryPoints.newBuilder()
    .setCollectionName("{collection_name}")
    .addPrefetch(PrefetchQuery.newBuilder()
      .setQuery(nearest(List.of(0.22f, 0.8f), List.of(1, 42)))
      .setUsing("sparse")
      .setLimit(20)
      .build())
    .addPrefetch(PrefetchQuery.newBuilder()
      .setQuery(nearest(List.of(0.01f, 0.45f, 0.67f)))
      .setUsing("dense")
      .setLimit(20)
      .build())
    .setQuery(rrf(Rrf.newBuilder().build()))
    .build())
  .get();

using Qdrant.Client;
using Qdrant.Client.Grpc;

var client = new QdrantClient("localhost", 6334);

await client.QueryAsync(
  collectionName: "{collection_name}",
  prefetch: new List < PrefetchQuery > {
    new() {
      Query = new(float, uint)[] {
          (0.22f, 1), (0.8f, 42),
        },
        Using = "sparse",
        Limit = 20
    },
    new() {
      Query = new float[] {
          0.01f, 0.45f, 0.67f
        },
        Using = "dense",
        Limit = 20
    }
  },
  query: new Rrf()
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.Query(context.Background(), &qdrant.QueryPoints{
	CollectionName: "{collection_name}",
	Prefetch: []*qdrant.PrefetchQuery{
		{
			Query: qdrant.NewQuerySparse([]uint32{1, 42}, []float32{0.22, 0.8}),
			Using: qdrant.PtrOf("sparse"),
			Limit: qdrant.PtrOf(uint64(20)),
		},
		{
			Query: qdrant.NewQueryDense([]float32{0.01, 0.45, 0.67}),
			Using: qdrant.PtrOf("dense"),
			Limit: qdrant.PtrOf(uint64(20)),
		},
	},
	Query: qdrant.NewQueryRRF(&qdrant.Rrf{}),
})

Setting RRF Constant k

Available as of v1.16.0

To set the constant $k$ in the formula:

httppythontypescriptrustjavacsharpgo

POST /collections/{collection_name}/points/query
{
    "prefetch": [
      // 2+ prefetches here
    ],
    "query": { "rrf": {"k": 60 } }, // <--- parameterized reciprocal rank fusion
    "limit": 10
}

from qdrant_client import QdrantClient, models

client = QdrantClient(url="http://localhost:6333")

client.query_points(
    collection_name="{collection_name}",
    prefetch=[
        # 2+ prefetches here
    ],
    query=models.RrfQuery(rrf=models.Rrf(k=60)),
)

import { QdrantClient } from "@qdrant/js-client-rest";

const client = new QdrantClient({ host: "localhost", port: 6333 });

client.query("{collection_name}", {
    prefetch: [
      // 2+ prefetches here
    ],
    query: { rrf: { k: 60 } },
});

use qdrant_client::Qdrant;
use qdrant_client::qdrant::{RrfBuilder, Query, QueryPointsBuilder};

let client = Qdrant::from_url("http://localhost:6334").build()?;

client.query(
    QueryPointsBuilder::new("{collection_name}")
        // .add_prefetch(...)  <┐
        // .add_prefetch(...)  <┴─ 2+ prefetches here
        .query(Query::new_rrf(RrfBuilder::with_k(60)))
).await?;

import static io.qdrant.client.QueryFactory.rrf;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Points.PrefetchQuery;
import io.qdrant.client.grpc.Points.QueryPoints;
import io.qdrant.client.grpc.Points.Rrf;
import java.util.List;

QdrantClient client = new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client
    .queryAsync(
        QueryPoints.newBuilder()
            .setCollectionName("{collection_name}")
            // .addPrefetch(...) <┐
            // .addPrefetch(...) <┴─ 2+ prefetches here
            .setQuery(rrf(Rrf.newBuilder().setK(60).build()))
            .build())
    .get();

using Qdrant.Client;
using Qdrant.Client.Grpc;

var client = new QdrantClient("localhost", 6334);

await client.QueryAsync(
  collectionName: "{collection_name}",
  prefetch: new List<PrefetchQuery>
  {
	  // 2+ prefetches here
  },
  query: new Rrf
  {
	  K = 60,
  }
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.Query(context.Background(), &qdrant.QueryPoints{
	CollectionName: "{collection_name}",
	Prefetch:       []*qdrant.PrefetchQuery{
		// 2+ prefetches here
	},
	Query: qdrant.NewQueryRRF(
		&qdrant.Rrf{
			K: qdrant.PtrOf(uint32(60)),
		}),
})

Weighted RRF

Available as of v1.17.0

By default, each query is assigned an equal weight. In reality, one retriever is often stronger than the other for a given workload. For example, a dense retriever may dominate on natural-language queries, while BM25 may win on identifier-heavy ones. Assigning equal weight to both can let the weaker retriever drag down results. To address this, you can assign greater weight to rankers that perform well on your evaluation set.

The rrf query allows you to configure relative weights for each of the prefetches. For example, if you have two prefetches and assign a weight of 3.0 to the first and 1.0 to the second, a document ranked third in the first query scores the same as a document ranked first in the second query. In the case of non-overlapping result sets, these weights return three results from the first set for every one result from the second set.

