Text Embeddings

Access to Weaviate Embeddings during technical preview

Weaviate Embeddings is currently in free technical preview.

To try out Weaviate Embeddings at this time, please contact us to request access.

Weaviate Embeddings

Weaviate Embeddings' models can be accessed directly from a Weaviate Cloud instance.

Configure a Weaviate vector index to use a Weaviate Embeddings model, and Weaviate will generate embeddings for various operations using the specified model and your Weaviate API key. This feature is called the vectorizer.

At import time, Weaviate generates text object embeddings and saves them into the index. For vector and hybrid search operations, Weaviate converts text queries into embeddings.

Requirements

To use Weaviate Embeddings, you need:

• A Weaviate Cloud instance running at least Weaviate 1.27.6
• To have enabled "Weaviate Embeddings" in your Weaviate Cloud organisation
• A Weaviate client library that supports Weaviate Embeddings:
  • Python client version 4.9.5 or higher
  • JavaScript/TypeScript client version 3.2.5 or higher
  • Go/Java clients are not yet officially supported; you must pass the X-Weaviate-Api-Key and X-Weaviate-Cluster-Url headers manually upon instantiation as shown below.

Weaviate configuration

The Weaviate Embeddings vectorizer is only available for use by Weaviate Cloud instances. At this time, Weaviate Embeddings is not available for self-hosted users.

API credentials

Weaviate Embeddings is integrated with Weaviate Cloud. Your Weaviate Cloud credentials will be used to authorize your Weaviate Cloud instance's access for Weaviate Embeddings.

Python API v4

import weaviate
from weaviate.classes.init import Auth
import os

client = weaviate.connect_to_weaviate_cloud(
    cluster_url=weaviate_url,                       # `weaviate_url`: your Weaviate URL
    auth_credentials=Auth.api_key(weaviate_key),    # `weaviate_key`: your Weaviate API key
)

# Work with Weaviate

client.close()

  API docs

JS/TS API v3

import weaviate from 'weaviate-client'

const client = await weaviate.connectToWeaviateCloud(
  'WEAVIATE_INSTANCE_URL',  // Replace with your instance URL
  {
    authCredentials: new weaviate.ApiKey('WEAVIATE_INSTANCE_APIKEY'),
  }
)

// Work with Weaviate

client.close()

  API docs

Go

// Set these environment variables
// WCD_HOSTNAME            your Weaviate instance hostname
// WCD_API_KEY          your Weaviate instance API key

package main

import (
    "context"
    "fmt"
    "os"

    "github.com/weaviate/weaviate-go-client/v4/weaviate"
    "github.com/weaviate/weaviate-go-client/v4/weaviate/auth"
)

func main() {
    cfg := weaviate.Config{
        Host:       os.Getenv("WCD_W_EMB_HOSTNAME"),
        Scheme:     "https",
        AuthConfig: auth.ApiKey{Value: os.Getenv("WCD_W_EMB_API_KEY")},
        Headers: map[string]string{
            "X-Weaviate-Api-Key":     os.Getenv("WCD_W_EMB_API_KEY"),
            "X-Weaviate-Cluster-Url": fmt.Sprintf("https://%s", os.Getenv("WCD_W_EMB_HOSTNAME")),
        },
    }

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

    // Work with Weaviate
}

  API docs

Java

import io.weaviate.client.Config;
import io.weaviate.client.WeaviateAuthClient;
import io.weaviate.client.WeaviateClient;
import io.weaviate.client.base.Result;

import static org.assertj.core.api.Assertions.assertThat;

// Set these environment variables
// WCD_HOSTNAME         Your Weaviate instance hostname
// WCD_API_KEY          Your Weaviate instance API key

public class ConnectWeaviateEmbeddings {
  public static void main(String[] args) throws Exception {

    String host = System.getenv("WCD_W_EMB_HOSTNAME");
    String apiKey = System.getenv("WCD_W_EMB_API_KEY");

    Map<String, String> headers = new HashMap<String, String>() { {
      put("X-Weaviate-Api-Key", apiKey);
      put("X-Weaviate-Cluster-Url", "https://" + System.getenv("WCD_W_EMB_HOSTNAME"));
    } };

