Multiple target vectors

In a multi-target vector search, Weaviate searches multiple target vector spaces concurrently. These results are combined using a "join strategy" to produce a single set of search results.

There are multiple ways to specify the target vectors and query vectors, such as:

Specify target vector names only
Specify query vectors
Specify target vector names and join strategy
Weight raw vector distances
Weight normalized vector distances

Multi-target vector search is available for near_xxx queries (from v1.26), as well as hybrid queries (from v1.27).

Available join strategies.

minimum (default) Use the minimum of all vector distances.
sum Use the sum of the vector distances.
average Use the average of the vector distances.
manual weights Use the sum of weighted distances, where the weight is provided for each target vector.
relative score Use the sum of weighted normalized distances, where the weight is provided for each target vector.

Specify target vector names only

As a minimum, specify the target vector names as an array of named vectors. This will use the default join strategy.

Python

from weaviate.classes.query import MetadataQuerycollection = client.collections.use("JeopardyTiny")response = collection.query.near_text(    query="a wild animal",    limit=2,    target_vector=["jeopardy_questions_vector", "jeopardy_answers_vector"],  # Specify the target vectors    return_metadata=MetadataQuery(distance=True))for o in response.objects:    print(o.properties)    return_metadata=MetadataQuery(distance=True)

TypeScript

jeopardy = client.collections.use('JeopardyTiny');result = await jeopardy.query.nearText('a wild animal', {  limit: 2,  targetVector: ['jeopardy_questions_vector', 'jeopardy_answers_vector'],  returnMetadata: ['distance'],});result.objects.forEach((item) => {  console.log(JSON.stringify(item.properties, null, 2));  console.log(JSON.stringify(item.metadata?.distance, null, 2));});

concepts := []string{"a wild animal"}
nearText := client.GraphQL().NearTextArgBuilder().
  WithConcepts(concepts).
  WithTargetVectors("jeopardy_questions_vector", "jeopardy_answers_vector")

ctx := context.Background()

result, err := client.GraphQL().Get().
WithClassName(className).
WithFields(graphql.Field{Name: "question"}, graphql.Field{Name: "answer"}).
WithNearText(nearText).
Do(ctx)

Complete code

package main

import (
  "context"
  "fmt"
  "os"

  "github.com/weaviate/weaviate-go-client/v5/weaviate"
  "github.com/weaviate/weaviate-go-client/v5/weaviate/graphql"
)

func main() {
  cfg := weaviate.Config{
    Host:   "localhost:8080",
    Scheme: "http",
    Headers: map[string]string{
      "X-Openai-Api-Key": os.Getenv("OPENAI_API_KEY"),
    },
  }

  client, err := weaviate.NewClient(cfg)
  if err != nil {
    panic(err)
  }

  className := "JeopardyTiny"

Java

CollectionHandle<Map<String, Object>> collection =    client.collections.use(COLLECTION_NAME);var response = collection.query.nearText(    // In Java, a plain list of target vectors implies an "average" strategy    Target.average("a wild animal", "jeopardy_questions_vector",        "jeopardy_answers_vector"),    q -> q.limit(2).returnMetadata(Metadata.DISTANCE));for (var o : response.objects()) {  System.out.println(objectMapper.writerWithDefaultPrettyPrinter()      .writeValueAsString(o.properties()));  System.out.println("Distance: " + o.queryMetadata().distance());}

var collection = client.Collections.Use(CollectionName);var response = await collection.Query.NearText(    query =>        query(["a wild animal"])            .TargetVectorsMinimum("jeopardy_questions_vector", "jeopardy_answers_vector"), // Specify the target vectors    limit: 2,    returnMetadata: MetadataOptions.Distance);foreach (var o in response.Objects){    Console.WriteLine(JsonSerializer.Serialize(o.Properties));    Console.WriteLine(o.Metadata.Distance);}

Specify query vectors

You can specify multiple query vectors in the search query with a nearVector search. This allows use of a different query vector for each corresponding target vector.

