Gemini in BigQuery

This document describes how Gemini in BigQuery, which is a product in the Gemini for Google Cloud portfolio, provides AI-powered assistance to help you work with your data.

AI assistance with Gemini in BigQuery

Gemini in BigQuery provides AI assistance in the following ways:

  • Explore and understand your data with data insights. (Preview) Data insights offers an automated, intuitive way to uncover patterns, assess data quality, and perform statistical analysis by using insightful queries 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.
  • Discover, transform, query, and visualize data with BigQuery data canvas. (Preview) Using natural language, you can find, join, and query table assets, visualize results, and seamlessly collaborate with others throughout the entire process. For more information, see Analyze with data canvas.
  • Get assisted SQL and Python data analysis. You can use Gemini in BigQuery to generate or suggest code in 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:
  • Optimize your data infrastructure with partitioning, clustering, and materialized view recommendations. You can let BigQuery monitor your SQL workloads for opportunities to improve performance and reduce costs. For more information, see the following documentation:
  • Autotune and troubleshoot serverless Apache Spark workloads. (Preview) Autotuning can automatically optimize Spark jobs by applying configuration settings to a recurring Spark workload based on best practices and an analysis of prior workload runs. Advanced troubleshooting with Gemini can explain and surface job errors, and it can offer actionable recommendations to fix slow or failed jobs. For more information, see Autotuning Spark workloads and Advanced troubleshooting.
  • Customize your SQL translations with translation rules. (Preview) Create Gemini-enhanced translation rules to customize your SQL translations when using the 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 rule.
Gemini in BigQuery uses large language models (LLMs) that are developed by Google. The LLMs are fine-tuned with billions of lines of open source code, security data, and Google Cloud-specific content such as documentation and sample code.

Learn how and when Gemini for Google Cloud uses your data. As an early-stage technology, Gemini for Google Cloud can generate output that seems plausible but is factually incorrect. We recommend that you validate all output from Gemini for Google Cloud before you use it. For more information, see Gemini for Google Cloud and responsible AI.

Where to interact with Gemini

After you set up Gemini in BigQuery, you can use Gemini in BigQuery to do the following in BigQuery Studio:

  • To use data insights, go to the Insights tab for a table entry, where you can identify patterns, assess quality, and run statistical analysis across your BigQuery data.
  • To use data canvas, create a data canvas or use data canvas from a table or query to explore data assets with natural language and share your canvases.
  • To get assisted SQL queries, use the Help me code tool, which lets you iterate on your query, specify source data, and then insert the query into BigQuery Studio.
  • To view recommendations for partitioning, clustering, and materialized views, click Recommendations in the Google Cloud console toolbar.
  • To use natural language to generate SQL or Python code, or receive suggestions with autocomplete while typing, use the Help me code tool for your SQL queries or Python code. Gemini can also explain your SQL code in natural language.

Autotune and troubleshoot Spark jobs

Autotuning can help you optimize your Spark workloads for performance and resilience. Instead of manually configuring settings, Gemini can apply best practices for recurring workloads and then help you understand and monitor your autotuning. Advanced troubleshooting provides natural language answers to "What was autotuned?", "What is happening now?", and "What can I do about it?"

Set up Gemini for Google Cloud in BigQuery

For detailed setup steps, see Set up Gemini for Google Cloud in BigQuery.

What's next