Weights should be provided as an array of numbers, where each weight is applied to the corresponding prefetch in the order they are defined. The number of weights must match the number of prefetches.

httppythontypescriptrustjavacsharpgo

POST /collections/{collection_name}/points/query
{
    "prefetch": [
        // Prefetches here
    ],
    "query": {
        "rrf": {
            "weights": [3.0, 1.0]
        }
    },
    "limit": 10
}

from qdrant_client import QdrantClient, models

client = QdrantClient(url="http://localhost:6333")

client.query_points(
    collection_name="{collection_name}",
    prefetch=[
        # 2+ prefetches here
    ],
    query=models.RrfQuery(rrf=models.Rrf(weights=[3.0, 1.0])),
)

import { QdrantClient } from "@qdrant/js-client-rest";

const client = new QdrantClient({ host: "localhost", port: 6333 });

client.query("{collection_name}", {
    prefetch: [
        // Prefetches here
    ],
    query: {
        rrf: {
            weights: [3.0, 1.0],
        },
    },
    limit: 10,
});

use qdrant_client::qdrant::{Query, QueryPointsBuilder, RrfBuilder};
use qdrant_client::Qdrant;

let client = Qdrant::from_url("http://localhost:6334").build()?;

client
    .query(
        QueryPointsBuilder::new("{collection_name}")
            // .add_prefetch(...)  <┐
            // .add_prefetch(...)  <┴─ 2+ prefetches here
            .query(Query::new_rrf(RrfBuilder::new().weights(vec![3.0, 1.0]))),
    )
    .await?;

import static io.qdrant.client.QueryFactory.rrf;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Points.PrefetchQuery;
import io.qdrant.client.grpc.Points.QueryPoints;
import io.qdrant.client.grpc.Points.Rrf;
import java.util.List;

QdrantClient client = new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client
        .queryAsync(
        QueryPoints.newBuilder()
                .setCollectionName("{collection_name}")
                // .addPrefetch(...) <┐
                // .addPrefetch(...) <┴─ Prefetches here
                .setQuery(rrf(Rrf.newBuilder().addAllWeights(List.of(3.0f, 1.0f)).build()))
                .build())
        .get();

using Qdrant.Client;
using Qdrant.Client.Grpc;

var client = new QdrantClient("localhost", 6334);

await client.QueryAsync(
  collectionName: "{collection_name}",
  prefetch: new List<PrefetchQuery>
  {
	  // 2+ prefetches here
  },
  query: new Rrf
  {
	  Weights = {3.0f, 1.0f},
  }
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.Query(context.Background(), &qdrant.QueryPoints{
	CollectionName: "{collection_name}",
	Prefetch:       []*qdrant.PrefetchQuery{
		// Prefetches here
	},
	Query: qdrant.NewQueryRRF(
		&qdrant.Rrf{
			Weights: []float32{3.0, 1.0},
		}),
})

Weights are a configuration choice, not something you can tune arbitrarily. The most reliable way to set them is by testing on your data.

With an eval set (queries paired with known-relevant docs): split your eval queries in two. Try different weights on the first half, then measure on the second half. Measuring on the same queries you tuned on inflates the result. The Choosing a Fusion Method notebook provides a reusable tune_rrf_weights grid-search helper you can adapt to a train/val split.
Without an eval set: leave weights at the default (1.0, 1.0). Hand-tuned weights without measurement are unlikely to beat the default reliably.

Retune when your retrievers change (new embedding model, new chunking), when your corpus drifts substantially, or on a fixed cadence with a fresh eval sample.

Distribution-Based Score Fusion (DBSF)

Available as of v1.11.0

DBSF keeps the raw scores from each query but normalizes their distributions before combining. For each retriever’s returned set, it computes the mean $μ$ and sample standard deviation $σ$ , then normalizes every score using the 3-sigma extremes as endpoints:

$\hat{s} = \frac{s - (μ - 3 σ)}{6 σ}$

Normalized scores are summed across retrievers. Different score magnitudes no longer matter because each retriever contributes on the same comparable range.

dbsf is stateless and computes its normalization limits from each query's returned points, not from all the scores it has seen. Scores are not clipped to [0, 1]; values outside the 3-sigma range remain outside it after the remap. If all returned scores are identical (or only one point is returned), DBSF emits 0.5 rather than dividing by zero.

DBSF is a reasonable choice when you trust your retrievers’ raw scores to carry magnitude information. On well-calibrated retrievers DBSF can outperform tuned weighted RRF; on others weighted RRF wins. Neither dominates the other in general, so use your eval set to choose between them. Two caveats apply: the statistics come from the prefetch top-k (a small sample), and a single dominant outlier in that top-k can skew normalization for that query. Increase the prefetch limit if you see unstable rankings.

httppythontypescriptrustjavacsharpgo

POST /collections/{collection_name}/points/query
{
    "prefetch": [
        {
            "query": { 
                "indices": [1, 42],    // <┐
                "values": [0.22, 0.8]  // <┴─sparse vector
             },
            "using": "sparse",
            "limit": 20
        },
        {
            "query": [0.01, 0.45, 0.67, ...], // <-- dense vector
            "using": "dense",
            "limit": 20
        }
    ],
    "query": { "fusion": "dbsf" }, // <--- distribution-based score fusion
    "limit": 10
}

from qdrant_client import QdrantClient, models

client = QdrantClient(url="http://localhost:6333")

client.query_points(
    collection_name="{collection_name}",
    prefetch=[
        models.Prefetch(
            query=models.SparseVector(indices=[1, 42], values=[0.22, 0.8]),
            using="sparse",
            limit=20,
        ),
        models.Prefetch(
            query=[0.01, 0.45, 0.67],  # <-- dense vector
            using="dense",
            limit=20,
        ),
    ],
    query=models.FusionQuery(fusion=models.Fusion.DBSF),
)

import { QdrantClient } from "@qdrant/js-client-rest";

const client = new QdrantClient({ host: "localhost", port: 6333 });