Python

from weaviate.classes.query import MetadataQuerycollection = client.collections.use("JeopardyTiny")response = collection.query.near_vector(    # Specify the query vectors for each target vector    near_vector={        "jeopardy_questions_vector": v1,        "jeopardy_answers_vector": v2,    },    limit=2,    target_vector=["jeopardy_questions_vector", "jeopardy_answers_vector"],  # Specify the target vectors    return_metadata=MetadataQuery(distance=True))for o in response.objects:    print(o.properties)    return_metadata=MetadataQuery(distance=True)

JavaScript/TypeScript

jeopardy = client.collections.use('JeopardyTiny');result = await jeopardy.query.nearVector({  'jeopardy_questions_vector': v1,  'jeopardy_answers_vector': v2}, {  limit: 2,  targetVector: ['jeopardy_questions_vector', 'jeopardy_answers_vector'],  returnMetadata: ['distance'],});result.objects.forEach((item) => {  console.log(JSON.stringify(item.properties, null, 2));  console.log(JSON.stringify(item.metadata?.distance, null, 2));});

Java

var response = collection.query.nearVector(    // Specify the query vectors for each target vector using Target objects    // The default combination strategy is "average"    Target.average(Target.vector("jeopardy_questions_vector", v1),        Target.vector("jeopardy_answers_vector", v2)),    q -> q.limit(2).returnMetadata(Metadata.DISTANCE));for (var o : response.objects()) {  System.out.println(objectMapper.writerWithDefaultPrettyPrinter()      .writeValueAsString(o.properties()));  System.out.println("Distance: " + o.queryMetadata().distance());}

var response = await collection.Query.NearVector(    // Specify the query vectors for each target vector    vectors: new Vectors    {        { "jeopardy_questions_vector", v1 },        { "jeopardy_answers_vector", v2 },    },    limit: 2,    returnMetadata: MetadataOptions.Distance);foreach (var o in response.Objects){    Console.WriteLine(JsonSerializer.Serialize(o.Properties));    Console.WriteLine(o.Metadata.Distance);}

You can also specify the query vectors as an array of vectors. The array will be parsed according to the order of the specified target vectors.

Specify array(s) of query vectors

You can also specify the same target vector multiple times with different query vectors. In other words, you can use multiple query vectors for the same target vector.

The query vectors in this case are specified as an array of vectors. There are multiple ways to specify the target vectors in this case:

Target vector names only

The target vectors can be specified as an array as shown here.

Python

from weaviate.classes.query import MetadataQuerycollection = client.collections.use("JeopardyTiny")response = collection.query.near_vector(    # Specify the query vectors for each target vector    near_vector={        "jeopardy_questions_vector": v1,        "jeopardy_answers_vector": [v2, v3]    },    limit=2,    # Specify the target vectors as a list    target_vector=[        "jeopardy_questions_vector",        "jeopardy_answers_vector",    ],    return_metadata=MetadataQuery(distance=True))for o in response.objects:    print(o.properties)    return_metadata=MetadataQuery(distance=True)

JavaScript/TypeScript

jeopardy = client.collections.use('JeopardyTiny');result = await jeopardy.query.nearVector({  // Specify the query vectors for each target vector. where v1, v2.. are vectors  'jeopardy_questions_vector': v1,  'jeopardy_answers_vector': [v2, v3]}, {  limit: 2,  // Specify the target vectors as a list  targetVector: ['jeopardy_questions_vector', 'jeopardy_answers_vector'],  returnMetadata: ['distance'],});result.objects.forEach((item) => {  console.log(JSON.stringify(item.properties, null, 2));  console.log(JSON.stringify(item.metadata?.distance, null, 2));});

Java

var responseV1 = collection.query.nearVector(    // Pass multiple Target.vector objects with the same name    // The default combination strategy is "average"    Target.average(Target.vector("jeopardy_questions_vector", v1),        Target.vector("jeopardy_answers_vector", v2),        Target.vector("jeopardy_answers_vector", v3)),    q -> q.limit(2).returnMetadata(Metadata.DISTANCE));for (var o : responseV1.objects()) {  System.out.println(objectMapper.writerWithDefaultPrettyPrinter()      .writeValueAsString(o.properties()));  System.out.println("Distance: " + o.queryMetadata().distance());}

var response = await collection.Query.NearVector(    // Use NearVectorInput to pass multiple vectors naturally    vectors: v =>        v.TargetVectorsSum(            ("jeopardy_questions_vector", v1),            ("jeopardy_answers_vector", v2),            ("jeopardy_answers_vector", v3)        ),    limit: 2,    returnMetadata: MetadataOptions.Distance);

Target vectors and weights

If you want to provide weights for each target vector you can do it as shown here.

