Skip to main content

Google AI Multimodal Embeddings with Weaviate

New Documentation

The model provider integration pages are new and still undergoing improvements. We appreciate any feedback on this forum thread.

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

AI Studio not available

Multimodal embeddings are currently not available to Google AI Studio users.

Configure a Weaviate vector index to use a Google AI embedding model, and Weaviate will generate embeddings for various operations using the specified model and your Google 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.

Embedding integration illustration

Requirements​

Weaviate configuration​

Your Weaviate instance must be configured with the Google AI vectorizer integration (multi2vec-palm) module.

For Weaviate Cloud (WCD) users

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

For self-hosted users

API credentials​

You must provide valid API credentials to Weaviate for the appropriate integration.

Vertex AI​

This is called an access token in Google Cloud.

If you have the Google Cloud CLI tool installed and set up, you can view your token by running the following command:

gcloud auth print-access-token

Token expiry for Vertex AI users​

Important

By default, Google Cloud's OAuth 2.0 access tokens have a lifetime of 1 hour. You can create tokens that last up to 12 hours. To create longer lasting tokens, follow the instructions in the Google Cloud IAM Guide.

Since the OAuth token is only valid for a limited time, you must periodically replace the token with a new one. After you generate the new token, you have to re-instantiate your Weaviate client to use it.

You can update the OAuth token manually, but manual updates may not be appropriate for your use case.

You can also automate the OAth token update. Weaviate does not control the OAth token update procedure. However, here are some automation options:

With Google Cloud CLI

If you are using the Google Cloud CLI, write a script to periodically update the token and extract the results.


Python code to extract the token looks like this:

client = re_instantiate_weaviate()

This is the re_instantiate_weaviate function:

import subprocess
import weaviate

def refresh_token() -> str:
    result = subprocess.run(["gcloud", "auth", "print-access-token"], capture_output=True, text=True)
    if result.returncode != 0:
        print(f"Error refreshing token: {result.stderr}")
        return None
    return result.stdout.strip()

def re_instantiate_weaviate() -> weaviate.Client:
    token = refresh_token()

    client = weaviate.Client(
      url = "https://WEAVIATE_INSTANCE_URL",  # Replace WEAVIATE_INSTANCE_URL with the URL
      additional_headers = {
        "X-Google-Vertex-Api-Key": token,
      }
    )
    return client

# Run this every ~60 minutes
client = re_instantiate_weaviate()
With google-auth

Another way is through Google's own authentication library google-auth.


See the links to google-auth in Python and Node.js libraries.


You can, then, periodically the refresh function (see Python docs) to obtain a renewed token, and re-instantiate the Weaviate client.

For example, you could periodically run:

client = re_instantiate_weaviate()

Where re_instantiate_weaviate is something like:

from google.auth.transport.requests import Request
from google.oauth2.service_account import Credentials
import weaviate
import os


def get_credentials() -> Credentials:
    credentials = Credentials.from_service_account_file(
        "path/to/your/service-account.json",
        scopes=[
            "https://www.googleapis.com/auth/generative-language",
            "https://www.googleapis.com/auth/cloud-platform",
        ],
    )
    request = Request()
    credentials.refresh(request)
    return credentials


def re_instantiate_weaviate() -> weaviate.Client:
    credentials = get_credentials()
    token = credentials.token

    client = weaviate.connect_to_wcs(  # e.g. if you use the Weaviate Cloud Service
        cluster_url="https://WEAVIATE_INSTANCE_URL",  # Replace WEAVIATE_INSTANCE_URL with the URL
        auth_credentials=weaviate.auth.AuthApiKey(os.getenv("WCD_DEMO_RO_KEY")),  # Replace with your Weaviate Cloud key
        headers={
            "X-Google-Vertex-Api-Key": token,
        },
    )
    return client


# Run this every ~60 minutes
client = re_instantiate_weaviate()

The service account key shown above can be generated by following this guide.

Provide the API key​

Provide the API key to Weaviate at runtime, as shown in the examples below.

API key headers

Starting from v1.25.1 and v1.24.14, there are separate headers X-Google-Vertex-Api-Key and X-Google-Studio-Api-Key for Vertex AI users and AI Studio respectively.


Prior to Weaviate v1.25.1 or v1.24.14, there was one header for both Vertex AI users and AI Studio, specified with either X-Google-Api-Key or X-PaLM-Api-Key. We recommend using the new headers for clarity and future compatibility.

import weaviate
from weaviate.auth import AuthApiKey
import os

# Recommended: save sensitive data as environment variables
vertex_key = os.getenv("VERTEX_APIKEY")
headers = {
    "X-Google-Vertex-Api-Key": vertex_key,
}

client = weaviate.connect_to_wcs(
    cluster_url=weaviate_url,                       # `weaviate_url`: your Weaviate URL
    auth_credentials=AuthApiKey(weaviate_key),      # `weaviate_key`: your Weaviate API key
    headers=headers
)

# Work with Weaviate

client.close()

Configure the vectorizer​

Configure a Weaviate index to use a Google AI embedding model by setting the vectorizer as follows:

from weaviate.classes.config import Property, DataType, Configure, Multi2VecField

client.collections.create(
    "DemoCollection",
    properties=[
        Property(name="title", data_type=DataType.TEXT),
        Property(name="poster", data_type=DataType.BLOB),
    ],
    vectorizer_config=[
        Configure.NamedVectors.multi2vec_palm(
            name="title_vector",
            # Define the fields to be used for the vectorization - using image_fields, text_fields, video_fields
            image_fields=[
                Multi2VecField(name="poster", weight=0.9)
            ],
            text_fields=[
                Multi2VecField(name="title", weight=0.1)
            ],
            # video_fields=[],
            project_id="<google-cloud-project-id>",  # Required for Vertex AI
            location="<google-cloud-location>",  # Required for Vertex AI
        )
    ],
    # Additional parameters not shown
)

You can specify one of the available models for the vectorizer to use. Currently, multimodalembedding@001 is the only available model.

Data import​

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

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"],
            "description": src_obj["description"],
            "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
        )
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 Google AI 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.

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"])
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.

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"])

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.

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"])

References​

Vectorizer parameters​

The following examples show how to configure Google AI-specific options.

  • location (Required): e.g. "us-central1"
  • projectId (Only required if using Vertex AI): e.g. cloud-large-language-models
  • apiEndpoint (Optional): e.g. us-central1-aiplatform.googleapis.com
  • modelId (Optional): e.g. multimodalembedding@001
  • dimensions (Optional): Must be one of: 128, 256, 512, 1408. Default is 1408.
from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    properties=[
        Property(name="title", data_type=DataType.TEXT),
        Property(name="description", data_type=DataType.TEXT),
        Property(name="poster", data_type=DataType.BLOB),
    ],
    vectorizer_config=[
        Configure.NamedVectors.multi2vec_palm(
            name="title_vector",
            # project_id="<google-cloud-project-id>"  # Required for Vertex AI
            # model_id="<google-model-id>",
            # location="us-central1",
            # dimensions=512,
            image_fields=[
                Multi2VecField(name="poster", weight=0.9)
            ],
            text_fields=[
                Multi2VecField(name="title", weight=0.1)
            ],
            # video_fields=[]
            # video_interval_seconds=20
        )
    ],
    # Additional parameters not shown
)

Available models​

  • multimodalembedding@001 (default)

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 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​

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