Grounding with Google Search

from google import genai
from google.genai import types

# Configure the client
client = genai.Client()

# Define the grounding tool
grounding_tool = types.Tool(
    google_search=types.GoogleSearch()
)

# Configure generation settings
config = types.GenerateContentConfig(
    tools=[grounding_tool]
)

# Make the request
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Who won the euro 2024?",
    config=config,
)

# Print the grounded response
print(response.text)

import { GoogleGenAI } from "@google/genai";

// Configure the client
const ai = new GoogleGenAI({});

// Define the grounding tool
const groundingTool = {
  googleSearch: {},
};

// Configure generation settings
const config = {
  tools: [groundingTool],
};

// Make the request
const response = await ai.models.generateContent({
  model: "gemini-2.5-flash",
  contents: "Who won the euro 2024?",
  config,
});

// Print the grounded response
console.log(response.text);

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -X POST \
  -d '{
    "contents": [
      {
        "parts": [
          {"text": "Who won the euro 2024?"}
        ]
      }
    ],
    "tools": [
      {
        "google_search": {}
      }
    ]
  }'

def add_citations(response):
    text = response.text
    supports = response.candidates[0].grounding_metadata.grounding_supports
    chunks = response.candidates[0].grounding_metadata.grounding_chunks

    # Sort supports by end_index in descending order to avoid shifting issues when inserting.
    sorted_supports = sorted(supports, key=lambda s: s.segment.end_index, reverse=True)

    for support in sorted_supports:
        end_index = support.segment.end_index
        if support.grounding_chunk_indices:
            # Create citation string like [1](link1)[2](link2)
            citation_links = []
            for i in support.grounding_chunk_indices:
                if i < len(chunks):
                    uri = chunks[i].web.uri
                    citation_links.append(f"[{i + 1}]({uri})")

            citation_string = ", ".join(citation_links)
            text = text[:end_index] + citation_string + text[end_index:]

    return text

# Assuming response with grounding metadata
text_with_citations = add_citations(response)
print(text_with_citations)

function addCitations(response) {
    let text = response.text;
    const supports = response.candidates[0]?.groundingMetadata?.groundingSupports;
    const chunks = response.candidates[0]?.groundingMetadata?.groundingChunks;

    // Sort supports by end_index in descending order to avoid shifting issues when inserting.
    const sortedSupports = [...supports].sort(
        (a, b) => (b.segment?.endIndex ?? 0) - (a.segment?.endIndex ?? 0),
    );

    for (const support of sortedSupports) {
        const endIndex = support.segment?.endIndex;
        if (endIndex === undefined || !support.groundingChunkIndices?.length) {
        continue;
        }

        const citationLinks = support.groundingChunkIndices
        .map(i => {
            const uri = chunks[i]?.web?.uri;
            if (uri) {
            return `[${i + 1}](${uri})`;
            }
            return null;
        })
        .filter(Boolean);

        if (citationLinks.length > 0) {
        const citationString = citationLinks.join(", ");
        text = text.slice(0, endIndex) + citationString + text.slice(endIndex);
        }
    }

    return text;
}

const textWithCitations = addCitations(response);
console.log(textWithCitations);

# Note: This is a legacy approach for Gemini 1.5 models.
# The 'google_search' tool is recommended for all new development.
import os
from google import genai
from google.genai import types

client = genai.Client()

retrieval_tool = types.Tool(
    google_search_retrieval=types.GoogleSearchRetrieval(
        dynamic_retrieval_config=types.DynamicRetrievalConfig(
            mode=types.DynamicRetrievalConfigMode.MODE_DYNAMIC,
            dynamic_threshold=0.7 # Only search if confidence > 70%
        )
    )
)

config = types.GenerateContentConfig(
    tools=[retrieval_tool]
)

response = client.models.generate_content(
    model='gemini-1.5-flash',
    contents="Who won the euro 2024?",
    config=config,
)
print(response.text)
if not response.candidates[0].grounding_metadata:
  print("\nModel answered from its own knowledge.")

// Note: This is a legacy approach for Gemini 1.5 models.
// The 'googleSearch' tool is recommended for all new development.
import { GoogleGenAI, DynamicRetrievalConfigMode } from "@google/genai";

const ai = new GoogleGenAI({});

const retrievalTool = {
  googleSearchRetrieval: {
    dynamicRetrievalConfig: {
      mode: DynamicRetrievalConfigMode.MODE_DYNAMIC,
      dynamicThreshold: 0.7, // Only search if confidence > 70%
    },
  },
};

const config = {
  tools: [retrievalTool],
};

const response = await ai.models.generateContent({
  model: "gemini-1.5-flash",
  contents: "Who won the euro 2024?",
  config,
});

console.log(response.text);
if (!response.candidates?.[0]?.groundingMetadata) {
  console.log("\nModel answered from its own knowledge.");
}

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \

  -H "Content-Type: application/json" \
  -X POST \
  -d '{
    "contents": [
      {"parts": [{"text": "Who won the euro 2024?"}]}
    ],
    "tools": [{
      "google_search_retrieval": {
        "dynamic_retrieval_config": {
          "mode": "MODE_DYNAMIC",
          "dynamic_threshold": 0.7
        }
      }
    }]
  }'