BigQuery의 Gemini 일부 기능은 추가 비용 없이 사용할 수 있지만 다른 기능에는 컴퓨팅 용량을 사용하여 획득한 할당량이 필요합니다. BigQuery의 Gemini 기능 사용에 대해 자세히 알아보려면 BigQuery의 Gemini 가격 책정을 참조하세요.
필요한 API 사용 설정 및 역할 부여
BigQuery의 Gemini를 사용하려면 필수 API를 사용 설정하고 필요한 Identity and Access Management(IAM) 역할을 부여해야 합니다. 일반적으로 serviceusage.services.enable IAM 권한이 있는 서비스 관리자나 프로젝트 소유자가 이 단계를 수행합니다.
Google Cloud 콘솔에서 프로젝트를 선택한 후 BigQuery Studio 페이지로 이동합니다.
특정 BigQuery의 Gemini 기능을 사용하여 SQL 쿼리와 Python 코드를 작성하려는 데이터 분석가, 데이터 과학자 또는 개발자라면 Google Cloud 콘솔에서 이 기능을 사용 설정해야 합니다. 기능을 사용 설정하는 방법을 알아보려면 'Gemini 지원으로 쿼리 작성'의 시작하기 전에를 참조하세요.
필요한 IAM 역할이나 권한이 있는 사용자는 Google Cloud 프로젝트에 사용 설정된 BigQuery의 Gemini 기능에 액세스할 수 있습니다. 자세한 내용은 Google Cloud 를 위한 Gemini 개요를 참조하세요.
데이터 통계 및 자동 메타데이터 생성 기능 사용
BigQuery 데이터 통계 및 자동 메타데이터 생성 기능은 BigQuery 주문형 컴퓨팅, Enterprise 버전 또는 Enterprise Plus 버전을 사용하는 고객에게 제공됩니다. 데이터 통계 스캔 및 메타데이터 생성의 할당량은 조직 수준에서 이러한 컴퓨팅 모델을 사용량을 기준으로 합니다. 이러한 기능의 할당량에 대한 자세한 내용은 BigQuery의 Gemini 할당량을 참조하세요.
미리보기 버전의 특정 BigQuery의 Gemini 기능은 신뢰할 수 있는 테스터 프로그램의 일부입니다. 이러한 기능에 대한 액세스를 요청하려면 관리자가 BigQuery의 Gemini GA 이전 가입 양식을 작성해야 합니다.
BigQuery의 Gemini GA 이전 기능 액세스는 주기적으로 일괄 사용 설정됩니다.
[[["이해하기 쉬움","easyToUnderstand","thumb-up"],["문제가 해결됨","solvedMyProblem","thumb-up"],["기타","otherUp","thumb-up"]],[["이해하기 어려움","hardToUnderstand","thumb-down"],["잘못된 정보 또는 샘플 코드","incorrectInformationOrSampleCode","thumb-down"],["필요한 정보/샘플이 없음","missingTheInformationSamplesINeed","thumb-down"],["번역 문제","translationIssue","thumb-down"],["기타","otherDown","thumb-down"]],["최종 업데이트: 2025-07-21(UTC)"],[[["\u003cp\u003eTo use Gemini in BigQuery, you must purchase either the Enterprise Plus edition or Gemini Code Assist Enterprise edition.\u003c/p\u003e\n"],["\u003cp\u003eEnabling Gemini in BigQuery requires enabling the Gemini for Google Cloud API and, optionally, the Recommender API for certain features.\u003c/p\u003e\n"],["\u003cp\u003eGranting users access to Gemini in BigQuery involves assigning them the Gemini for Google Cloud User IAM role, along with other feature-specific roles if needed.\u003c/p\u003e\n"],["\u003cp\u003eCertain preview features, like SQL query completion and Apache Spark assisted troubleshooting, require signing up through the Gemini in BigQuery Pre-GA Sign-up form.\u003c/p\u003e\n"],["\u003cp\u003eData analysts, scientists, or developers need to turn on Gemini in BigQuery features in the Google Cloud console to utilize AI-assisted SQL query and Python code writing.\u003c/p\u003e\n"]]],[],null,["# Set up Gemini in BigQuery\n\nBefore you can use\n[Gemini in BigQuery](/gemini/docs/bigquery/overview), which\noffers AI-powered assistance for your data analytics, your team must do\nthe following:\n\n1. [Enable necessary APIs and grant roles.](#enable-api)\n2. [Turn on Gemini in BigQuery features in\n the Google Cloud console.](#use)\n\nSome Gemini in BigQuery features are available at no\nadditional charge while other features require [quota](/gemini/docs/quotas#bigquery)\nwhich is earned by using compute capacity. To learn more about using\nGemini in BigQuery features, see [Gemini\nin BigQuery pricing](/gemini/pricing#gemini-in-bigquery-pricing).\n| **Note** : Gemini in BigQuery is part of Gemini for Google Cloud and doesn't support the same compliance and security offerings as BigQuery. You should only set up Gemini in BigQuery for BigQuery projects that don't require [compliance offerings that aren't supported by Gemini for Google Cloud](/gemini/docs/discover/certifications). For information about how to turn off or prevent access to Gemini in BigQuery, see [Turn off Gemini for Google Cloud products](/gemini/docs/turn-off-gemini).\n\nEnable necessary APIs and grant roles\n-------------------------------------\n\nTo use Gemini in BigQuery,\nyou must enable required APIs and grant necessary Identity and Access Management (IAM)\nroles. A service administrator or project\nowner with the [`serviceusage.services.enable` IAM permission](/service-usage/docs/access-control#predefined_roles)\ntypically performs this step. For a list of APIs and services used by\nBigQuery, see [Manage BigQuery API dependencies](/bigquery/docs/service-dependencies).