---
title: "Google Text Embeddings with Weaviate"
description: "Weaviate's integration with Google Gemini API and Google Vertex AI APIs allows you to access their models' capabilities directly from Weaviate."
url: https://docs.weaviate.io/weaviate/model-providers/google/embeddings
---

# Google Text Embeddings with Weaviate

Weaviate's integration with [Google Gemini API](https://ai.google.dev/?utm_source=weaviate\&utm_medium=referral\&utm_campaign=partnerships\&utm_content=) and [Google Vertex AI](https://cloud.google.com/vertex-ai) APIs allows you to access their models' capabilities directly from Weaviate.

[Configure a Weaviate vector index](https://docs.weaviate.io/weaviate/model-providers/google/embeddings#configure-the-vectorizer) to use a Google embedding model, and Weaviate will generate embeddings for various operations using the specified model and your Google API key. This feature is called the *vectorizer*.

At [import time](https://docs.weaviate.io/weaviate/model-providers/google/embeddings#data-import), Weaviate generates text object embeddings and saves them into the index. For [vector](https://docs.weaviate.io/weaviate/model-providers/google/embeddings#vector-near-text-search) and [hybrid](https://docs.weaviate.io/weaviate/model-providers/google/embeddings#hybrid-search) search operations, Weaviate converts text queries into embeddings.

![Embedding integration illustration](https://docs.weaviate.io/assets/images/integration_google_embedding-64c7752f66b74f65a565891b7da297bb.png)

> [!TIP]
>
> **Which Google service should I use?**
>
> - **Google AI Studio (Gemini API)**: Simpler setup, ideal for prototyping and development. Get started quickly with just an API key.
> - **Vertex AI**: Enterprise-grade service with more features, better for production deployments with advanced requirements.

> [!NOTE]
>
> **Gemini API availability**
>
> Gemini API is not available in all regions. See [this page](https://ai.google.dev/gemini-api/docs/available-regions) for the latest information.

## Requirements

### Weaviate configuration

Your Weaviate instance must be configured with the Google vectorizer integration (`text2vec-google`) module.

> [!NOTE]
>
> **Module name change**
>
> `text2vec-google` was called `text2vec-palm` in Weaviate versions prior to `v1.27`.

**For Weaviate Cloud (WCD) users**

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

**For self-hosted users**

- Check the [cluster metadata](https://docs.weaviate.io/deploy/configuration/status#cluster-metadata) to verify if the module is enabled.
- Follow the [how-to configure modules](https://docs.weaviate.io/weaviate/configuration/modules) guide to enable the module in Weaviate.

### API credentials

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

#### Google AI Studio (Gemini API)

1. Go to [Google AI Studio](https://aistudio.google.com/app/apikey/?utm_source=weaviate\&utm_medium=referral\&utm_campaign=partnerships\&utm_content=)
2. In the "API Keys" section create a new API key
3. Use the `X-Goog-Studio-Api-Key` header to provide your API key to Weaviate

#### Vertex AI

This is called an `access token` in Google Cloud.

##### Automatic token generation

> [!NOTE]
>
> **Not available on Weaviate Cloud instances**
>
> This feature is not available on Weaviate cloud instances.

You can save your Google Vertex AI credentials and have Weaviate generate the necessary tokens for you. This enables use of IAM service accounts in private deployments that can hold Google credentials.

To do so:

- Set `USE_GOOGLE_AUTH` [environment variable](https://docs.weaviate.io/deploy/configuration/env-vars#module-specific) to `true`.
- Have the credentials available in one of the following locations.

Once appropriate credentials are found, Weaviate uses them to generate an access token and authenticates itself against Vertex AI. Upon token expiry, Weaviate generates a replacement access token.

In a containerized environment, you can mount the credentials file to the container. For example, you can mount the credentials file to the `/etc/weaviate/` directory and set the `GOOGLE_APPLICATION_CREDENTIALS` environment variable to `/etc/weaviate/google_credentials.json`.