Python

from weaviate.classes.query import TargetVectors, MetadataQuerycollection = client.collections.use("JeopardyTiny")response = collection.query.near_vector(    # Specify the query vectors for each target vector    near_vector={        "jeopardy_questions_vector": v1,        "jeopardy_answers_vector": [v2, v3]    },    limit=2,    # Specify the target vectors and weights    target_vector=TargetVectors.manual_weights({        "jeopardy_questions_vector": 10,        "jeopardy_answers_vector": [30, 30],  # Matches the order of the vectors above    }),    return_metadata=MetadataQuery(distance=True))for o in response.objects:    print(o.properties)    return_metadata=MetadataQuery(distance=True)

JavaScript/TypeScript

jeopardy = client.collections.use('JeopardyTiny');result = await jeopardy.query.nearVector({  'jeopardy_questions_vector': v1,  'jeopardy_answers_vector': [v2, v3]}, {  limit: 2,  // Specify the target vectors as a list  targetVector: jeopardy.multiTargetVector.manualWeights({    "jeopardy_questions_vector": 10,    "jeopardy_answers_vector": [30, 30], // Matches the order of the vectors above  }),  returnMetadata: ['distance'],});result.objects.forEach((item) => {  console.log(JSON.stringify(item.properties, null, 2));  console.log(JSON.stringify(item.metadata?.distance, null, 2));});

Java

var responseV2 = collection.query.nearVector(    // Specify weights for each vector    Target.manualWeights(        Target.vector("jeopardy_questions_vector", 10f, v1),        Target.vector("jeopardy_answers_vector", 30f, v2),        Target.vector("jeopardy_answers_vector", 30f, v3) // Weights match the vectors    ),    q -> q.limit(2).returnMetadata(Metadata.DISTANCE));for (var o : responseV2.objects()) {  System.out.println(objectMapper.writerWithDefaultPrettyPrinter()      .writeValueAsString(o.properties()));  System.out.println("Distance: " + o.queryMetadata().distance());}

var responseV2 = await collection.Query.NearVector(    vectors: v =>        v.TargetVectorsManualWeights(            ("jeopardy_questions_vector", 10, v1),            ("jeopardy_answers_vector", 30, v2),            ("jeopardy_answers_vector", 30, v3)        ),    limit: 2,    returnMetadata: MetadataOptions.Distance);

Specify target vector names and join strategy

Specify target vectors as an array of named vectors and how to join the result sets.

The sum, average, minimum join strategies only require the name of the strategy and the target vectors.

Python

from weaviate.classes.query import TargetVectors, MetadataQuerycollection = client.collections.use("JeopardyTiny")response = collection.query.near_text(    query="a wild animal",    limit=2,    target_vector=TargetVectors.average(["jeopardy_questions_vector", "jeopardy_answers_vector"]),  # Specify the target vectors and the join strategy    # .sum(), .minimum(), .manual_weights(), .relative_score() also available    return_metadata=MetadataQuery(distance=True))for o in response.objects:    print(o.properties)    print(o.metadata.distance)

JavaScript/TypeScript

jeopardy = client.collections.use('JeopardyTiny');result = await jeopardy.query.nearText('a wild animal', {  limit: 2,  targetVector: jeopardy.multiTargetVector.average(['jeopardy_questions_vector', 'jeopardy_answers_vector']),  returnMetadata: ['distance'],});result.objects.forEach((item) => {  console.log(JSON.stringify(item.properties, null, 2));  console.log(JSON.stringify(item.metadata?.distance, null, 2));});

Java

CollectionHandle<Map<String, Object>> collection =    client.collections.use(COLLECTION_NAME);var response = collection.query.nearText(    Target.average("a wild animal", "jeopardy_questions_vector",        "jeopardy_answers_vector"), // Specify the target vectors and the join strategy    // .sum(), .min(), .manualWeights(), .relativeScore() also available    q -> q.limit(2).returnMetadata(Metadata.DISTANCE));for (var o : response.objects()) {  System.out.println(objectMapper.writerWithDefaultPrettyPrinter()      .writeValueAsString(o.properties()));  System.out.println("Distance: " + o.queryMetadata().distance());}

var collection = client.Collections.Use(CollectionName);var response = await collection.Query.NearText(    query =>        query(["a wild animal"])            // Specify the target vectors and the join strategy            // Available: Sum, Minimum, Average, ManualWeights, RelativeScore            .TargetVectorsAverage("jeopardy_questions_vector", "jeopardy_answers_vector"),    limit: 2,    returnMetadata: MetadataOptions.Distance);foreach (var o in response.Objects){    Console.WriteLine(JsonSerializer.Serialize(o.Properties));    Console.WriteLine(o.Metadata.Distance);}

Weight raw vector distances

Search by sums of weighted, raw distances to each target vector.

The weighting in detail

Each distance between the query vector and the target vector is multiplied by the specified weight, then the resulting weighted distances are summed for each object to produce a combined distance. The search results are sorted by this combined distance.

