為提供準確的結果，Gemini in BigQuery 需要存取您儲存在 BigQuery 的客戶資料和中繼資料，以便提供強化功能。啟用 Gemini in BigQuery 之後，Gemini 會取得這類資料的存取權限，包括您的資料表和查詢記錄。Gemini in BigQuery 不會使用您的資料訓練或微調模型。如要進一步瞭解 Gemini 如何使用您的資料，請參閱「Gemini for Google Cloud 如何使用您的資料」一文。
[[["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)。"],[[["\u003cp\u003eGemini in BigQuery offers AI-powered assistance to explore, understand, and analyze your data by using data insights, and data canvas features.\u003c/p\u003e\n"],["\u003cp\u003eYou can utilize Gemini in BigQuery to generate, complete, and explain SQL and Python code, as well as translate SQL code.\u003c/p\u003e\n"],["\u003cp\u003eGemini in BigQuery helps optimize your data infrastructure with recommendations for partitioning, clustering, and materialized views.\u003c/p\u003e\n"],["\u003cp\u003eWith Gemini in BigQuery you can use the Data preparation tool to get AI-generated data transformation recommendations to prepare your data for analysis.\u003c/p\u003e\n"],["\u003cp\u003eGemini in BigQuery allows for advanced troubleshooting of serverless Apache Spark workloads by explaining job errors and offering actionable recommendations.\u003c/p\u003e\n"]]],[],null,["# Gemini in BigQuery overview\n\nThis document describes how Gemini in BigQuery, which is part\nof the [Gemini for Google Cloud](/gemini/docs/overview) product suite,\nprovides AI-powered assistance to help you work with your data.\n\nAI assistance with Gemini in BigQuery\n-------------------------------------\n\nGemini in BigQuery provides AI assistance to help\nyou do the following:\n\n- **Explore and understand your data with data insights** . Data insights offers an automated, intuitive way to uncover patterns and perform statistical analysis by using insightful queries that are generated from the metadata of your tables. This feature is especially helpful in addressing the cold-start challenges of early data exploration. For more information, see [Generate data insights in BigQuery](/bigquery/docs/data-insights).\n- **Discover, transform, query, and visualize data with BigQuery data canvas** . You can use natural language with Gemini in BigQuery, to find, join, and query table assets, visualize results, and seamlessly collaborate with others throughout the entire process. For more information, see [Analyze with\n data canvas](/bigquery/docs/data-canvas).\n- **Get assisted SQL and Python data analysis** . You can use Gemini in BigQuery to generate or suggest code in either SQL or Python, and to explain an existing SQL query. You can also use natural language queries to begin data analysis. To learn how to generate, complete, and summarize code, see the following documentation: \n - SQL code assist\n - [Use the SQL generation tool](/bigquery/docs/write-sql-gemini#use_the_sql_generation_tool)\n - [Prompt to generate SQL queries](/bigquery/docs/write-sql-gemini#chat)\n - [Generate SQL queries with Gemini Cloud Assist](/bigquery/docs/write-sql-gemini#chat) ([Preview](/products#product-launch-stages))\n - [Complete a SQL query](/bigquery/docs/write-sql-gemini#complete_a_sql_query) ([Preview](/products#product-launch-stages))\n - [Explain a SQL query](/bigquery/docs/write-sql-gemini#explain_a_sql_query)\n - Python code assist\n - [Generate Python code with the code generation tool](/bigquery/docs/write-sql-gemini#generate_python_code)\n - [Generate Python code with Gemini Cloud Assist](/bigquery/docs/write-sql-gemini#chat-python) ([Preview](/products#product-launch-stages))\n - [Python code completion](/bigquery/docs/write-sql-gemini#python_code_completion)\n - [Generate BigQuery DataFrames Python code](/bigquery/docs/write-sql-gemini#dataframe) ([Preview](/products#product-launch-stages))\n- **Prepare data for analysis** . Data preparation in BigQuery gives you context aware, AI-generated transformation recommendations to cleanse data for analysis. For more information, see [Prepare data with Gemini](/bigquery/docs/data-prep-get-suggestions).