Grounding with Google Search

Grounding with Google Search connects a Gemini model to real-time, publicly-available web content. This allows the model to provide more accurate, up-to-date answers and cite verifiable sources beyond its knowledge cutoff.

Grounding with Google Search has the following benefits:

Increase factual accuracy: Reduce model hallucinations by basing responses on real-world information.
Access real-time information: Answer questions about recent events and topics.
Provide citations: Build user trust or allow users to browse relevant sites by showing the sources for the model's claims.
Complete more complex tasks: Retrieve artifacts and relevant images, videos, or other media to assist in reasoning tasks.
Improve region or language-specific responses: Find region-specific information, or assist in translating content accurately.

Note that support for Grounding for Google Search is available for iOS+, Android, Web, and Flutter. It will be available for Unity in its upcoming release.

Supported models

gemini-2.5-pro
gemini-2.5-flash
gemini-2.5-flash-lite-preview-06-17
gemini-2.0-flash-001 (and its auto-updated alias gemini-2.0-flash)
gemini-2.0-flash-live-preview-04-09

Supported languages

See supported languages for Gemini models.

Ground the model with Google Search

Click your Gemini API provider to view provider-specific content and code on this page.

When you create the GenerativeModel instance, provide GoogleSearch as a tool that the model can use to generate its response.

Swift


import FirebaseAI

// Initialize the Gemini Developer API backend service
let ai = FirebaseAI.firebaseAI(backend: .googleAI())

// Create a `GenerativeModel` instance with a model that supports your use case
let model = ai.generativeModel(
    modelName: "GEMINI_MODEL_NAME",
    // Provide Google Search as a tool that the model can use to generate its response
    tools: [Tool.googleSearch()]
)

let response = try await model.generateContent("Who won the euro 2024?")
print(response.text ?? "No text in response.")

// Make sure to comply with the "Grounding with Google Search" usage requirements,
// which includes how you use and display the grounded result

Kotlin


// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
    modelName = "GEMINI_MODEL_NAME",
    // Provide Google Search as a tool that the model can use to generate its response
    tools = listOf(Tool.GoogleSearch())
)

val response = model.generateContent("Who won the euro 2024?")
print(response.text)

// Make sure to comply with the "Grounding with Google Search" usage requirements,
// which includes how you use and display the grounded result

Java


// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .generativeModel("GEMINI_MODEL_NAME",
                        null,
                        null,
                        // Provide Google Search as a tool that the model can use to generate its response
                        List.of(Tool.GoogleSearch()));

// Use the GenerativeModelFutures Java compatibility layer which offers
// support for ListenableFuture and Publisher APIs
GenerativeModelFutures model = GenerativeModelFutures.from(ai);

ListenableFuture response = model.generateContent("Who won the euro 2024?");
  Futures.addCallback(response, new FutureCallback() {
      @Override
      public void onSuccess(GenerateContentResponse result) {
          String resultText = result.getText();
          System.out.println(resultText);
      }

      @Override
      public void onFailure(Throwable t) {
          t.printStackTrace();
      }
  }, executor);

// Make sure to comply with the "Grounding with Google Search" usage requirements,
// which includes how you use and display the grounded result

Web


import { initializeApp } from "firebase/app";
import { getAI, getGenerativeModel, GoogleAIBackend } from "firebase/ai";

// TODO(developer) Replace the following with your app's Firebase configuration
// See: https://firebase.google.com/docs/web/learn-more#config-object
const firebaseConfig = {
  // ...
};

// Initialize FirebaseApp
const firebaseApp = initializeApp(firebaseConfig);

// Initialize the Gemini Developer API backend service
const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Create a `GenerativeModel` instance with a model that supports your use case
const model = getGenerativeModel(
  ai,
  {
    model: "GEMINI_MODEL_NAME",
    // Provide Google Search as a tool that the model can use to generate its response
    tools: [{ googleSearch: {} }]
  }
);

const result = await model.generateContent("Who won the euro 2024?");

console.log(result.response.text());

// Make sure to comply with the "Grounding with Google Search" usage requirements,
// which includes how you use and display the grounded result

Dart


import 'package:firebase_core/firebase_core.dart';
import 'package:firebase_ai/firebase_ai.dart';
import 'firebase_options.dart';

// Initialize FirebaseApp
await Firebase.initializeApp(
  options: DefaultFirebaseOptions.currentPlatform,
);

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
final model = FirebaseAI.googleAI().generativeModel(
  model: 'GEMINI_MODEL_NAME',
  // Provide Google Search as a tool that the model can use to generate its response
  tools: [
    Tool.googleSearch(),
  ],
);

final response = await model.generateContent([Content.text("Who won the euro 2024?")]);
print(response.text);

// Make sure to comply with the "Grounding with Google Search" usage requirements,
// which includes how you use and display the grounded result

Unity

Support for Unity is coming in its next release.

Learn how to choose a model appropriate for your use case and app.

For ideal results, use a temperature of 1.0 (which is the default for all 2.5 models). Learn how to set temperature in the model's configuration.

