Google AI Generative AI 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 AI Studio and Google Vertex AI APIs allows you to access their models' capabilities directly from Weaviate.

Configure a Weaviate collection to use a Google AI generative AI model, and Weaviate will perform retrieval augmented generation (RAG) using the specified model and your Google AI API key.

More specifically, Weaviate will perform a search, retrieve the most relevant objects, and then pass them to the Google AI generative model to generate outputs.

RAG integration illustration

AI Studio availability

At the time of writing (November 2023), AI Studio is not available in all regions. See this page for the latest information.

Requirements

Weaviate configuration

Your Weaviate instance must be configured with the Google AI generative AI integration (generative-palm) 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 valid API credentials to Weaviate for the appropriate integration.

AI Studio

Go to Google AI Studio to sign up and obtain an API key.

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.

Note the separate headers that are available for AI Studio and Vertex AI users.

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.

Python API v4
JS/TS API v3

import weaviate
from weaviate.auth import AuthApiKey
import os

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

import weaviate from 'weaviate-client'

const vertexApiKey = process.env.VERTEX_APIKEY || '';  // Replace with your inference API key
const studioApiKey = process.env.STUDIO_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-Vertex-Api-Key': vertexApiKey,
      'X-Studio-Api-Key': studioApiKey,
    }
  }
)

// Work with Weaviate

client.close()

Configure collection

Configure a Weaviate collection to use a Google AI generative AI model as follows:

Note that the required parameters differ between Vertex AI and AI Studio.

The default model is used if no model is specified.

Vertex AI

Vertex AI users must provide the Google Cloud project ID in the collection configuration.

Python API v4
JS/TS API v3

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    generative_config=Configure.Generative.palm(
        project_id="<google-cloud-project-id>",  # Required for Vertex AI
        model_id="gemini-1.0-pro"
    )
    # Additional parameters not shown
)

await client.collections.create({
  name: 'DemoCollection',
  generative: weaviate.configure.generative.palm({
    projectId: '<google-cloud-project-id>',  // Required for Vertex AI
    modelId: 'gemini-1.0-pro'
  }),
  // Additional parameters not shown
});

AI Studio

Python API v4
JS/TS API v3

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    generative_config=Configure.Generative.palm(
        model_id="gemini-pro"
    )
    # Additional parameters not shown
)

// Coming soon

Retrieval augmented generation

After configuring the generative AI integration, perform RAG operations, either with the single prompt or grouped task method.

Single prompt

Single prompt RAG integration generates individual outputs per search result

To generate text for each object in the search results, use the single prompt method.

The example below generates outputs for each of the n search results, where n is specified by the limit parameter.

When creating a single prompt query, use braces {} to interpolate the object properties you want Weaviate to pass on to the language model. For example, to pass on the object's title property, include {title} in the query.

Python API v4
JS/TS API v3

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

response = collection.generate.near_text(
    query="A holiday film",  # The model provider integration will automatically vectorize the query
    single_prompt="Translate this into French: {title}",
    limit=2
)

for obj in response.objects:
    print(obj.properties["title"])
    print(f"Generated output: {obj.generated}")  # Note that the generated output is per object

let myCollection = client.collections.get('DemoCollection');

const singlePromptResults = await myCollection.generate.nearText(
  ['A holiday film'],
  {
    singlePrompt: `Translate this into French: {title}`,
  },
  {
    limit: 2,
  }
);

for (const obj of singlePromptResults.objects) {
  console.log(obj.properties['title']);
  console.log(`Generated output: ${obj.generated}`);  // Note that the generated output is per object
}

Grouped task

Grouped task RAG integration generates one output for the set of search results

To generate one text for the entire set of search results, use the grouped task method.

In other words, when you have n search results, the generative model generates one output for the entire group.

Python API v4
JS/TS API v3

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

response = collection.generate.near_text(
    query="A holiday film",  # The model provider integration will automatically vectorize the query
    grouped_task="Write a fun tweet to promote readers to check out these films.",
    limit=2
)

print(f"Generated output: {response.generated}")  # Note that the generated output is per query
for obj in response.objects:
    print(obj.properties["title"])

let myCollection = client.collections.get('DemoCollection');
const groupedTaskResults = await myCollection.generate.nearText(
  ['A holiday film'],
  {
    groupedTask: `Write a fun tweet to promote readers to check out these films.`,
  },
  {
    limit: 2,
  }
);

console.log(`Generated output: ${groupedTaskResults.generated}`);  // Note that the generated output is per query
for (const obj of groupedTaskResults.objects) {
  console.log(obj.properties['title']);
}

References

Generative parameters

Configure the following generative parameters to customize the model behavior.

Python API v4
JS/TS API v3

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    generative_config=Configure.Generative.palm(
        # project_id="<google-cloud-project-id>",  # Required for Vertex AI
        # model_id="<google-model-id>",
        # api_endpoint="<google-api-endpoint>",
        # temperature=0.7,
        # top_k=5,
        # top_p=0.9,
        # vectorize_collection_name=False,
    )
    # Additional parameters not shown
)

await client.collections.create({
  name: 'DemoCollection',
  generative: weaviate.configure.generative.palm({
    projectId: '<google-cloud-project-id>',  // Required for Vertex AI
    // model_id='<google-model-id>',
    // api_endpoint='<google-api-endpoint>',
    // temperature=0.7,
    // top_k=5,
    // top_p=0.9,
    // vectorize_collection_name=False,
  }),
  // Additional parameters not shown
});

Available models

Vertex AI:

chat-bison (default)
chat-bison-32k (from Weaviate v1.24.9)
chat-bison@002 (from Weaviate v1.24.9)
chat-bison-32k@002 (from Weaviate v1.24.9)
chat-bison@001 (from Weaviate v1.24.9)
gemini-1.5-pro-preview-0514 (from Weaviate v1.25.1)
gemini-1.5-pro-preview-0409 (from Weaviate v1.25.1)
gemini-1.5-flash-preview-0514 (from Weaviate v1.25.1)
gemini-1.0-pro-002 (from Weaviate v1.25.1)
gemini-1.0-pro-001 (from Weaviate v1.25.1)
gemini-1.0-pro (from Weaviate v1.25.1)

AI Studio:

chat-bison-001 (default)
gemini-pro

Further resources

Other integrations

Google AI embedding 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.

References

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

Google AI Generative AI with Weaviate

Requirements​

Weaviate configuration​

API credentials​

AI Studio​

Vertex AI​

Token expiry for Vertex AI users​

Provide the API key​

Configure collection​

Vertex AI​

AI Studio​

Retrieval augmented generation​

Single prompt​

Grouped task​

References​

Generative parameters​

Available models​

Further resources​

Other integrations​

Code examples​

References​

Requirements

Weaviate configuration

API credentials

AI Studio

Vertex AI

Token expiry for Vertex AI users

Provide the API key

Configure collection

Vertex AI

AI Studio

Retrieval augmented generation

Single prompt

Grouped task

References

Generative parameters

Available models

Further resources

Other integrations

Code examples

References