\n- **Customize your SQL translations with translation rules** . ([Preview](/products#product-launch-stages)) Create Gemini-enhanced translation rules to customize your SQL translations when using the [interactive SQL translator](/bigquery/docs/interactive-sql-translator). You can describe changes to the SQL translation output using natural language prompts or specify SQL patterns to find and replace. For more information, see [Create a translation\n rule](/bigquery/docs/interactive-sql-translator#create_a_translation_rule).\n\nGemini for Google Cloud doesn't use your prompts or its\nresponses as data to train its models without your express permission. For more\ninformation about how Google uses your data, see\n[How Gemini for Google Cloud uses your data](/gemini/docs/discover/data-governance).\n| As an early-stage technology, Gemini for Google Cloud\n| products can generate output that seems plausible but is factually incorrect. We recommend that you\n| validate all output from Gemini for Google Cloud products before you use it.\n| For more information, see\n| [Gemini for Google Cloud and responsible AI](/gemini/docs/discover/responsible-ai).\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\nPricing\n-------\n\nSee [Gemini for Google Cloud pricing](/products/gemini/pricing).\n\nQuotas and limits\n-----------------\n\nFor quotas and limits that apply to Gemini in BigQuery,\nsee [Gemini for Google Cloud quotas and limits](/gemini/docs/quotas).\n\nWhere to interact with Gemini in BigQuery\n-----------------------------------------\n\nAfter you [set up Gemini in BigQuery](/gemini/docs/bigquery/set-up-gemini),\nyou can use Gemini in BigQuery to do the following\nin BigQuery Studio:\n\n- To [generate data insights](/bigquery/docs/data-insights#insights-bigquery-table), go to the **Insights** tab for a table entry, where you can identify patterns, assess quality, and run statistical analysis across your BigQuery data.\n- To use data canvas, [create a data canvas or use data canvas](/bigquery/docs/data-canvas#work-with-data-canvas) from a table or query to explore data assets with natural language and share your canvases.\n- To use natural language to generate SQL or Python code, or receive suggestions with autocomplete while typing, use the **SQL generation tool** for your [SQL queries](/bigquery/docs/write-sql-gemini#generate_a_sql_query) or [Python code](/bigquery/docs/write-sql-gemini#python_code_completion). Gemini in BigQuery can also explain your SQL code in natural language.\n- To prepare data for analysis, in the **Create new** list, select **Data preparation** . For more information, see [Open the data preparation editor in BigQuery](/bigquery/docs/data-prep-get-suggestions#open-data-prep-editor).\n\nSet up Gemini in BigQuery\n-------------------------\n\nFor detailed setup steps, see\n[Set up Gemini in BigQuery](/gemini/docs/bigquery/set-up-gemini).\n\nHow Gemini in BigQuery uses your data\n-------------------------------------\n\nIn order to provide accurate results, Gemini in\nBigQuery requires access to both your\n[Customer Data](/terms/data-processing-addendum) and metadata\nin BigQuery for enhanced features. Enabling Gemini\nin BigQuery grants Gemini permission to access\nthis data, which includes your tables and query history. Gemini\nin BigQuery doesn't use your data to train or fine-tune its\nmodels. For more information on how Gemini uses your data, see\n[how Gemini for Google Cloud uses your data](/gemini/docs/discover/data-governance).\n\nEnhanced features in Gemini in BigQuery are the following:\n\n- SQL generation tool\n- Prompt to generate SQL queries\n- Complete a SQL query\n- Explain a SQL query\n- Generate python code\n- Python code completion\n- Data canvas\n- Data preparation\n- Data insights\n\n### Locations\n\nFor information about where Gemini processes your data, see\n[Gemini serving locations](/gemini/docs/locations).\n\nWhat's next\n-----------\n\n- See the latest enhancements and fixes in [release notes](/gemini/docs/release-notes).\n- Learn how to [set up Gemini in BigQuery](/gemini/docs/bigquery/set-up-gemini).\n- Learn how to [write queries with Gemini assistance](/bigquery/docs/write-sql-gemini).\n- Learn more about [Google Cloud compliance](/security/compliance)."]]
