# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values# with appropriate values for your project.exportGOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECTexportGOOGLE_CLOUD_LOCATION=globalexportGOOGLE_GENAI_USE_VERTEXAI=True
fromgoogleimportgenaifromgoogle.genai.typesimport(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 ToolTool(enterprise_web_search=EnterpriseWebSearch())],),)print(response.text)# Example response:# 'The next total solar eclipse in the United States will occur on ...'
[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["難以理解","hardToUnderstand","thumb-down"],["資訊或程式碼範例有誤","incorrectInformationOrSampleCode","thumb-down"],["缺少我需要的資訊/範例","missingTheInformationSamplesINeed","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間:2025-09-04 (世界標準時間)。"],[],[],null,["# Web Grounding for Enterprise\n\nThis page describes Web Grounding for Enterprise compliance controls and how to use\nthe Web Grounding for Enterprise API to generate responses that are grounded on the\nweb. The indexed content is a subset of what's available on\nGoogle Search and suitable for customers in highly-regulated\nindustries, such as finance, healthcare, and the public sector.\n\nIf you don't require the compliance controls, use [Ground with\nGoogle Search](/vertex-ai/generative-ai/docs/grounding/ground-with-google-search),\nbecause it offers access to a broader web index.\n\nOverview\n--------\n\nWeb Grounding for Enterprise uses a web index that is used to generate grounded\nresponses. The web index supports the following:\n\n- ML processing in the US or European multi-regions\n- No logging of customer data\n- [VPC Service Controls](/vertex-ai/generative-ai/docs/security-controls)\n\nBecause no customer data is persisted, customer-managed encryption keys (CMEK)\nand Access Transparency (AxT) aren't applicable.\n\nUse the API\n-----------\n\nThis section provides sample requests of using the Generative AI API [Gemini 2](/vertex-ai/generative-ai/docs/gemini-v2) on\nVertex AI to create grounded responses with Gemini. To use the API, you\nmust set the following fields:\n\n- **`Contents.parts.text`**: The text query users want to send to the API.\n- **`tools.enterpriseWebSearch`**: When this tool is provided, Web Grounding for Enterprise can be used by Gemini.\n\n### Python\n\n#### Install\n\n```\npip install --upgrade google-genai\n```\n\n\nTo learn more, see the\n[SDK reference documentation](https://googleapis.github.io/python-genai/).\n\n\nSet environment variables to use the Gen AI SDK with Vertex AI:\n\n```bash\n# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values\n# with appropriate values for your project.\nexport GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT\nexport GOOGLE_CLOUD_LOCATION=global\nexport GOOGLE_GENAI_USE_VERTEXAI=True\n```\n\n\u003cbr /\u003e\n\n from google import genai\n from google.genai.types import (\n EnterpriseWebSearch,\n GenerateContentConfig,\n HttpOptions,\n Tool,\n )\n\n client = genai.Client(http_options=HttpOptions(api_version=\"v1\"))\n\n response = client.models.generate_content(\n model=\"gemini-2.5-flash\",\n contents=\"When is the next total solar eclipse in the United States?\",\n config=GenerateContentConfig(\n tools=[\n # Use Enterprise Web Search Tool\n Tool(enterprise_web_search=EnterpriseWebSearch())\n ],\n ),\n )\n\n print(response.text)\n # Example response:\n # 'The next total solar eclipse in the United States will occur on ...'\n\n### REST\n\nReplace the following variables with values:\n\n- **\u003cvar translate=\"no\"\u003ePROJECT_NUMBER\u003c/var\u003e**: Your project number.\n- **\u003cvar translate=\"no\"\u003eLOCATION\u003c/var\u003e**: Your region.\n- **\u003cvar translate=\"no\"\u003eTEXT\u003c/var\u003e**: Your prompt.\n\n curl -X POST -H \"Authorization: Bearer $(gcloud auth print-access-token)\" -H \"Content-Type: application/json\" -H \"x-server-timeout: 60\" https://\u003cvar translate=\"no\"\u003eLOCATION\u003c/var\u003e-aiplatform.googleapis.com/v1/projects/\u003cvar translate=\"no\"\u003ePROJECT_NUMBER\u003c/var\u003e/locations/\u003cvar translate=\"no\"\u003eLOCATION\u003c/var\u003e/publishers/google/models/gemini-2.0-flash:generateContent -d '\n {\n \"contents\": [{\n \"role\": \"user\",\n \"parts\": [{\n \"text\": \u003cvar translate=\"no\"\u003eTEXT\u003c/var\u003e\n }]\n }],\n \"tools\": [{\n \"enterpriseWebSearch\": {\n }\n }]\n }\n '\n\n\u003cbr /\u003e\n\nWhat's next\n-----------\n\n- To learn more about how to ground Gemini models to your data, see [Grounding with Vertex AI Search](/vertex-ai/generative-ai/docs/grounding/grounding-with-vertex-ai-search).\n- To learn more about responsible AI best practices and Vertex AI's safety filters, see [Responsible AI](/vertex-ai/generative-ai/docs/learn/responsible-ai)."]]