client.query("{collection_name}", {
    prefetch: [
        {
            query: {
                values: [0.22, 0.8],
                indices: [1, 42],
            },
            using: 'sparse',
            limit: 20,
        },
        {
            query: [0.01, 0.45, 0.67],
            using: 'dense',
            limit: 20,
        },
    ],
    query: {
        fusion: 'dbsf',
    },
});

use qdrant_client::Qdrant;
use qdrant_client::qdrant::{Fusion, PrefetchQueryBuilder, Query, QueryPointsBuilder};

let client = Qdrant::from_url("http://localhost:6334").build()?;

client.query(
    QueryPointsBuilder::new("{collection_name}")
        .add_prefetch(PrefetchQueryBuilder::default()
            .query(Query::new_nearest([(1, 0.22), (42, 0.8)].as_slice()))
            .using("sparse")
            .limit(20u64)
        )
        .add_prefetch(PrefetchQueryBuilder::default()
            .query(Query::new_nearest(vec![0.01, 0.45, 0.67]))
            .using("dense")
            .limit(20u64)
        )
        .query(Query::new_fusion(Fusion::Dbsf))
).await?;

import static io.qdrant.client.QueryFactory.fusion;
import static io.qdrant.client.QueryFactory.nearest;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Points.Fusion;
import io.qdrant.client.grpc.Points.PrefetchQuery;
import io.qdrant.client.grpc.Points.QueryPoints;
import java.util.List;

QdrantClient client = new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client.queryAsync(
    QueryPoints.newBuilder()
    .setCollectionName("{collection_name}")
    .addPrefetch(PrefetchQuery.newBuilder()
      .setQuery(nearest(List.of(0.22f, 0.8f), List.of(1, 42)))
      .setUsing("sparse")
      .setLimit(20)
      .build())
    .addPrefetch(PrefetchQuery.newBuilder()
      .setQuery(nearest(List.of(0.01f, 0.45f, 0.67f)))
      .setUsing("dense")
      .setLimit(20)
      .build())
    .setQuery(fusion(Fusion.DBSF))
    .build())
  .get();

using Qdrant.Client;
using Qdrant.Client.Grpc;

var client = new QdrantClient("localhost", 6334);

await client.QueryAsync(
  collectionName: "{collection_name}",
  prefetch: new List < PrefetchQuery > {
    new() {
      Query = new(float, uint)[] {
          (0.22f, 1), (0.8f, 42),
        },
        Using = "sparse",
        Limit = 20
    },
    new() {
      Query = new float[] {
          0.01f, 0.45f, 0.67f
        },
        Using = "dense",
        Limit = 20
    }
  },
  query: Fusion.Dbsf
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.Query(context.Background(), &qdrant.QueryPoints{
	CollectionName: "{collection_name}",
	Prefetch: []*qdrant.PrefetchQuery{
		{
			Query: qdrant.NewQuerySparse([]uint32{1, 42}, []float32{0.22, 0.8}),
			Using: qdrant.PtrOf("sparse"),
			Limit: qdrant.PtrOf(uint64(20)),
		},
		{
			Query: qdrant.NewQueryDense([]float32{0.01, 0.45, 0.67}),
			Using: qdrant.PtrOf("dense"),
			Limit: qdrant.PtrOf(uint64(20)),
		},
	},
	Query: qdrant.NewQueryFusion(qdrant.Fusion_DBSF),
})

Choosing a Fusion Method

If you have…	Use
An eval set (queries with known-relevant docs) to tune on	Weighted RRF, with weights tuned on a train/val split
Trust in your retrievers’ raw scores and no eval set	DBSF
Neither an eval set nor strong score priors	RRF (the safe default)

For a deeper breakdown of when to prefer each, see the FAQ on RRF vs. DBSF. To layer business logic (recency, popularity, geo) on top of a fused result, see Custom scoring with a formula query.

Multi-Stage Queries

In general, larger vector representations give more accurate search results, but makes them more expensive to compute.

Splitting the search into two stages is a known technique to mitigate this effect:

First, use a smaller and cheaper representation to get a large list of candidates.
Then, re-score the candidates using the larger and more accurate representation.

There are a few ways to build search architectures around this idea:

The quantized vectors as a first stage, and the full-precision vectors as a second stage.
Leverage Matryoshka Representation Learning (MRL) to generate candidate vectors with a shorter vector, and then refine them with a longer one.
Use regular dense vectors to pre-fetch the candidates, and then re-score them with a multi-vector model like ColBERT.

To get the best of all worlds, Qdrant has a convenient interface to perform the queries in stages, such that the coarse results are fetched first, and then they are refined later with larger vectors.

Disable the HNSW index for vectors used only for rescoring by setting m=0 in the vector's HNSW configuration. Rescoring does not use the HNSW index, so disabling it will free up memory.