    Config config = new Config("https", host, headers);
    WeaviateClient client = WeaviateAuthClient.apiKey(config, apiKey);

    // check the result
    Result<Boolean> result = client.misc().readyChecker().run();
    System.out.println(result.getResult());

  }
}

  API docs

Configure the vectorizer

Configure a Weaviate index as follows to use a Weaviate Embeddings model:

Python API v4

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    vectorizer_config=[
        Configure.NamedVectors.text2vec_weaviate(
            name="title_vector",
            source_properties=["title"]
        )
    ],
    # Additional parameters not shown
)

  API docs

JS/TS API v3

await client.collections.create({
  name: 'DemoCollection',
  properties: [
    {
      name: 'title',
      dataType: 'text' as const,
    },
  ],
  vectorizers: [
    weaviate.configure.vectorizer.text2VecWeaviate({
        name: 'title_vector',
        sourceProperties: ['title'],
      },
    ),
  ],
  // Additional parameters not shown
});

  API docs

Go

// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    // Define the collection
    basicWeaviateVectorizerDef := &models.Class{
        Class: "DemoCollection",
        VectorConfig: map[string]models.VectorConfig{
            "title_vector": {
                Vectorizer: map[string]interface{}{
                    "text2vec-weaviate": map[string]interface{}{},
                },
            },
        },
    }

    // add the collection
    err = client.Schema().ClassCreator().WithClass(basicWeaviateVectorizerDef).Do(ctx)
    if err != nil {
        panic(err)
    }
}

  API docs

Java

Map<String, Object> text2vecWeaviate = new HashMap<>();
Map<String, Object> text2vecWeaviateSettings = new HashMap<>();

text2vecWeaviateSettings.put("properties", new String[]{"title"});
text2vecWeaviate.put("text2vec-weaviate", text2vecWeaviateSettings);

// Define the vector configurations
Map<String, WeaviateClass.VectorConfig> vectorConfig = new HashMap<>();
vectorConfig.put("title_vector", WeaviateClass.VectorConfig.builder()
  .vectorIndexType("hnsw")
  .vectorizer(text2vecWeaviate)
  .build());

// Create the collection "DemoCollection"
WeaviateClass clazz = WeaviateClass.builder()
  .className("DemoCollection")
  .vectorConfig(vectorConfig)
  .build();

Result<Boolean> result = client.schema().classCreator().withClass(clazz).run();

  API docs

Select a model

You can specify one of the available models for the vectorizer to use, as shown in the following configuration example.

Python API v4

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    vectorizer_config=[
        Configure.NamedVectors.text2vec_weaviate(
            name="title_vector",
            source_properties=["title"],
            model="arctic-embed-m-v1.5"
        )
    ],
    # Additional parameters not shown
)

  API docs

JS/TS API v3

await client.collections.create({
  name: 'DemoCollection',
  properties: [
    {
      name: 'title',
      dataType: 'text' as const,
    },
  ],
  vectorizers: [
    weaviate.configure.vectorizer.text2VecWeaviate({
      name: 'title_vector',
      sourceProperties: ['title'],
      model: 'arctic-embed-m-v1.5',
    }),
  ],
  // Additional parameters not shown
});

  API docs

Go

// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    // Define the collection
    weaviateVectorizerWithModelDef := &models.Class{
        Class: "DemoCollection",
        VectorConfig: map[string]models.VectorConfig{
            "title_vector": {
                Vectorizer: map[string]interface{}{
                    "text2vec-weaviate": map[string]interface{}{
                        "model": "arctic-embed-m-v1.5",
                    },
                },
            },
        },
    }

    // add the collection
    err = client.Schema().ClassCreator().WithClass(weaviateVectorizerWithModelDef).Do(ctx)
    if err != nil {
        panic(err)
    }
}

  API docs

Java

Map<String, Object> text2vecWeaviate = new HashMap<>();
Map<String, Object> text2vecWeaviateSettings = new HashMap<>();

text2vecWeaviateSettings.put("properties", new String[]{"title"});
text2vecWeaviateSettings.put("model", new String[]{"arctic-embed-m-v1.5"});
text2vecWeaviate.put("text2vec-weaviate", text2vecWeaviateSettings);