**Search locations for Google Vertex AI credentials**

Once `USE_GOOGLE_AUTH` is set to `true`, Weaviate will look for credentials in the following places, preferring the first location found:

1. A JSON file whose path is specified by the `GOOGLE_APPLICATION_CREDENTIALS` environment variable. For workload identity federation, refer to [this link](https://cloud.google.com/iam/docs/how-to#using-workload-identity-federation) on how to generate the JSON configuration file for on-prem/non-Google cloud platforms.
2. A JSON file in a location known to the `gcloud` command-line tool. On Windows, this is `%APPDATA%/gcloud/application_default_credentials.json`. On other systems, `$HOME/.config/gcloud/application_default_credentials.json`.
3. On Google App Engine standard first generation runtimes (<= Go 1.9) it uses the appengine.AccessToken function.
4. On Google Compute Engine, Google App Engine standard second generation runtimes (>= Go 1.11), and Google App Engine flexible environment, it fetches credentials from the metadata server.

If you have the [Google Cloud CLI tool](https://cloud.google.com/cli) installed and set up, you can view your token by running the following command:

```shell
gcloud auth print-access-token
```

##### Token expiry for Vertex AI users

> [!WARNING]
>
> **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](https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#rest_2).

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:

```python
client = re_instantiate_weaviate()
```

This is the `re_instantiate_weaviate` function:

```python
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-Goog-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](https://google-auth.readthedocs.io/en/master/index.html) and [Node.js](https://cloud.google.com/nodejs/docs/reference/google-auth-library/latest) libraries.

You can, then, periodically the `refresh` function ([see Python docs](https://google-auth.readthedocs.io/en/master/reference/google.oauth2.service_account.html#google.oauth2.service_account.Credentials.refresh)) to obtain a renewed token, and re-instantiate the Weaviate client.

For example, you could periodically run:

```python
client = re_instantiate_weaviate()
```

Where `re_instantiate_weaviate` is something like:

```python
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:
    from weaviate.classes.init import Auth

    weaviate_api_key = os.environ["WEAVIATE_API_KEY"]
    credentials = get_credentials()
    token = credentials.token

    client = weaviate.connect_to_weaviate_cloud(  # e.g. if you use the Weaviate Cloud Service
        cluster_url="https://WEAVIATE_INSTANCE_URL",  # Replace WEAVIATE_INSTANCE_URL with the URL
        auth_credentials=Auth.api_key(weaviate_api_key),  # Replace with your Weaviate Cloud key
        headers={
            "X-Goog-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](https://cloud.google.com/iam/docs/keys-create-delete).

#### 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 [Google AI Studio (Gemini API)](https://docs.weaviate.io/weaviate/model-providers/google/embeddings#google-ai-studio-gemini-api) and [Vertex AI](https://docs.weaviate.io/weaviate/model-providers/google/embeddings#vertex-ai) users.

**API key headers**

From `v1.27.7`, `v1.26.12` and `v1.25.27`, `X-Goog-Vertex-Api-Key` and `X-Goog-Studio-Api-Key` headers are supported for Vertex AI users and Gemini API respectively. We recommend these headers for highest compatibility.



Consider `X-Google-Vertex-Api-Key`, `X-Google-Studio-Api-Key`, `X-Google-Api-Key` and `X-PaLM-Api-Key` deprecated.

**Python**

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

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

**JavaScript/TypeScript**

```ts
import weaviate from '@weaviate/node'

const vertexApiKey = process.env.VERTEX_API_KEY || '';  // Replace with your inference API key
const studioApiKey = process.env.STUDIO_API_KEY || '';  // 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_API_KEY'),
    headers: {
      'X-Vertex-Api-Key': vertexApiKey,
      'X-Studio-Api-Key': studioApiKey,
    }
  }
)

// Work with Weaviate

client.close()
```