Re-Scoring Examples

Fetch 1000 results using a shorter MRL byte vector, then re-score them using the full vector and get the top 10.

httppythontypescriptrustjavacsharpgo

POST /collections/{collection_name}/points/query
{
    "prefetch": {
        "query": [1, 23, 45, 67], // <------------- small byte vector
        "using": "mrl_byte",
        "limit": 1000
    },
    "query": [0.01, 0.299, 0.45, 0.67, ...], // <-- full vector
    "using": "full",
    "limit": 10
}

from qdrant_client import QdrantClient, models

client = QdrantClient(url="http://localhost:6333")

client.query_points(
    collection_name="{collection_name}",
    prefetch=models.Prefetch(
        query=[1, 23, 45, 67],  # <------------- small byte vector
        using="mrl_byte",
        limit=1000,
    ),
    query=[0.01, 0.299, 0.45, 0.67],  # <-- full vector
    using="full",
    limit=10,
)

import { QdrantClient } from "@qdrant/js-client-rest";

const client = new QdrantClient({ host: "localhost", port: 6333 });

client.query("{collection_name}", {
  prefetch: {
    query: [1, 23, 45, 67], // <------------- small byte vector
    using: 'mrl_byte',
    limit: 1000,
  },
  query: [0.01, 0.299, 0.45, 0.67], // <-- full vector,
  using: 'full',
  limit: 10,
});

use qdrant_client::Qdrant;
use qdrant_client::qdrant::{PrefetchQueryBuilder, Query, QueryPointsBuilder};

let client = Qdrant::from_url("http://localhost:6334").build()?;

client.query(
    QueryPointsBuilder::new("{collection_name}")
        .add_prefetch(PrefetchQueryBuilder::default()
            .query(Query::new_nearest(vec![1.0, 23.0, 45.0, 67.0]))
            .using("mlr_byte")
            .limit(1000u64)
        )
        .query(Query::new_nearest(vec![0.01, 0.299, 0.45, 0.67]))
        .using("full")
        .limit(10u64)
).await?;

import static io.qdrant.client.QueryFactory.nearest;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Points.PrefetchQuery;
import io.qdrant.client.grpc.Points.QueryPoints;

QdrantClient client =
    new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client
    .queryAsync(
        QueryPoints.newBuilder()
            .setCollectionName("{collection_name}")
            .addPrefetch(
                PrefetchQuery.newBuilder()
                    .setQuery(nearest(1, 23, 45, 67))	// <------------- small byte vector
                    .setLimit(1000)
                    .setUsing("mrl_byte")
                    .build())
            .setQuery(nearest(0.01f, 0.299f, 0.45f, 0.67f))	 // <-- full vector
            .setUsing("full")
            .setLimit(10)
            .build())
    .get();

using Qdrant.Client;
using Qdrant.Client.Grpc;

var client = new QdrantClient("localhost", 6334);

await client.QueryAsync(
  collectionName: "{collection_name}",
  prefetch: new List<PrefetchQuery> {
    new() {
      Query = new float[] { 1,23, 45, 67 }, // <------------- small byte vector
        Using = "mrl_byte",
        Limit = 1000
    }
  },
  query: new float[] { 0.01f, 0.299f, 0.45f, 0.67f }, // <-- full vector
  usingVector: "full",
  limit: 10
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.Query(context.Background(), &qdrant.QueryPoints{
	CollectionName: "{collection_name}",
	Prefetch: []*qdrant.PrefetchQuery{
		{
			Query: qdrant.NewQueryDense([]float32{1, 23, 45, 67}),
			Using: qdrant.PtrOf("mrl_byte"),
			Limit: qdrant.PtrOf(uint64(1000)),
		},
	},
	Query: qdrant.NewQueryDense([]float32{0.01, 0.299, 0.45, 0.67}),
	Using: qdrant.PtrOf("full"),
})

Fetch 100 results using the default vector, then re-score them using a multi-vector to get the top 10.

httppythontypescriptrustjavacsharpgo

POST /collections/{collection_name}/points/query
{
    "prefetch": {
        "query": [0.01, 0.45, 0.67, ...], // <-- dense vector
        "limit": 100
    },
    "query": [           // <─┐
        [0.1, 0.2, ...], // < │
        [0.2, 0.1, ...], // < ├─ multi-vector
        [0.8, 0.9, ...]  // < │
    ],                   // <─┘       
    "using": "colbert",
    "limit": 10
}

from qdrant_client import QdrantClient, models

client = QdrantClient(url="http://localhost:6333")

client.query_points(
    collection_name="{collection_name}",
    prefetch=models.Prefetch(
        query=[0.01, 0.45, 0.67, 0.53],  # <-- dense vector
        limit=100,
    ),
    query=[
        [0.1, 0.2, 0.32],  # <─┐
        [0.2, 0.1, 0.52],  # < ├─ multi-vector
        [0.8, 0.9, 0.93],  # < ┘
    ],
    using="colbert",
    limit=10,
)

import { QdrantClient } from "@qdrant/js-client-rest";

const client = new QdrantClient({ host: "localhost", port: 6333 });

client.query("{collection_name}", {
    prefetch: {
        query: [1, 23, 45, 67], // <------------- small byte vector
        limit: 100,
    },
    query: [
        [0.1, 0.2], // <─┐
        [0.2, 0.1], // < ├─ multi-vector
        [0.8, 0.9], // < ┘
    ],
    using: 'colbert',
    limit: 10,
});

use qdrant_client::Qdrant;
use qdrant_client::qdrant::{PrefetchQueryBuilder, Query, QueryPointsBuilder};

let client = Qdrant::from_url("http://localhost:6334").build()?;

client.query(
    QueryPointsBuilder::new("{collection_name}")
        .add_prefetch(PrefetchQueryBuilder::default()
            .query(Query::new_nearest(vec![0.01, 0.45, 0.67]))
            .limit(100u64)
        )
        .query(Query::new_nearest(vec![
            vec![0.1, 0.2],
            vec![0.2, 0.1],
            vec![0.8, 0.9],
        ]))
        .using("colbert")
        .limit(10u64)
).await?;

import static io.qdrant.client.QueryFactory.nearest;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Points.PrefetchQuery;
import io.qdrant.client.grpc.Points.QueryPoints;