// Define the vector configurations
Map<String, WeaviateClass.VectorConfig> vectorConfig = new HashMap<>();
vectorConfig.put("title_vector", WeaviateClass.VectorConfig.builder()
  .vectorIndexType("hnsw")
  .vectorizer(text2vecWeaviate)
  .build());

// Create the collection "DemoCollection"
WeaviateClass clazz = WeaviateClass.builder()
  .className("DemoCollection")
  .vectorConfig(vectorConfig)
  .build();

Result<Boolean> result = client.schema().classCreator().withClass(clazz).run();

  API docs

You can specify one of the available models for Weaviate to use. The default model is used if no model is specified.

Vectorization behavior

Weaviate follows the collection configuration and a set of predetermined rules to vectorize objects.

Unless specified otherwise in the collection definition, the default behavior is to:

• Only vectorize properties that use the text or text[] data type (unless skipped)
• Sort properties in alphabetical (a-z) order before concatenating values
• If vectorizePropertyName is true (false by default) prepend the property name to each property value
• Join the (prepended) property values with spaces
• Prepend the class name (unless vectorizeClassName is false)
• Convert the produced string to lowercase

Vectorizer parameters

The following examples show how to configure Weaviate Embeddings-specific options.

Python API v4

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    vectorizer_config=[
        Configure.NamedVectors.text2vec_weaviate(
            name="title_vector",
            source_properties=["title"],
            # Further options
            # model="arctic-embed-m-v1.5",
            # dimensions=256
            # base_url="<custom_weaviate_embeddings_url>",
        )
    ],
    # Additional parameters not shown
)

  API docs

JS/TS API v3

await client.collections.create({
  name: 'DemoCollection',
  properties: [
    {
      name: 'title',
      dataType: 'text' as const,
    },
  ],
  vectorizers: [
    weaviate.configure.vectorizer.text2VecWeaviate({
        name: 'title_vector',
        sourceProperties: ['title'],
        // // Further options
        // model: 'arctic-embed-m-v1.5',
        // dimensions: 256,
        // baseUrl: '<custom_weaviate_embeddings_url>',
      },
    ),
  ],
  // Additional parameters not shown
});

  API docs

Go

// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    // Define the collection
    weaviateVectorizerFullDef := &models.Class{
        Class: "DemoCollection",
        VectorConfig: map[string]models.VectorConfig{
            "title_vector": {
                Vectorizer: map[string]interface{}{
                    "text2vec-weaviate": map[string]interface{}{
                        "model":      "arctic-embed-m-v1.5",
                        "dimensions": 256, // Or 756
                        "base_url":   "<custom_weaviate_url>",
                    },
                },
            },
        },
    }

    // add the collection
    err = client.Schema().ClassCreator().WithClass(weaviateVectorizerFullDef).Do(ctx)
    if err != nil {
        panic(err)
    }
}

  API docs

Java

Map<String, Object> text2vecWeaviate = new HashMap<>();
Map<String, Object> text2vecWeaviateSettings = new HashMap<>();

text2vecWeaviateSettings.put("properties", new String[]{"title"});
text2vecWeaviateSettings.put("model", new String[]{"arctic-embed-m-v1.5"});
text2vecWeaviateSettings.put("dimensions", new Integer[]{768});  // 768, 256
text2vecWeaviateSettings.put("base_url", new String[]{"<custom_weaviate_url>"});
text2vecWeaviate.put("text2vec-weaviate", text2vecWeaviateSettings);

// Define the vector configurations
Map<String, WeaviateClass.VectorConfig> vectorConfig = new HashMap<>();
vectorConfig.put("title_vector", WeaviateClass.VectorConfig.builder()
  .vectorIndexType("hnsw")
  .vectorizer(text2vecWeaviate)
  .build());

// Create the collection "DemoCollection"
WeaviateClass clazz = WeaviateClass.builder()
  .className("DemoCollection")
  .vectorConfig(vectorConfig)
  .build();

Result<Boolean> result = client.schema().classCreator().withClass(clazz).run();

  API docs

• model: The name of the model to use for embedding generation.
• dimensions: The number of dimensions to use for the generated embeddings. Only available for models that support Matryoshka Representation Learning.
• base_url: The base URL for the Weaviate Embeddings service. (Not required in most cases.)