**Go (v5)**

```go
// Set these environment variables
// WEAVIATE_HOSTNAME            your Weaviate instance hostname, excluding the scheme (https://)
// WEAVIATE_API_KEY          your Weaviate instance API key
// <PROVIDER>_API_KEY       your model provider API key (or token)

package main

import (
    "context"
    "fmt"
    "os"

    "github.com/weaviate/weaviate-go-client/v5/weaviate"
    "github.com/weaviate/weaviate-go-client/v5/weaviate/auth"
)

func main() {
    cfg := weaviate.Config{
        Host:       os.Getenv("WEAVIATE_HOSTNAME"),
        Scheme:     "https",
        AuthConfig: auth.ApiKey{Value: os.Getenv("WEAVIATE_API_KEY")},
        Headers: map[string]string{
            "X-Goog-Vertex-Key": os.Getenv("VERTEX_API_KEY"),
            "X-Goog-Studio-Key": os.Getenv("STUDIO_API_KEY"),
        },
    }

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

    // Work with Weaviate
}
```

## Configure the vectorizer

[Configure a Weaviate index](https://docs.weaviate.io/weaviate/manage-collections/vector-config#specify-a-vectorizer) as follows to use a Google embedding model:

> [!NOTE]
>
> **Important: Different vectorizers for different services**
>
> - **Google AI Studio (Gemini API)**: Use `text2vec_google_gemini()`
> - **Vertex AI**: Use `text2vec_google()`

You can [specify](https://docs.weaviate.io/weaviate/model-providers/google/embeddings#vectorizer-parameters) one of the [available models](https://docs.weaviate.io/weaviate/model-providers/google/embeddings#available-models) for Weaviate to use. The [default model](https://docs.weaviate.io/weaviate/model-providers/google/embeddings#available-models) is used if no model is specified.

### Google AI Studio (Gemini API)

For Google AI Studio, use the Gemini-specific vectorizer. A Google Cloud project ID is not required. The Python and TypeScript clients set the Gemini API endpoint for you.

**Python**

```py
from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    vector_config=Configure.Vectors.text2vec_google_gemini(
        name="title_vector",
        source_properties=["title"],
        # (Optional) To manually set the model ID
        model="gemini-embedding-2"
    ),
    # Additional parameters not shown
)
```

**JavaScript/TypeScript**

```ts
await client.collections.create({
  name: 'DemoCollection',
  properties: [
    {
      name: 'title',
      dataType: 'text' as const,
    },
  ],
  vectorizers: [
    weaviate.configure.vectors.text2VecGoogleGemini({
      name: 'title_vector',
      sourceProperties: ['title'],
      // (Optional) To manually set the model ID
      model: 'gemini-embedding-2'
    }),
  ],
  // Additional parameters not shown
});
```

**Go (v5)**

```go
// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    // Define the collection
    basicGoogleStudioVectorizerDef := &models.Class{
        Class: "DemoCollection",
        VectorConfig: map[string]models.VectorConfig{
            "title_vector": {
                Vectorizer: map[string]interface{}{
                    "text2vec-google": map[string]interface{}{
                        "properties":  []string{"title"},
                        "apiEndpoint": "generativelanguage.googleapis.com",
                        "modelId":     "gemini-embedding-001", // (Optional) To manually set the model ID
                    },
                },
            },
        },
    }

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

### Vertex AI

For Vertex AI, use the `text2vec_google()` vectorizer. You must provide your Google Cloud `project_id`.

**Python**

```py
from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    vector_config=Configure.Vectors.text2vec_google(
        name="title_vector",
        source_properties=["title"],
        project_id="<google-cloud-project-id>",  # Required for Vertex AI
        # (Optional) To manually set the model ID
        model="gemini-embedding-2"
    ),
    # Additional parameters not shown
)
```

**JavaScript/TypeScript**

```ts
await client.collections.create({
  name: 'DemoCollection',
  properties: [
    {
      name: 'title',
      dataType: 'text' as const,
    },
  ],
  vectorizers: [
    weaviate.configure.vectors.text2VecGoogle({
      name: 'title_vector',
      sourceProperties: ['title'],
      projectId: '<google-cloud-project-id>',
      // (Optional) To manually set the model ID
      model: 'gemini-embedding-2'
    }),
  ],
  // Additional parameters not shown
});
```

**Go (v5)**