QdrantClient client =
    new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client
    .queryAsync(
        QueryPoints.newBuilder()
            .setCollectionName("{collection_name}")
            .addPrefetch(
                PrefetchQuery.newBuilder()
                    .setQuery(nearest(0.01f, 0.45f, 0.67f)) // <-- dense vector
                    .setLimit(100)
                    .build())
            .setQuery(
                nearest(
                    new float[][] {
                      {0.1f, 0.2f},	// <─┐
                      {0.2f, 0.1f},	// < ├─ multi-vector
                      {0.8f, 0.9f}	// < ┘
                    }))
            .setUsing("colbert")
            .setLimit(10)
            .build())
    .get();

using Qdrant.Client;
using Qdrant.Client.Grpc;

var client = new QdrantClient("localhost", 6334);

await client.QueryAsync(
  collectionName: "{collection_name}",
  prefetch: new List <PrefetchQuery> {
    new() {
      Query = new float[] { 0.01f, 0.45f, 0.67f	},	// <-- dense vector****
        Limit = 100
    }
  },
  query: new float[][] {
    [0.1f, 0.2f], // <─┐
    [0.2f, 0.1f], // < ├─ multi-vector
    [0.8f, 0.9f]  // < ┘
  },
  usingVector: "colbert",
  limit: 10
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.Query(context.Background(), &qdrant.QueryPoints{
	CollectionName: "{collection_name}",
	Prefetch: []*qdrant.PrefetchQuery{
		{
			Query: qdrant.NewQueryDense([]float32{0.01, 0.45, 0.67}),
			Limit: qdrant.PtrOf(uint64(100)),
		},
	},
	Query: qdrant.NewQueryMulti([][]float32{
		{0.1, 0.2},
		{0.2, 0.1},
		{0.8, 0.9},
	}),
	Using: qdrant.PtrOf("colbert"),
})

You can combine all of these techniques in a single query:

httppythontypescriptrustjavacsharpgo

POST /collections/{collection_name}/points/query
{
    "prefetch": {
        "prefetch": {
            "query": [1, 23, 45, 67], // <------ small byte vector
            "using": "mrl_byte",
            "limit": 1000
        },
        "query": [0.01, 0.45, 0.67, ...], // <-- full dense vector
        "using": "full",
        "limit": 100
    },
    "query": [           // <─┐
        [0.1, 0.2, ...], // < │
        [0.2, 0.1, ...], // < ├─ multi-vector
        [0.8, 0.9, ...]  // < │
    ],                   // <─┘       
    "using": "colbert",
    "limit": 10
}

from qdrant_client import QdrantClient, models

client = QdrantClient(url="http://localhost:6333")

client.query_points(
    collection_name="{collection_name}",
    prefetch=models.Prefetch(
        prefetch=models.Prefetch(
            query=[1, 23, 45, 67],  # <------ small byte vector
            using="mrl_byte",
            limit=1000,
        ),
        query=[0.01, 0.45, 0.67],  # <-- full dense vector
        using="full",
        limit=100,
    ),
    query=[
        [0.17, 0.23, 0.52],  # <─┐
        [0.22, 0.11, 0.63],  # < ├─ multi-vector
        [0.86, 0.93, 0.12],  # < ┘
    ],
    using="colbert",
    limit=10,
)

import { QdrantClient } from "@qdrant/js-client-rest";

const client = new QdrantClient({ host: "localhost", port: 6333 });

client.query("{collection_name}", {
  prefetch: {
    prefetch: {
      query: [1, 23, 45, 67], // <------------- small byte vector
      using: 'mrl_byte',
      limit: 1000,
    },
    query: [0.01, 0.45, 0.67],  // <-- full dense vector
    using: 'full',
    limit: 100,
  },
  query: [
    [0.1, 0.2], // <─┐
    [0.2, 0.1], // < ├─ multi-vector
    [0.8, 0.9], // < ┘
  ],
  using: 'colbert',
  limit: 10,
});

use qdrant_client::Qdrant;
use qdrant_client::qdrant::{PrefetchQueryBuilder, Query, QueryPointsBuilder};

let client = Qdrant::from_url("http://localhost:6334").build()?;

client.query(
    QueryPointsBuilder::new("{collection_name}")
        .add_prefetch(PrefetchQueryBuilder::default()
            .add_prefetch(PrefetchQueryBuilder::default()
                .query(Query::new_nearest(vec![1.0, 23.0, 45.0, 67.0]))
                .using("mlr_byte")
                .limit(1000u64)
            )
            .query(Query::new_nearest(vec![0.01, 0.45, 0.67]))
            .using("full")
            .limit(100u64)
        )
        .query(Query::new_nearest(vec![
            vec![0.1, 0.2],
            vec![0.2, 0.1],
            vec![0.8, 0.9],
        ]))
        .using("colbert")
        .limit(10u64)
).await?;

import static io.qdrant.client.QueryFactory.nearest;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Points.PrefetchQuery;
import io.qdrant.client.grpc.Points.QueryPoints;