Data import

After configuring the vectorizer, import data into Weaviate. Weaviate generates embeddings for text objects using the specified model.

Python API v4

collection = client.collections.get("DemoCollection")

with collection.batch.dynamic() as batch:
    for src_obj in source_objects:
        weaviate_obj = {
            "title": src_obj["title"],
            "description": src_obj["description"],
        }

        # The model provider integration will automatically vectorize the object
        batch.add_object(
            properties=weaviate_obj,
            # vector=vector  # Optionally provide a pre-obtained vector
        )

  API docs

JS/TS API v3

const collectionName = 'DemoCollection'
const myCollection = client.collections.get(collectionName)

let dataObjects = []

for (let srcObject of srcObjects) {
  dataObject.push({
    title: srcObject.title,
    description: srcObject.description,
  });
}

const response = await myCollection.data.insertMany(dataObjects);

console.log(response);

  API docs

Go

// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    var sourceObjects = []map[string]string{
        // Objects not shown
    }

    // Convert items into a slice of models.Object
    objects := []models.PropertySchema{}
    for i := range sourceObjects {
        objects = append(objects, map[string]interface{}{
            // Populate the object with the data
        })
    }

    // Batch write items
    batcher := client.Batch().ObjectsBatcher()
    for _, dataObj := range objects {
        batcher.WithObjects(&models.Object{
            Class:      "DemoCollection",
            Properties: dataObj,
        })
    }

    // Flush
    batchRes, err := batcher.Do(ctx)

    // Error handling
    if err != nil {
        panic(err)
    }
    for _, res := range batchRes {
        if res.Result.Errors != nil {
            for _, err := range res.Result.Errors.Error {
                if err != nil {
                    fmt.Printf("Error details: %v\n", *err)
                    panic(err.Message)
                }
            }
        }
    }
}

  API docs

Java

List<HashMap<String, Object>> objects = new ArrayList<>();
for (Map<String, String> sourceObject : sourceObjects) {
  HashMap<String, Object> schema = new HashMap<>();
  schema.put("title", sourceObject.get("title"));
  schema.put("description", sourceObject.get("description"));
  objects.add(schema);
}

// Batch write items
ObjectsBatcher batcher = client.batch().objectsBatcher();
for (Map<String, Object> properties : objects) {
  batcher.withObject(WeaviateObject.builder()
    .className("DemoCollection")
    .properties(properties)
    // .tenant("tenantA")  // If multi-tenancy is enabled, specify the tenant to which the object will be added.
    .build()
  );
}

// Flush
batcher.run();

  API docs

Re-use existing vectors

If you already have a compatible model vector available, you can provide it directly to Weaviate. This can be useful if you have already generated embeddings using the same model and want to use them in Weaviate, such as when migrating data from another system.

Searches

Once the vectorizer is configured, Weaviate will perform vector and hybrid search operations using the specified WED model.

Vector (near text) search

When you perform a vector search, Weaviate converts the text query into an embedding using the specified model and returns the most similar objects from the database.

The query below returns the n most similar objects from the database, set by limit.

Python API v4

collection = client.collections.get("DemoCollection")

response = collection.query.near_text(
    query="A holiday film",  # The model provider integration will automatically vectorize the query
    limit=2
)

for obj in response.objects:
    print(obj.properties["title"])

  API docs

JS/TS API v3

const collectionName = 'DemoCollection'
const myCollection = client.collections.get(collectionName)

let result;

result = await myCollection.query.nearText(
  'A holiday film',  // The model provider integration will automatically vectorize the query
  {
    limit: 2,
  }
)

console.log(JSON.stringify(result.objects, null, 2));

  API docs

Go

// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    nearTextResponse, err := client.GraphQL().Get().
        WithClassName("DemoCollection").
        WithFields(
            graphql.Field{Name: "title"},
        ).
        WithNearText(client.GraphQL().NearTextArgBuilder().
            WithConcepts([]string{"A holiday film"})).
        WithLimit(2).
        Do(ctx)

    if err != nil {
        panic(err)
    }
    fmt.Printf("%v", nearTextResponse)
}