Python

from weaviate.classes.query import TargetVectors, MetadataQuerycollection = client.collections.use("JeopardyTiny")response = collection.query.near_text(    query="a wild animal",    limit=2,    target_vector=TargetVectors.manual_weights({        "jeopardy_questions_vector": 10,        "jeopardy_answers_vector": 50    }),    return_metadata=MetadataQuery(distance=True))for o in response.objects:    print(o.properties)    print(o.metadata.distance)

JavaScript/TypeScript

jeopardy = client.collections.use('JeopardyTiny');result = await jeopardy.query.nearText('a wild animal', {  limit: 2,  targetVector: jeopardy.multiTargetVector.manualWeights({    jeopardy_questions_vector: 10,    jeopardy_answers_vector: 50,  }),  returnMetadata: ['distance'],});result.objects.forEach((item) => {  console.log(JSON.stringify(item.properties, null, 2));  console.log(JSON.stringify(item.metadata?.distance, null, 2));});

Java

CollectionHandle<Map<String, Object>> collection =    client.collections.use(COLLECTION_NAME);var response = collection.query.nearText(    Target.manualWeights("a wild animal",        Target.weight("jeopardy_questions_vector", 10f),        Target.weight("jeopardy_answers_vector", 50f)),    q -> q.limit(2).returnMetadata(Metadata.DISTANCE));for (var o : response.objects()) {  System.out.println(objectMapper.writerWithDefaultPrettyPrinter()      .writeValueAsString(o.properties()));  System.out.println("Distance: " + o.queryMetadata().distance());}

var collection = client.Collections.Use(CollectionName);var response = await collection.Query.NearText(    query =>        query(["a wild animal"])            .TargetVectorsManualWeights(                ("jeopardy_questions_vector", 10),                ("jeopardy_answers_vector", 50)            ),    limit: 2,    returnMetadata: MetadataOptions.Distance);foreach (var o in response.Objects){    Console.WriteLine(JsonSerializer.Serialize(o.Properties));    Console.WriteLine(o.Metadata.Distance);}

Weight normalized vector distances

Search by sums of weighted, normalized distances to each target vector.

The weighting in detail

Each distance is normalized against other results for that target vector. Each normalized distance between the query vector and the target vector is multiplied by the specified weight. The resulting weighted distances are summed for each object to produce a combined distance. The search results are sorted by this combined distance.

For a more detailed explanation of how scores are normalized, see the blog post on hybrid relative score fusion

Python

from weaviate.classes.query import TargetVectors, MetadataQuerycollection = client.collections.use("JeopardyTiny")response = collection.query.near_text(    query="a wild animal",    limit=2,    target_vector=TargetVectors.relative_score({        "jeopardy_questions_vector": 10,        "jeopardy_answers_vector": 10    }),    return_metadata=MetadataQuery(distance=True))for o in response.objects:    print(o.properties)    print(o.metadata.distance)

JavaScript/TypeScript

jeopardy = client.collections.use('JeopardyTiny');result = await jeopardy.query.nearText('a wild animal', {  limit: 2,  targetVector: jeopardy.multiTargetVector.relativeScore({    jeopardy_questions_vector: 10,    jeopardy_answers_vector: 10,  }),  returnMetadata: ['distance'],});result.objects.forEach((item) => {  console.log(JSON.stringify(item.properties, null, 2));  console.log(JSON.stringify(item.metadata?.distance, null, 2));});

Java

CollectionHandle<Map<String, Object>> collection =    client.collections.use(COLLECTION_NAME);var response = collection.query.nearText(    Target.relativeScore("a wild animal",        Target.weight("jeopardy_questions_vector", 10f),        Target.weight("jeopardy_answers_vector", 10f)),    q -> q.limit(2).returnMetadata(Metadata.DISTANCE));for (var o : response.objects()) {  System.out.println(objectMapper.writerWithDefaultPrettyPrinter()      .writeValueAsString(o.properties()));  System.out.println("Distance: " + o.queryMetadata().distance());}

var collection = client.Collections.Use(CollectionName);var response = await collection.Query.NearText(    query =>        query(["a wild animal"])            .TargetVectorsRelativeScore(                ("jeopardy_questions_vector", 10),                ("jeopardy_answers_vector", 10)            ),    returnMetadata: MetadataOptions.Distance);foreach (var o in response.Objects){    Console.WriteLine(JsonSerializer.Serialize(o.Properties));    Console.WriteLine(o.Metadata.Distance);}

Connect to Weaviate

Questions and feedback

Have a question or feedback? Here's how to reach us.

Community Forum

Ask questions and connect with other developers on our Community forum.

Support

Weaviate Cloud user or customer? Find the right channel on the Support page.

Available join strategies.

Specify target vector names only

Specify query vectors

Specify array(s) of query vectors

Target vector names only

Target vectors and weights

Specify target vector names and join strategy

Weight raw vector distances

Weight normalized vector distances

Related pages

Questions and feedback