Jina AI Multimodal Embeddings with Weaviate

Added in 1.25.26, 1.26.11 and v1.27.5

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

Configure a Weaviate vector index to use an Jina AI embedding model, and Weaviate will generate embeddings for various operations using the specified model and your Jina AI 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 queries of one or more modalities into embeddings. Multimodal search operations are also supported.

Requirements

Weaviate configuration

Your Weaviate instance must be configured with the Jina AI multimodal vectorizer integration (multi2vec-jinaai) module.

For Weaviate Cloud (WCD) users

This integration is enabled by default on Weaviate Cloud (WCD) serverless 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 Jina AI API key to Weaviate for this integration. Go to Jina AI to sign up and obtain an API key.

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

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

Python API v4

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

# Recommended: save sensitive data as environment variables
jinaai_key = os.getenv("JINAAI_APIKEY")
headers = {
    "X-JinaAI-Api-Key": jinaai_key,
}

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
    headers=headers
)

# Work with Weaviate

client.close()

JS/TS API v3

import weaviate from 'weaviate-client'

const jinaaiApiKey = process.env.JINAAI_APIKEY || '';  // Replace with your inference API key

const client = await weaviate.connectToWeaviateCloud(
  'WEAVIATE_INSTANCE_URL',  // Replace with your instance URL
  {
    authCredentials: new weaviate.ApiKey('WEAVIATE_INSTANCE_APIKEY'),
    headers: {
      'X-JinaAI-Api-Key': jinaaiApiKey,
    }
  }
)

// Work with Weaviate

client.close()

Configure the vectorizer

Configure a Weaviate index as follows to use a Jina AI embedding model:

Python API v4

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    properties=[
        Property(name="title", data_type=DataType.TEXT),
        Property(name="poster", data_type=DataType.BLOB),
    ],
    vectorizer_config=[
        Configure.NamedVectors.multi2vec_jinaai(
            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
)

JS/TS API v3

// TS client support coming soon

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",
    properties=[
        Property(name="title", data_type=DataType.TEXT),
        Property(name="poster", data_type=DataType.BLOB),
    ],
    vectorizer_config=[
        Configure.NamedVectors.multi2vec_jinaai(
            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)
            ],
            model="jina-clip-v2",
        )
    ],
)

JS/TS API v3

// TS client support coming soon

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 Jina AI-specific options.

Python API v4

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    properties=[
        Property(name="title", data_type=DataType.TEXT),
        Property(name="poster", data_type=DataType.BLOB),
    ],
    vectorizer_config=[
        Configure.NamedVectors.multi2vec_jinaai(
            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="jina-clip-v2",
            # dimensions=512,  # Only applicable for some models (e.g. `jina-clip-v2`)
        )
    ],
    # Additional parameters not shown
)

JS/TS API v3

// TS client support coming soon

Vectorizer parameters

• model: The model name.
• dimensions: The number of dimensions for the model.
  • Note that not all models support this parameter.

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:
        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
        )

JS/TS API v3

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

let multiModalObjects = []

for (let mmSrcObject of mmSrcObjects) {
  multiModalObjects.push({
    title: mmSrcObject.title,
    poster: mmSrcObject.poster,  // Add the image in base64 encoding
  });
}

// The model provider integration will automatically vectorize the object
const mmInsertResponse = await myCollection.data.insertMany(dataObject);

console.log(mmInsertResponse);

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 Jina AI 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"])

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));

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"])

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));

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 API v4

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")


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

query_b64 = url_to_base64(src_img_path)

response = collection.query.near_image(
    near_image=query_b64,
    limit=2,
    return_properties=["title", "release_date", "tmdb_id", "poster"]  # To include the poster property in the response (`blob` properties are not returned by default)
)

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

JS/TS API v3

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

• jina-clip-v2
  • This model is a multilingual, multimodal model using Matryoshka Representation Learning.
  • It will accept a dimensions parameter, which can be any integer between (and including) 64 and 1024. The default value is 1024.
• jina-clip-v1
  • This model will always return a 768-dimensional embedding.

Further resources

Other integrations

• Jina AI text embedding models + Weaviate.
• Jina AI reranker models + Weaviate.

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.

External resources

• Jina AI Embeddings API documentation

Questions and feedback

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

• Technical questions
• Documentation feedback