QdrantClient client =
    new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client
    .queryAsync(
        QueryPoints.newBuilder()
            .setCollectionName("{collection_name}")
            .addPrefetch(
                PrefetchQuery.newBuilder()
                    .addPrefetch(
                        PrefetchQuery.newBuilder()
                            .setQuery(nearest(1, 23, 45, 67))	// <------------- small byte vector
                            .setUsing("mrl_byte")
                            .setLimit(1000)
                            .build())
                    .setQuery(nearest(0.01f, 0.45f, 0.67f)) // <-- dense vector
                    .setUsing("full")
                    .setLimit(100)
                    .build())
            .setQuery(
                nearest(
                    new float[][] {
                      {0.1f, 0.2f},	// <─┐
                      {0.2f, 0.1f},	// < ├─ multi-vector
                      {0.8f, 0.9f}	// < ┘
                    }))
            .setUsing("colbert")
            .setLimit(10)
            .build())
    .get();

using Qdrant.Client;
using Qdrant.Client.Grpc;

var client = new QdrantClient("localhost", 6334);

await client.QueryAsync(
  collectionName: "{collection_name}",
  prefetch: new List <PrefetchQuery> {
    new() {
      Prefetch = {
          new List <PrefetchQuery> {
            new() {
              Query = new float[] { 1, 23, 45, 67 }, // <------------- small byte vector
                Using = "mrl_byte",
                Limit = 1000
            },
          }
        },
        Query = new float[] {0.01f, 0.45f, 0.67f}, // <-- dense vector
        Using = "full",
        Limit = 100
    }
  },
  query: new float[][] {
    [0.1f, 0.2f], // <─┐
    [0.2f, 0.1f], // < ├─ multi-vector
    [0.8f, 0.9f]  // < ┘
  },
  usingVector: "colbert",
  limit: 10
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.Query(context.Background(), &qdrant.QueryPoints{
	CollectionName: "{collection_name}",
	Prefetch: []*qdrant.PrefetchQuery{
		{
			Prefetch: []*qdrant.PrefetchQuery{
				{
					Query: qdrant.NewQueryDense([]float32{1, 23, 45, 67}),
					Using: qdrant.PtrOf("mrl_byte"),
					Limit: qdrant.PtrOf(uint64(1000)),
				},
			},
			Query: qdrant.NewQueryDense([]float32{0.01, 0.45, 0.67}),
			Limit: qdrant.PtrOf(uint64(100)),
			Using: qdrant.PtrOf("full"),
		},
	},
	Query: qdrant.NewQueryMulti([][]float32{
		{0.1, 0.2},
		{0.2, 0.1},
		{0.8, 0.9},
	}),
	Using: qdrant.PtrOf("colbert"),
})

Custom Scoring with a Formula Query

Available as of v1.14.0

A formula query lets you compose a final score from prefetch scores ($score), payload fields, and built-in helpers like exponential or Gaussian decay. The typical pattern is to fuse retrievers with RRF or DBSF in a prefetch, then wrap that prefetch in a formula query that layers ranking logic on top: recency decay, popularity boosts, geo decay, or category-conditional multipliers.

httppythontypescriptrustjavacsharpgo

POST /collections/{collection_name}/points/query
{
    "prefetch": {
        "prefetch": [
            {
                "query": {
                    "indices": [1, 42],    // <┐
                    "values": [0.22, 0.8]  // <┴─sparse vector
                },
                "using": "sparse",
                "limit": 100
            },
            {
                "query": [0.01, 0.45, 0.67, ...], // <-- dense vector
                "using": "dense",
                "limit": 100
            }
        ],
        "query": { "rrf": {} },
        "limit": 100
    },
    "query": {
        "formula": {
            "sum": [
                "$score", // the fused score from the RRF prefetch
                {
                    "mult": [
                        0.1, // caps decay contribution
                        {
                            "exp_decay": {
                                "x": {
                                    "datetime_key": "published_at"
                                },
                                "target": {
                                    "datetime": "YYYY-MM-DDT00:00:00Z"
                                },
                                "scale": 15552000, // 180 days in seconds
                                "midpoint": 0.5
                            }
                        }
                    ]
                }
            ]
        }
    },
    "limit": 10
}

from qdrant_client import QdrantClient, models

client = QdrantClient(url="http://localhost:6333")

client.query_points(
    collection_name="{collection_name}",
    prefetch=models.Prefetch(
        prefetch=[
            models.Prefetch(
                query=models.SparseVector(indices=[1, 42], values=[0.22, 0.8]),
                using="sparse",
                limit=100,
            ),
            models.Prefetch(
                query=[0.01, 0.45, 0.67],  # <-- dense vector
                using="dense",
                limit=100,
            ),
        ],
        query=models.RrfQuery(rrf=models.Rrf()),
        limit=100,
    ),
    query=models.FormulaQuery(
        formula=models.SumExpression(
            sum=[
                "$score",  # the fused score from the RRF prefetch
                models.MultExpression(mult=[
                    0.1,  # caps decay contribution; un-weighted decay [0, 1] would otherwise crowd out small RRF scores
                    models.ExpDecayExpression(
                        exp_decay=models.DecayParamsExpression(
                            x=models.DatetimeKeyExpression(datetime_key="published_at"),
                            target=models.DatetimeExpression(datetime="YYYY-MM-DDT00:00:00Z"),
                            scale=86400 * 180,  # 180 days in seconds
                            midpoint=0.5,
                        )
                    ),
                ]),
            ]
        )
    ),
    limit=10,
)

import { QdrantClient } from "@qdrant/js-client-rest";

const client = new QdrantClient({ host: "localhost", port: 6333 });

await client.query("{collection_name}", {
    prefetch: {
        prefetch: [
            {
                query: {
                    values: [0.22, 0.8],
                    indices: [1, 42],
                },
                using: "sparse",
                limit: 100,
            },
            {
                query: [0.01, 0.45, 0.67], // <-- dense vector
                using: "dense",
                limit: 100,
            },
        ],
        query: { rrf: {} },
        limit: 100,
    },
    query: {
        formula: {
            sum: [
                "$score", // the fused score from the RRF prefetch
                {
                    mult: [
                        0.1, // caps decay contribution; un-weighted decay [0, 1] would otherwise crowd out small RRF scores
                        {
                            exp_decay: {
                                x: { datetime_key: "published_at" },
                                target: { datetime: "YYYY-MM-DDT00:00:00Z" },
                                scale: 86400 * 180, // 180 days in seconds
                                midpoint: 0.5,
                            },
                        },
                    ],
                },
            ],
        },
    },
    limit: 10,
});