```go
// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    // Define the collection
    basicGoogleVertexVectorizerDef := &models.Class{
        Class: "DemoCollection",
        VectorConfig: map[string]models.VectorConfig{
            "title_vector": {
                Vectorizer: map[string]interface{}{
                    "text2vec-google": map[string]interface{}{
                        "projectId": "<google-cloud-project-id>",
                        "modelId":   "gemini-embedding-001", // (Optional) To manually set the model ID
                    },
                },
            },
        },
    }

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

**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](https://docs.weaviate.io/weaviate/manage-collections/vector-config#property-level-settings))
- 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 collection name if `vectorizeClassName` is `true` (the default differs by integration — check this page's parameter table)



Since `v1.27`, the string is sent to the model as is. Earlier versions lowercase it first, and you can restore that behavior with the [`LOWERCASE_VECTORIZATION_INPUT`](https://docs.weaviate.io/deploy/configuration/env-vars#module-specific) environment variable.

### Vectorizer parameters

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

**Google AI Studio (Gemini API) parameters:**

- `modelId` (Optional): e.g. `gemini-embedding-001`
- `dimensions` (Optional): The length of the returned vector. Default: `768`
- `taskType` (Optional): What the embeddings are for. Default: `RETRIEVAL_QUERY`

**Vertex AI parameters:**

- `projectId` (Required): Your Google Cloud project ID, e.g. `cloud-large-language-models`
- `location` (Optional): The Google Cloud region to send requests to, e.g. `europe-west1`.
- `apiEndpoint` (Optional): Regional endpoint, e.g. `us-central1-aiplatform.googleapis.com`
- `modelId` (Optional): e.g. `gemini-embedding-001`, `text-embedding-005`
- `dimensions` (Optional): The length of the returned vector. Default: `768`
- `taskType` (Optional): What the embeddings are for. Default: `RETRIEVAL_QUERY`

Set `location` together with a matching `apiEndpoint` to keep data in a specific region.

> [!TIP]
>
> **Vertex AI location affects latency**
>
> Use the Vertex AI region closest to your Weaviate cluster rather than `global`. The `global` location can route requests to any region, which may add latency. Set `apiEndpoint` to match, for example `location: europe-west1` with `apiEndpoint: europe-west1-aiplatform.googleapis.com`. Check that your model is available in the region you choose.

> [!NOTE]
>
> **Changed in `v1.38.20` and `v1.39.10`**
>
> You can [update](https://docs.weaviate.io/weaviate/manage-collections/collection-operations#update-a-collection-definition) `apiEndpoint`, `projectId` and `location` on an existing collection. This lets you switch a collection between Google AI Studio (`apiEndpoint: generativelanguage.googleapis.com`) and Vertex AI, or move it to another project or region. Every other vectorizer setting, including `modelId` and `dimensions`, stays immutable. Weaviate does not check that the new endpoint serves the collection's model. If it does not, vectorization fails until the collection points at an endpoint that serves the model.

`dimensions` defaults to `768` for backward compatibility with the earlier `textembedding-gecko@001` and `embedding-001` models. `gemini-embedding-001` produces 3072 dimensions natively, so leaving the default in place truncates its output. Set `dimensions` explicitly if you want the model's full vector.

**`taskType` parameter**

`taskType` tells Google what the embeddings are for, and it changes the vectors the model returns, so it affects retrieval quality. The accepted values are `RETRIEVAL_QUERY` (the default), `QUESTION_ANSWERING`, `FACT_VERIFICATION`, `CODE_RETRIEVAL_QUERY`, `CLASSIFICATION`, `CLUSTERING`, and `SEMANTIC_SIMILARITY`. For the retrieval task types, Weaviate sends the matching document task type when it embeds objects and the query task type when it embeds a search query. `CLASSIFICATION`, `CLUSTERING`, and `SEMANTIC_SIMILARITY` are used for both.