How grounding with Google Search works

When you use the GoogleSearch tool, the model handles the entire workflow of searching, processing, and citing information automatically.

Here's the workflow of the model:

Receive prompt: Your app sends a prompt to the Gemini model with the GoogleSearch tool enabled.
Analyze prompt: The model analyzes the prompt and determines if Google Search can improve its response.
Send queries to Google Search: If needed, the model automatically generates one or multiple search queries and executes them.
Process the Search results: The model processes the Google Search results and formulates a response to the original prompt.
Return a "grounded result": The model returns a final, user-friendly response that is grounded in the Google Search results. This response includes the model's text answer and groundingMetadata with the search queries, web results, and citations.

Note that providing Google Search as a tool to the model doesn't require the model to always use the Google Search tool to generate its response. In these cases, the response won't contain a groundingMetadata object and thus it's not a "grounded result".

Understand the grounded result

If the model grounds its response in Google Search results, then the response includes a groundingMetadata object that contains structured data that's essential for verifying claims and building a rich citation experience in your application.

The groundingMetadata object in a "grounded result" contains the following information:

webSearchQueries: An array of the search queries sent to Google Search. This information is useful for debugging and understanding the model's reasoning process.
searchEntryPoint: Contains the HTML and CSS to render the required "Google Search suggestions". You're required to comply with the "Grounding with Google Search" usage requirements for your chosen API provider: Gemini Developer API or Vertex AI Gemini API (see Service Terms section within the Service Specific Terms). Learn how to use and display a grounded result later on this page.
groundingChunks: An array of objects containing the web sources (uri and title).
groundingSupports: An array of chunks to connect model response text to the sources in groundingChunks. Each chunk links a text segment (defined by startIndex and endIndex) to one or more groundingChunkIndices. This field helps you build inline citations. Learn how to use and display a grounded result later on this page.

Here's an example response that includes a groundingMetadata object:

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "Spain won Euro 2024, defeating England 2-1 in the final. This victory marks Spain's record fourth European Championship title."
          }
        ],
        "role": "model"
      },
      "groundingMetadata": {
        "webSearchQueries": [
          "UEFA Euro 2024 winner",
          "who won euro 2024"
        ],
        "searchEntryPoint": {
          "renderedContent": "<!-- HTML and CSS for the search widget -->"
        },
        "groundingChunks": [
          {"web": {"uri": "https://vertexaisearch.cloud.google.com.....", "title": "aljazeera.com"}},
          {"web": {"uri": "https://vertexaisearch.cloud.google.com.....", "title": "uefa.com"}}
        ],
        "groundingSupports": [
          {
            "segment": {"startIndex": 0, "endIndex": 85, "text": "Spain won Euro 2024, defeatin..."},
            "groundingChunkIndices": [0]
          },
          {
            "segment": {"startIndex": 86, "endIndex": 210, "text": "This victory marks Spain's..."},
            "groundingChunkIndices": [0, 1]
          }
        ]
      }
    }
  ]
}

Use and display a grounded result

If the model uses the Google Search tool to generate a response, it will provide a groundingMetadata object in the response.

It's required to display Google Search suggestions and recommended to display citations.

Beyond complying with the requirements of using the Google Search tool, displaying this information helps you and your end users to validate responses and adds avenues for further learning.

(Required) Display Google Search suggestions

If a response contains "Google Search suggestions", then you're required to comply with the "Grounding with Google Search" usage requirements, which includes how you display Google Search suggestions.

The groundingMetadata object contains "Google Search suggestions", specifically the searchEntryPoint field, which has a renderedContent field that provides compliant HTML and CSS styling, which you need to implement to display Search suggestions in your app.

Review the detailed information about the display and behavior requirements for Google Search suggestions in the Google Cloud documentation. Note that even though this detailed guidance is in the Vertex AI Gemini API documentation, the guidance is applicable to the Gemini Developer API provider, as well.

See example code samples later in this section.

(Recommended) Display citations

The groundingMetadata object contains structured citation data, specifically the groundingSupports and groundingChunks fields. Use this information to link the model's statements directly to their sources within your UI (inline and in aggregate).

See example code samples later in this section.

Example code samples

These code samples provide generalized patterns for using and displaying the grounded result. However, it's your responsibility to make sure that your specific implementation aligns with the compliance requirements.

Swift

// ...

// Get the model's response
let text = response.text

// Get the grounding metadata
if let candidate = response.candidates.first,
   let groundingMetadata = candidate.groundingMetadata {
  // REQUIRED - display Google Search suggestions
  // (renderedContent contains HTML and CSS for the search widget)
  if let renderedContent = groundingMetadata.searchEntryPoint?.renderedContent {
    // TODO(developer): Display Google Search suggestions using a WebView
  }

  // RECOMMENDED - display citations
  let groundingChunks = groundingMetadata.groundingChunks
  for chunk in groundingMetadata.groundingChunks {
    if let web = chunk.web {
      let title = web.title  // for example, "uefa.com"
      let uri = web.uri  // for example, "https://vertexaisearch.cloud.google.com..."
      // TODO(developer): show citation in the UI
    }
  }
}

Kotlin

// ...