use qdrant_client::Qdrant;
use qdrant_client::qdrant::{
    DecayParamsExpressionBuilder, Expression, FormulaBuilder, PrefetchQueryBuilder, Query,
    QueryPointsBuilder, RrfBuilder,
};

let client = Qdrant::from_url("http://localhost:6334").build()?;

client.query(
    QueryPointsBuilder::new("{collection_name}")
        .add_prefetch(
            PrefetchQueryBuilder::default()
                .add_prefetch(
                    PrefetchQueryBuilder::default()
                        .query(Query::new_nearest([(1, 0.22), (42, 0.8)].as_slice()))
                        .using("sparse")
                        .limit(100u64),
                )
                .add_prefetch(
                    PrefetchQueryBuilder::default()
                        .query(Query::new_nearest(vec![0.01, 0.45, 0.67]))
                        .using("dense")
                        .limit(100u64),
                )
                .query(Query::new_rrf(RrfBuilder::default()))
                .limit(100u64),
        )
        .query(
            FormulaBuilder::new(Expression::sum_with([
                Expression::score(),
                Expression::mult_with([
                    Expression::constant(0.1),
                    Expression::exp_decay(
                        DecayParamsExpressionBuilder::new(Expression::datetime_key("published_at"))
                            .target(Expression::datetime("YYYY-MM-DDT00:00:00Z"))
                            .scale(86400.0 * 180.0)
                            .midpoint(0.5),
                    ),
                ]),
            ])),
        )
        .limit(10u64),
)
.await?;

import static io.qdrant.client.ExpressionFactory.constant;
import static io.qdrant.client.ExpressionFactory.datetime;
import static io.qdrant.client.ExpressionFactory.datetimeKey;
import static io.qdrant.client.ExpressionFactory.expDecay;
import static io.qdrant.client.ExpressionFactory.mult;
import static io.qdrant.client.ExpressionFactory.sum;
import static io.qdrant.client.ExpressionFactory.variable;
import static io.qdrant.client.QueryFactory.formula;
import static io.qdrant.client.QueryFactory.nearest;
import static io.qdrant.client.QueryFactory.rrf;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Points.DecayParamsExpression;
import io.qdrant.client.grpc.Points.Formula;
import io.qdrant.client.grpc.Points.MultExpression;
import io.qdrant.client.grpc.Points.PrefetchQuery;
import io.qdrant.client.grpc.Points.QueryPoints;
import io.qdrant.client.grpc.Points.Rrf;
import io.qdrant.client.grpc.Points.SumExpression;
import java.util.List;

QdrantClient client =
  new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client.queryAsync(
    QueryPoints.newBuilder()
        .setCollectionName("{collection_name}")
        .addPrefetch(
            PrefetchQuery.newBuilder()
                .addPrefetch(
                    PrefetchQuery.newBuilder()
                        .setQuery(nearest(List.of(0.22f, 0.8f), List.of(1, 42)))
                        .setUsing("sparse")
                        .setLimit(100)
                        .build())
                .addPrefetch(
                    PrefetchQuery.newBuilder()
                        .setQuery(nearest(List.of(0.01f, 0.45f, 0.67f)))
                        .setUsing("dense")
                        .setLimit(100)
                        .build())
                .setQuery(rrf(Rrf.newBuilder().build()))
                .setLimit(100)
                .build())
        .setQuery(
            formula(
                Formula.newBuilder()
                    .setExpression(
                        sum(
                            SumExpression.newBuilder()
                                .addSum(variable("$score"))
                                .addSum(
                                    mult(
                                        MultExpression.newBuilder()
                                            .addMult(constant(0.1f))
                                            .addMult(
                                                expDecay(
                                                    DecayParamsExpression.newBuilder()
                                                        .setX(datetimeKey("published_at"))
                                                        .setTarget(
                                                            datetime("YYYY-MM-DDT00:00:00Z"))
                                                        .setScale(86400 * 180)
                                                        .setMidpoint(0.5f)
                                                        .build()))
                                            .build()))
                                .build()))
                    .build()))
        .setLimit(10)
        .build())
  .get();

using Qdrant.Client;
using Qdrant.Client.Grpc;

var client = new QdrantClient("localhost", 6334);