**Python**

```py
from weaviate.classes.config import Configure

# For Vertex AI
client.collections.create(
    "DemoCollection",
    vector_config=Configure.Vectors.text2vec_google_vertex(
        name="title_vector",
        source_properties=["title"],
        project_id="<google-cloud-project-id>",  # Required for Vertex AI
        # Further options
        # model="<google-model-id>",
        # location="<google-cloud-region>",
        # api_endpoint="<google-api-endpoint>",
    ),
    # Additional parameters not shown
)

# clean up
client.collections.delete("DemoCollection")

# For Google AI Studio (Gemini API)
client.collections.create(
    "DemoCollection",
    vector_config=Configure.Vectors.text2vec_google_gemini(
        name="title_vector",
        source_properties=["title"],
        # Further options
        model="gemini-embedding-2",
    ),
    # Additional parameters not shown
)
```

**JavaScript/TypeScript**

```ts
await client.collections.create({
  name: 'DemoCollection',
  properties: [
    {
      name: 'title',
      dataType: 'text' as const,
    },
  ],
  vectorizers: [
    weaviate.configure.vectors.text2VecGoogle({
      name: 'title_vector',
      sourceProperties: ['title'],
      projectId: '<google-cloud-project-id>', // Required for Vertex AI
      // modelId: '<google-model-id>',
      // apiEndpoint: '<google-api_endpoint>',
      // vectorizeClassName: false,
    }),
  ],
  // Additional parameters not shown
});
```

**Go (v5)**

```go
// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    // Define the collection
    googleVectorizerFullDef := &models.Class{
        Class: "DemoCollection",
        VectorConfig: map[string]models.VectorConfig{
            "title_vector": {
                Vectorizer: map[string]interface{}{
                    "text2vec-google": map[string]interface{}{
                        "properties":  []string{"title"},
                        "projectId":   "<google-cloud-project-id>",  // Required for Vertex AI
                        "modelId":     "textembedding-gecko@latest", // (Optional) To manually set the model ID
                        "apiEndpoint": "<google-api-endpoint>",      // (Optional) To manually set the API endpoint
                    },
                },
            },
        },
    }

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

## Data import

After configuring the vectorizer, [import data](https://docs.weaviate.io/weaviate/manage-objects/import) into Weaviate. Weaviate generates embeddings for text objects using the specified model.

**Python**

```py
source_objects = [
    {"title": "The Shawshank Redemption", "description": "A wrongfully imprisoned man forms an inspiring friendship while finding hope and redemption in the darkest of places."},
    {"title": "The Godfather", "description": "A powerful mafia family struggles to balance loyalty, power, and betrayal in this iconic crime saga."},
    {"title": "The Dark Knight", "description": "Batman faces his greatest challenge as he battles the chaos unleashed by the Joker in Gotham City."},
    {"title": "Jingle All the Way", "description": "A desperate father goes to hilarious lengths to secure the season's hottest toy for his son on Christmas Eve."},
    {"title": "A Christmas Carol", "description": "A miserly old man is transformed after being visited by three ghosts on Christmas Eve in this timeless tale of redemption."}
]

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

with collection.batch.fixed_size(batch_size=200) as batch:
    for src_obj in source_objects:
        # The model provider integration will automatically vectorize the object
        batch.add_object(
            properties={
                "title": src_obj["title"],
                "description": src_obj["description"],
            },
            # vector=vector  # Optionally provide a pre-obtained vector
        )
        if batch.number_errors > 10:
            print("Batch import stopped due to excessive errors.")
            break

failed_objects = collection.batch.failed_objects
if failed_objects:
    print(f"Number of failed imports: {len(failed_objects)}")
    print(f"First failed object: {failed_objects[0]}")
```

**JavaScript/TypeScript**