// Get the model's response
val text = response.text

// Get the grounding metadata
val groundingMetadata = response.candidates.firstOrNull()?.groundingMetadata

// REQUIRED - display Google Search suggestions
// (renderedContent contains HTML and CSS for the search widget)
val renderedContent = groundingMetadata?.searchEntryPoint?.renderedContent
if (renderedContent != null) {
    // TODO(developer): Display Google Search suggestions using a WebView
}

// RECOMMENDED - display citations
val groundingChunks = groundingMetadata?.groundingChunks
groundingChunks?.let { chunks ->
  for (chunk in chunks) {
  	val title = chunk.web?.title  // for example, "uefa.com"
	val uri = chunk.web?.uri  // for example, "https://vertexaisearch.cloud.google.com..."
// TODO(developer): show citation in the UI
  }
}

Java

// ...

Futures.addCallback(response, new FutureCallback() {
  @Override
  public void onSuccess(GenerateContentResponse result) {
  // Get the model's response
  String text = result.getText();

  // Get the grounding metadata
  GroundingMetadata groundingMetadata =
  result.getCandidates()[0].getGroundingMetadata();

  if (groundingMetadata != null) {
    // REQUIRED - display Google Search suggestions
  // (renderedContent contains HTML and CSS for the search widget)
    String renderedContent =
  groundingMetadata.getSearchEntryPoint().getRenderedContent();
    if (renderedContent != null) {
      // TODO(developer): Display Google Search suggestions using a WebView
    }

    // RECOMMENDED - display citations
    List chunks = groundingMetadata.getGroundingChunks();
    if (chunks != null) {
      for(GroundingChunk chunk : chunks) {
        WebGroundingChunk web = chunk.getWeb();
        if (web != null) {
          String title = web.getTitle();  // for example, "uefa.com"
          String uri = web.getUri();  // for example, "https://vertexaisearch.cloud.google.com..."
          // TODO(developer): show citation in the UI
        }
      }
    }
  }
  }

  @Override
  public void onFailure(Throwable t) {
  t.printStackTrace();
  }
  }, executor);

Web

// ...

// Get the model's text response
const text = result.response.text();

// Get the grounding metadata
const groundingMetadata = result.response.candidates?.[0]?.groundingMetadata;

// REQUIRED - display Google Search suggestions
// (renderedContent contains HTML and CSS for the search widget)
const renderedContent = groundingMetadata?.searchEntryPoint?.renderedContent;
if (renderedContent) {
  // TODO(developer): render this HTML and CSS in the UI
}

// RECOMMENDED - display citations
const groundingChunks = groundingMetadata?.groundingChunks;
if (groundingChunks) {
  for (const chunk of groundingChunks) {
    const title = chunk.web?.title;  // for example, "uefa.com"
    const uri = chunk.web?.uri;  // for example, "https://vertexaisearch.cloud.google.com..."
    // TODO(developer): show citation in the UI
  }
}

Dart

// ...

// Get the model's response
final text = response.text;

// Get the grounding metadata
final groundingMetadata = response.candidates.first.groundingMetadata;

// REQUIRED - display Google Search suggestions
// (renderedContent contains HTML and CSS for the search widget)
final renderedContent = groundingMetadata?.searchEntryPoint?.renderedContent;
if (renderedContent != null) {
    // TODO(developer): Display Google Search suggestions using a WebView
}

// RECOMMENDED - display citations
final groundingChunks = groundingMetadata?.groundingChunks;
if (groundingChunks != null) {
  for (var chunk in groundingChunks) {
    final title = chunk.web?.title;  // for example, "uefa.com"
    final uri = chunk.web?.uri;  // for example, "https://vertexaisearch.cloud.google.com..."
    // TODO(developer): show citation in the UI
  }
}

Unity

Support for Unity is coming in its next release.

Grounded results and AI monitoring in the Firebase console

If you've enabled AI monitoring in the Firebase console, responses are stored in Cloud Logging. By default, this data has a 30-day retention period.

It's your responsibility to ensure that this retention period, or any custom period you set, fully aligns with your specific use case and any additional compliance requirements for your chosen Gemini API provider: Gemini Developer API or Vertex AI Gemini API (see Service Terms section within the Service Specific Terms). You may need to adjust the retention period in Cloud Logging to meet these requirements.

Pricing and limits

Make sure to review pricing, model availability, and limits for grounding with Google Search in your chosen Gemini API provider documentation: Gemini Developer API | Vertex AI Gemini API.

Grounding with Google Search Stay organized with collections Save and categorize content based on your preferences.

Supported models

Supported languages

Ground the model with Google Search

Swift

Kotlin

Java

Web

Dart

Unity

How grounding with Google Search works

Understand the grounded result

Use and display a grounded result

(Required) Display Google Search suggestions

(Recommended) Display citations

Example code samples

Swift

Kotlin

Java

Web

Dart

Unity

Grounded results and AI monitoring in the Firebase console

Pricing and limits

Grounding with Google Search