\n\n1. In the the Google Cloud console, with your project selected, go to the\n **BigQuery Studio** page.\n\n [Go to BigQuery Studio](https://console.cloud.google.com/bigquery)\n2. View a Gemini in BigQuery feature in the\n the Google Cloud console. For example, in BigQuery Studio hover\n over the\n pen_sparkarrow_drop_down**Gemini**\n icon.\n\n You are prompted to enable additional Google Cloud APIs.\n3. Click **Continue** to get started enabling required\n Google Cloud APIs. A side panel lists the required APIs\n required to use Gemini in BigQuery.\n\n4. For each required API, click **Enable** to enable the API for the current\n project, and then click **Next**.\n\n5. To grant principals the IAM roles that are required to use\n Gemini in BigQuery, enter their user names.\n The following roles grant the permissions required to use Gemini:\n\n - [BigQuery Studio User](/bigquery/docs/access-control#bigquery.studioUser)\n - [BigQuery Studio Admin](/bigquery/docs/access-control#bigquery.studioAdmin)\n6. Click **Done**.\n\nTurn on Gemini in BigQuery features\n-----------------------------------\n\nIf you're a data analyst, data scientist, or developer who wants to use\nspecific Gemini in BigQuery features to write\nSQL queries and Python code, then you need to turn on the feature in\nthe Google Cloud console. To learn how to turn on features, see\n[Before you begin](/bigquery/docs/write-sql-gemini#before_you_begin) in\n\"Write queries with Gemini assistance.\"\nUsers who have the necessary IAM roles or permissions can then access\nthe Gemini in BigQuery features that you enabled\nfor their Google Cloud project. For more information, see\n[Gemini for Google Cloud overview](/gemini/docs/overview).\n\n### Use data insights and automated metadata generation features\n\nBigQuery data insights and automated metadata generation features\nare available to customers using BigQuery on-demand compute,\nEnterprise edition, or Enterprise Plus edition. The quota for\ndata insights scans and metadata generation is based on the use of these\ncompute models at the\norganization level. For information about quotas for these features, see\n[Quotas for Gemini in BigQuery](/gemini/docs/quotas#bigquery).\n\nIf your organization is using BigQuery Standard edition\nfor compute only, then you can use Gemini Code Assist Standard, which\nincludes data insights and automated metadata generation capabilities in\naddition to features listed in [Gemini Code Assist Standard and\nEnterprise pricing\noverview](/products/gemini/pricing#gemini_code_assist_standard_and_enterprise_pricing_overview).\nTo learn how to purchase Gemini Code Assist Standard, see [Purchase a\nGemini Code Assist Standard\nsubscription](/gemini/docs/discover/set-up-gemini#purchase-subscription) and\nfollow the instructions to purchase Standard edition.\n\n### Enable Gemini in BigQuery preview features\n\nCertain Gemini in BigQuery features in\n[Preview](/products#product-launch-stages)\nare part of the trusted tester program. To request access to these features,\nan administrator must complete the\n[Gemini in BigQuery Pre-GA Sign-up form](https://goo.gle/gemini-in-bq-preview).\nGemini in BigQuery pre-GA feature access is\nenabled periodically in batches.\n\nPreview features that require Gemini in BigQuery\nsign-up include the following:\n\n- SQL query completion (Preview)\n- Automated metadata generation for data insights (Preview)\n- Natural language expressions in SQL (Experimental)\n- Dataset insights with BigQuery knowledge engine (Preview)\n\nWhat's next\n-----------\n\n- Learn more about the [types of generative AI assistance available in Gemini for Google Cloud](/gemini/docs/overview).\n- Learn [how Gemini for Google Cloud uses your data](/gemini/docs/discover/data-governance).\n- Learn [how to access and manage Gemini administrator controls](/gemini/docs/admin)."]]