await client.QueryAsync(
    collectionName: "{collection_name}",
    prefetch:
    [
        new PrefetchQuery {
            Prefetch = {
                new PrefetchQuery {
                    Query = new(float, uint)[] { (0.22f, 1), (0.8f, 42) },
                    Using = "sparse",
                    Limit = 100
                },
                new PrefetchQuery {
                    Query = new float[] { 0.01f, 0.45f, 0.67f },
                    Using = "dense",
                    Limit = 100
                },
            },
            Query = new Rrf(),
            Limit = 100
        },
    ],
    query: new Formula
    {
        Expression = new SumExpression
        {
            Sum =
            {
                "$score", // the fused score from the RRF prefetch
                new MultExpression
                {
                    Mult =
                    {
                        0.1f, // caps decay contribution
                        Expression.FromExpDecay(
                            new()
                            {
                                X = Expression.FromDateTimeKey("published_at"),
                                Target = Expression.FromDateTime("YYYY-MM-DDT00:00:00Z"),
                                Scale = 86400 * 180, // 180 days in seconds
                                Midpoint = 0.5f
                            }
                        )
                    }
                }
            }
        }
    },
    limit: 10
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.Query(context.Background(), &qdrant.QueryPoints{
	CollectionName: "{collection_name}",
	Prefetch: []*qdrant.PrefetchQuery{
		{
			Prefetch: []*qdrant.PrefetchQuery{
				{
					Query: qdrant.NewQuerySparse([]uint32{1, 42}, []float32{0.22, 0.8}),
					Using: qdrant.PtrOf("sparse"),
					Limit: qdrant.PtrOf(uint64(100)),
				},
				{
					Query: qdrant.NewQueryDense([]float32{0.01, 0.45, 0.67}),
					Using: qdrant.PtrOf("dense"),
					Limit: qdrant.PtrOf(uint64(100)),
				},
			},
			Query: qdrant.NewQueryRRF(&qdrant.Rrf{}),
			Limit: qdrant.PtrOf(uint64(100)),
		},
	},
	Query: qdrant.NewQueryFormula(&qdrant.Formula{
		Expression: qdrant.NewExpressionSum(&qdrant.SumExpression{
			Sum: []*qdrant.Expression{
				qdrant.NewExpressionVariable("$score"), // the fused score from the RRF prefetch
				qdrant.NewExpressionMult(&qdrant.MultExpression{
					Mult: []*qdrant.Expression{
						qdrant.NewExpressionConstant(0.1), // caps decay contribution
						qdrant.NewExpressionExpDecay(&qdrant.DecayParamsExpression{
							X:        qdrant.NewExpressionDatetimeKey("published_at"),
							Target:   qdrant.NewExpressionDatetime("YYYY-MM-DDT00:00:00Z"),
							Scale:    qdrant.PtrOf(float32(86400 * 180)), // 180 days in seconds
							Midpoint: qdrant.PtrOf(float32(0.5)),
						}),
					},
				}),
			},
		}),
	}),
	Limit: qdrant.PtrOf(uint64(10)),
})

Calibrate the decay weight against the scale of your fused $score. RRF scores are small (sums of 1/(k+rank) terms), while decay functions return values in [0, 1], so an unweighted decay term will dominate the fused score unless you multiply it by a smaller coefficient. Wrap the decay in a multiplication expression with a coefficient tuned to your workload.

The Choosing a Fusion Method notebook shows this pattern end-to-end with exponential decay on a published_at payload field. For full formula query and decay function syntax, see the Search Relevance reference.

Grouping

Available as of v1.11.0

It is possible to group results by a certain field. This is useful when you have multiple points for the same item, and you want to avoid redundancy of the same item in the results.

REST API (Schema):

httppythontypescriptrustjavacsharpgo

POST /collections/{collection_name}/points/query/groups
{
    // Same as in the regular query API
    "query": [1.1],
    // Grouping parameters
    "group_by": "document_id",  // Path of the field to group by
    "limit": 4,                 // Max amount of groups
    "group_size": 2            // Max amount of points per group
}

client.query_points_groups(
    collection_name="{collection_name}",
    # Same as in the regular query_points() API
    query=[1.1],
    # Grouping parameters
    group_by="document_id",  # Path of the field to group by
    limit=4,  # Max amount of groups
    group_size=2,  # Max amount of points per group
)

client.queryGroups("{collection_name}", {
    query: [1.1],
    group_by: "document_id",
    limit: 4,
    group_size: 2,
});

use qdrant_client::qdrant::QueryPointGroupsBuilder;

client
    .query_groups(
        QueryPointGroupsBuilder::new("{collection_name}", "document_id")
            .query(vec![0.2, 0.1, 0.9, 0.7])
            .group_size(2u64)
            .with_payload(true)
            .with_vectors(true)
            .limit(4u64),
    )
    .await?;

import static io.qdrant.client.QueryFactory.nearest;

import io.qdrant.client.grpc.Points.QueryPointGroups;
import io.qdrant.client.grpc.Points.SearchPointGroups;
import java.util.List;

client.queryGroupsAsync(
        QueryPointGroups.newBuilder()
                .setCollectionName("{collection_name}")
                .setQuery(nearest(0.2f, 0.1f, 0.9f, 0.7f))
                .setGroupBy("document_id")
                .setLimit(4)
                .setGroupSize(2)
                .build())
        .get();

using Qdrant.Client;

var client = new QdrantClient("localhost", 6334);

await client.QueryGroupsAsync(
    collectionName: "{collection_name}",
    query: new float[] { 0.2f, 0.1f, 0.9f, 0.7f },
    groupBy: "document_id",
    limit: 4,
    groupSize: 2
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.QueryGroups(context.Background(), &qdrant.QueryPointGroups{
	CollectionName: "{collection_name}",
	Query:          qdrant.NewQuery(0.2, 0.1, 0.9, 0.7),
	GroupBy:        "document_id",
	GroupSize:      qdrant.PtrOf(uint64(2)),
})

For more information on the grouping capabilities refer to the reference documentation for search with grouping and lookup.

See also: the Multi-Representation Search tutorial for a worked end-to-end example of grouping in a hybrid retrieval pipeline.

Hybrid and Multi-Stage Queries

Hybrid Search

Reciprocal Rank Fusion (RRF)

Setting RRF Constant k

Weighted RRF

Distribution-Based Score Fusion (DBSF)

Choosing a Fusion Method

Multi-Stage Queries

Re-Scoring Examples

Custom Scoring with a Formula Query

Grouping

Was this page useful?

About cookies on this site

Targeting Cookies

Functional Cookies

Strictly Necessary Cookies

Performance Cookies