```ts
let srcObjects = [
  { title: "The Shawshank Redemption", description: "A wrongfully imprisoned man forms an inspiring friendship while finding hope and redemption in the darkest of places." },
  { title: "The Godfather", description: "A powerful mafia family struggles to balance loyalty, power, and betrayal in this iconic crime saga." },
  { title: "The Dark Knight", description: "Batman faces his greatest challenge as he battles the chaos unleashed by the Joker in Gotham City." },
  { title: "Jingle All the Way", description: "A desperate father goes to hilarious lengths to secure the season's hottest toy for his son on Christmas Eve." },
  { title: "A Christmas Carol", description: "A miserly old man is transformed after being visited by three ghosts on Christmas Eve in this timeless tale of redemption." }
];

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

let dataObjects = new Array();

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

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

console.log(response);
```

**Go (v5)**

```go
// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    var sourceObjects = []map[string]string{
        {"title": "The Shawshank Redemption", "description": "A wrongfully imprisoned man forms an inspiring friendship while finding hope and redemption in the darkest of places."},
        {"title": "The Godfather", "description": "A powerful mafia family struggles to balance loyalty, power, and betrayal in this iconic crime saga."},
        {"title": "The Dark Knight", "description": "Batman faces his greatest challenge as he battles the chaos unleashed by the Joker in Gotham City."},
        {"title": "Jingle All the Way", "description": "A desperate father goes to hilarious lengths to secure the season's hottest toy for his son on Christmas Eve."},
        {"title": "A Christmas Carol", "description": "A miserly old man is transformed after being visited by three ghosts on Christmas Eve in this timeless tale of redemption."},
    }

    // 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
            "title":       sourceObjects[i]["title"],
            "description": sourceObjects[i]["description"],
        })
    }

    // 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)
                }
            }
        }
    }
}
```

> [!TIP]
>
> **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 model.

![Embedding integration at search illustration](https://docs.weaviate.io/assets/images/integration_google_embedding_search-aac2a6f4ddc35cbbf95d9c2cb8ffe813.png)

### Vector (near text) search

When you perform a [vector search](https://docs.weaviate.io/weaviate/search/similarity#search-with-text), 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**

```py
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**

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

**Go (v5)**

```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)
}
```

### Hybrid search

> [!NOTE]
>
> **What is a hybrid search?**
>
> A hybrid search performs a vector search and a keyword (BM25) search, before [combining the results](https://docs.weaviate.io/weaviate/search/hybrid) to return the best matching objects from the database.

When you perform a [hybrid search](https://docs.weaviate.io/weaviate/search/hybrid), 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**

```py
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**

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

**Go (v5)**

```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)
}
```

## References

### Available models

**Google AI Studio (Gemini API):**

- `gemini-embedding-2`
- `gemini-embedding-001` (default)

**Vertex AI:**

`gemini-embedding-001`, `text-embedding-005`, and `text-multilingual-embedding-002` were added in `v1.31.5`, and backported to `v1.30.11`.

- `gemini-embedding-2`
- `gemini-embedding-001` (default)
- `text-embedding-005`
- `text-multilingual-embedding-002`

**Deprecated models**

The following models have been deprecated by Google and are no longer supported. They may not function as expected.

- `text-embedding-004`
- `embedding-001`
- `textembedding-gecko@001`
- `textembedding-gecko@002`
- `textembedding-gecko@003`
- `textembedding-gecko@latest`
- `textembedding-gecko-multilingual@001`
- `textembedding-gecko-multilingual@latest`
- `text-embedding-preview-0409`
- `text-multilingual-embedding-preview-0409`

## Further resources

### Other integrations

- [Google generative models + Weaviate](https://docs.weaviate.io/weaviate/model-providers/google/generative).

### 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](https://docs.weaviate.io/weaviate/manage-collections) and [How-to: Manage objects](https://docs.weaviate.io/weaviate/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](https://docs.weaviate.io/weaviate/search) guides show how to perform search operations (i.e. vector, keyword, hybrid) as well as retrieval augmented generation.

### External resources

- [Google Vertex AI](https://cloud.google.com/vertex-ai)
- [Google Gemini API](https://ai.google.dev/?utm_source=weaviate\&utm_medium=referral\&utm_campaign=partnerships\&utm_content=)
