Web Grounding for Enterprise

This page describes Web Grounding for Enterprise compliance controls and how to use the Web Grounding for Enterprise API to generate responses that are grounded on the web. The indexed content is a subset of what's available on Google Search and suitable for customers in highly-regulated industries, such as finance, healthcare, and the public sector.

If you don't require the compliance controls, use Ground with Google Search, because it offers access to a broader web index.

Overview

Web Grounding for Enterprise uses a web index that is used to generate grounded responses. The web index supports the following:

• ML processing in the US or European multi-regions
• No logging of customer data
• VPC Service Controls

Because no customer data is persisted, customer-managed encryption keys (CMEK) and Access Transparency (AxT) aren't applicable.

Use the API

This section provides sample requests of using the Generative AI API Gemini 2 on Vertex AI to create grounded responses with Gemini. To use the API, you must set the following fields:

• Contents.parts.text: The text query users want to send to the API.
• tools.enterpriseWebSearch: When this tool is provided, Web Grounding for Enterprise can be used by Gemini.

pip install --upgrade google-genai

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

from google import genai
from google.genai.types import (
    EnterpriseWebSearch,
    GenerateContentConfig,
    HttpOptions,
    Tool,
)

client = genai.Client(http_options=HttpOptions(api_version="v1"))

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="When is the next total solar eclipse in the United States?",
    config=GenerateContentConfig(
        tools=[
            # Use Enterprise Web Search Tool
            Tool(enterprise_web_search=EnterpriseWebSearch())
        ],
    ),
)

print(response.text)
# Example response:
# 'The next total solar eclipse in the United States will occur on ...'

  curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" -H "x-server-timeout: 60" https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_NUMBER/locations/LOCATION/publishers/google/models/gemini-2.0-flash:generateContent -d '
  {
    "contents": [{
      "role": "user",
      "parts": [{
        "text": TEXT
      }]
    }],
    "tools": [{
      "enterpriseWebSearch": {
      }
    }]
  }
  '

What's next

• To learn more about how to ground Gemini models to your data, see Grounding with Vertex AI Search.
• To learn more about responsible AI best practices and Vertex AI's safety filters, see Responsible AI.