Multimodal Embeddings

Weaviate's integration with NVIDIA's APIs allows you to access their models' capabilities directly from Weaviate.

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

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

Embedding integration illustration

Requirements

Weaviate configuration

Your Weaviate instance must be configured with the NVIDIA vectorizer integration (multi2vec-nvidia) module.

For Weaviate Cloud (WCD) users

This integration is enabled by default on Weaviate Cloud (WCD) instances.

For self-hosted users

Check the cluster metadata to verify if the module is enabled.
Follow the how-to configure modules guide to enable the module in Weaviate.

API credentials

You must provide a valid NVIDIA NIM API key to Weaviate for this integration. Go to NVIDIA to sign up and obtain an API key.

Provide the API key to Weaviate using one of the following methods:

Set the NVIDIA_APIKEY environment variable that is available to Weaviate.
Provide the API key at runtime, as shown in the examples below.

Python

# Recommended: save sensitive data as environment variables
nvidia_key = os.getenv("NVIDIA_API_KEY")

JavaScript/TypeScript

const nvidiaApiKey = process.env.NVIDIA_API_KEY || '';  // Replace with your inference API key

Configure the vectorizer

Configure a Weaviate index as follows to use an NVIDIA embedding model:

Python

from weaviate.classes.config import Configure, DataType, Multi2VecField, Propertyclient.collections.create(    "DemoCollection",    properties=[        Property(name="title", data_type=DataType.TEXT),        Property(name="poster", data_type=DataType.BLOB),    ],    vector_config=[        Configure.Vectors.multi2vec_nvidia(            name="title_vector",            # Define the fields to be used for the vectorization - using image_fields, text_fields            image_fields=[                Multi2VecField(name="poster", weight=0.9)            ],            text_fields=[                Multi2VecField(name="title", weight=0.1)            ],        )    ],    # Additional parameters not shown)

JavaScript/TypeScript

await client.collections.create({
  name: 'DemoCollection',
  vectorizers: [
    weaviate.configure.vectors.multi2VecNvidia({
      name: 'title_vector',
      imageFields: [{
        name: "poster",
        weight: 0.9
      }],
      textFields: [{
        name: "title",
        weight: 0.1
      }],
    })
  ],
  // Additional parameters not shown
})

Select a model

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

Python

from weaviate.classes.config import Configure, DataType, Multi2VecField, Propertyclient.collections.create(    "DemoCollection",    properties=[        Property(name="title", data_type=DataType.TEXT),        Property(name="poster", data_type=DataType.BLOB),    ],    vector_config=[        Configure.Vectors.multi2vec_nvidia(            name="title_vector",            model="nvidia/nvclip",            # Define the fields to be used for the vectorization - using image_fields, text_fields            image_fields=[                Multi2VecField(name="poster", weight=0.9)            ],            text_fields=[                Multi2VecField(name="title", weight=0.1)            ],        )    ],    # Additional parameters not shown)

JavaScript/TypeScript

await client.collections.create({
  name: 'DemoCollection',
  vectorizers: [
    weaviate.configure.vectors.multi2VecNvidia({
      name: 'title_vector',
      model: "nvidia/nv-embed-v1",
      imageFields: [{
        name: "poster",
        weight: 0.9
      }],
      textFields: [{
        name: "title",
        weight: 0.1
      }],
    })
  ],
  // Additional parameters not shown
})

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 NVIDIA-specific options.

Python

from weaviate.classes.config import Configure, DataType, Multi2VecField, Propertyclient.collections.create(    "DemoCollection",    properties=[        Property(name="title", data_type=DataType.TEXT),        Property(name="poster", data_type=DataType.BLOB),    ],    vector_config=[        Configure.Vectors.multi2vec_nvidia(            name="title_vector",            # Define the fields to be used for the vectorization - using image_fields, text_fields            image_fields=[                Multi2VecField(name="poster", weight=0.9)            ],            text_fields=[                Multi2VecField(name="title", weight=0.1)            ],            # Further options            # model="nvidia/nvclip",        )    ],    # Additional parameters not shown)

JavaScript/TypeScript

await client.collections.create({
  name: 'DemoCollection',
  vectorizers: [
    weaviate.configure.vectors.multi2VecNvidia({
      name: 'title_vector',
      model: "nvidia/nv-embed-v1",
      imageFields: [{
        name: "poster",
        weight: 0.9
      }],
      textFields: [{
        name: "title",
        weight: 0.1
      }],
      // Further options
    })
  ],
  // Additional parameters not shown
})

For further details on model parameters, see the NVIDIA NIM API documentation.

Data import

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

Python

collection = client.collections.use("DemoCollection")with collection.batch.fixed_size(batch_size=200) as batch:    for src_obj in source_objects:        poster_b64 = url_to_base64(src_obj["poster_path"])        weaviate_obj = {            "title": src_obj["title"],            "poster": poster_b64  # Add the image in base64 encoding        }        # The model provider integration will automatically vectorize the object        batch.add_object(            properties=weaviate_obj,            # vector=vector  # Optionally provide a pre-obtained vector        )

JavaScript/TypeScript

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

Searches

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

Embedding integration at search illustration

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

collection = client.collections.use("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"])

JavaScript/TypeScript

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

Hybrid search

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

collection = client.collections.use("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"])

JavaScript/TypeScript

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

Vector (near media) search

When you perform a media search such as a near image search, Weaviate converts the query into an embedding using the specified model and returns the most similar objects from the database.

To perform a near media search such as near image search, convert the media query into a base64 string and pass it to the search query.

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

Python

def url_to_base64(url):
    import requests
    import base64

    image_response = requests.get(url)
    content = image_response.content
    return base64.b64encode(content).decode("utf-8")

JavaScript/TypeScript

const base64String = 'SOME_BASE_64_REPRESENTATION';

result = await myCollection.query.nearImage(
  base64String,  // The model provider integration will automatically vectorize the query
  {
    limit: 2,
  }
)

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

References

Available models

You can use any multimodal embedding model on NVIDIA NIM APIs with Weaviate.

The default model is nvidia/nvclip.

Further resources

Other integrations

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 collections and How-to: Manage objects guides show how to perform data operations (i.e. create, read, update, delete collections and objects within them).
The How-to: Query & Search guides show how to perform search operations (i.e. vector, keyword, hybrid) as well as retrieval augmented generation.

External resources

NVIDIA NIM API documentation

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.