  API docs

Java

Fields returnFields = Fields.builder()
  .fields(new Field[]{
    Field.builder().name("title").build(),
  })
  .build();

NearTextArgument nearText = NearTextArgument.builder()
  .concepts(new String[]{"A holiday film"})
  .build();

String nearTextQuery = GetBuilder.builder()
  .className("DemoCollection")
  .fields(returnFields)
  .withNearTextFilter(nearText)
  .limit(2)
  .build()
  .buildQuery();

Result<GraphQLResponse> nearTextResult = client.graphQL().raw().withQuery(nearTextQuery).run();

if (nearTextResult.hasErrors()) {
  System.err.println(nearTextResult.getError());
} else {
  System.out.println("Near Text Results: " + nearTextResult.getResult().getData());
}

  API docs

Hybrid search

What is a hybrid search?

A hybrid search performs a vector search and a keyword (BM25) search, before combining the results to return the best matching objects from the database.

When you perform a hybrid search, Weaviate converts the text query into an embedding using the specified model and returns the best scoring objects from the database.

The query below returns the n best scoring objects from the database, set by limit.

Python API v4

collection = client.collections.get("DemoCollection")

response = collection.query.hybrid(
    query="A holiday film",  # The model provider integration will automatically vectorize the query
    limit=2
)

for obj in response.objects:
    print(obj.properties["title"])

  API docs

JS/TS API v3

const collectionName = 'DemoCollection'
const myCollection = client.collections.get(collectionName)

result = await myCollection.query.hybrid(
  'A holiday film',  // The model provider integration will automatically vectorize the query
  {
    limit: 2,
  }
)

console.log(JSON.stringify(result.objects, null, 2));

  API docs

Go

// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    hybridResponse, err := client.GraphQL().Get().
        WithClassName("DemoCollection").
        WithFields(
            graphql.Field{Name: "title"},
        ).
        WithHybrid(client.GraphQL().HybridArgumentBuilder().
            WithQuery("A holiday film")).
        WithLimit(2).
        Do(ctx)

    if err != nil {
        panic(err)
    }
    fmt.Printf("%v", hybridResponse)
}

  API docs

Java

Fields returnFields = Fields.builder()
  .fields(new Field[]{
    Field.builder().name("title").build(),
  })
  .build();

HybridArgument hybrid = HybridArgument.builder()
  .query("A holiday film")
  .build();

String hybridQuery = GetBuilder.builder()
  .className("DemoCollection")
  .fields(returnFields)
  .withHybridFilter(hybrid)
  .limit(2)
  .build()
  .buildQuery();

Result<GraphQLResponse> hybridResult = client.graphQL().raw().withQuery(hybridQuery).run();

if (hybridResult.hasErrors()) {
  System.err.println(hybridResult.getError());
} else {
  System.out.println("Hybrid Results: " + hybridResult.getResult().getData());
}

  API docs

References

Available models

• arctic-embed-m-v1.5 (default)
  • A 109M parameter, 768-dimensional model for enterprise retrieval tasks in English.
  • Trained with Matryoshka Representation Learning to allow vector truncation with minimal loss.
  • Quantization-friendly: Using scalar quantization and 256 dimensions provides 99% of unquantized, full-precision performance.
  • Read more at the Snowflake blog, and the Hugging Face model card
  • Allowable dimensions: 768 (default), 256

Additional models will be added in the future.

Input truncation

Currently, input exceeding the model's context windows is truncated from the right (i.e. the end of the input).

Further resources

Code examples

Once the integrations are configured at the collection, the data management and search operations in Weaviate work identically to any other collection. See the following model-agnostic examples:

• The how-to: manage data guides show how to perform data operations (i.e. create, update, delete).
• The how-to: search guides show how to perform search operations (i.e. vector, keyword, hybrid) as well as retrieval augmented generation.

Further resources

• Weaviate Embeddings Documentation

Questions and feedback

If you have any questions or feedback, let us know in the user forum.

• Technical questions
• Documentation feedback