Gemini for Google Cloud release notes

You can now automatically or manually assign Gemini Code Assist licenses. For more information, see Manage Gemini for Google Cloud licenses.

You can now purchase Gemini Code Assist Enterprise edition on the Admin for Gemini page within the Google Cloud console. For more information, see Add or change Gemini for Google Cloud subscriptions.

VS Code and IntelliJ Gemini Code Assist now support admin feedback block. This feature allows admins to control whether developers can send Gemini Code Assist feedback.

BigQuery provides context-aware transformation recommendations from Gemini for cleansing data for analysis. Data preparation is available in Preview.

You can now assign Gemini Code Assist subscription licenses to users in your organization. Use the Admin for Gemini page in the Google Cloud console or use the billingAccounts.orders API to view, assign, or unassign user licenses. For more information, see Manage Gemini for Google Cloud licenses.

Code customization is now generally available in Gemini Code Assist for:

• VS Code with the Gemini Code Assist + Cloud Code extension (version 2.18.0+)
• IntelliJ with the Gemini Code Assist/Cloud Code plugin (version 1.1.0)
• Cloud Workstations
• Cloud Shell Editor

With code customization, Gemini Code Assist lets you get enhanced code suggestions based on your organization's private codebase(s) (in GitHub.com or GitLab.com) and in line with your coding conventions. For more information, see the code customization overview.

Local codebase awareness is now available for VS Code Gemini Code Assist. Local codebase awareness helps you with high quality code suggestions that are syntactically correct and semantically meaningful within the broader context of your codebase, when you specify files for Gemini Code Assist to use as context. You can specify files in your chat prompt by typing @ and selecting the files. For more information, see Code with Gemini Code Assist.

Gemini Code Assist for VS Code, Cloud Shell, and Cloud Workstations now supports code transformation. You can use commands or natural language prompts in the Quick Pick bar to request modifications to your code, and get a diff view to show pending changes to your code.

The following Gemini in Looker features are available in Public Preview:

• Create custom Looker visualizations: The Visualization Assistant lets you customize formatting options for Looker visualizations using natural language.
• Generate LookML: Gemini in Looker assists you in generating LookML parameters based on a natural language prompt.

To learn more about how to activate these features, see Administer Gemini on your Looker (Google Cloud core) instance.

Available now in Preview, you can monitor Gemini for Google Cloud usage in your organization. For more information, see Monitor Gemini for Google Cloud usage.

The following Gemini in Looker feature is available in Public Preview:

• Query your data in natural language: Conversational Analytics is a Gemini-powered data querying experience that makes it easier to find answers, explore data, and share insights using natural language.

To learn more about how to activate Conversation Analytics, see Enable and disable Gemini in Looker in Looker Studio.

The following Gemini in BigQuery features are now generally available (GA):

• Data insights
• Data canvas
• SQL and Python code assistance features:
  • Use the SQL generation tool
  • Prompt to generate SQL queries
  • Explain a SQL query
  • Generate Python code
• Partitioning and clustering recommendations

To learn how to enable and activate Gemini in BigQuery features, see Set up Gemini in BigQuery.

Code completions for IntelliJ Gemini Code Assist are now completely integrated with native IDE completion framework, which makes it easier to use and override key combinations to trigger, and less conflicting with various IDE or Tab based actions.

Updated IntelliJ Gemini Code Assist chat UX and styling.

You can now use the arrow keys to traverse previous chat history entries to repeat and edit questions in IntelliJ Gemini Code Assist.

Chat conversation history now persists across IDE sessions and restarts for IntelliJ Gemini Code Assist.

You can now exclude any files from AI completions and chat interactions using .aiexclude in IntelliJ Gemini Code Assist, with a format similar to .gitignore.

Available in Preview, you can now use Gemini to create functional playbooks based on your prompts in Google Security Operations. For more information, see Create playbooks with Gemini.

The VS Code Gemini Code Assist extension now supports Code Transformation. Press Ctrl+I for Windows and Linux or Cmd+I for macOS and use the /generate command to generate code based on your prompt anywhere in the file. For more information, see Code with Gemini Code Assist.

Conversational assistance in Gemini in Databases is now available in Preview for standard and enhanced query insights, system insights, index advisor, and active queries (AlloyDB for PostgreSQL, Cloud SQL for MySQL, and Cloud SQL for PostgreSQL). In the Gemini pane in the Google Cloud console, you can enter prompts to generate troubleshooting guidance for your database workloads and to accelerate the resolution of complex database performance issues. For more information, see Conversational assistance for query insights and system insights.

Gemini conversion assistant in Database Migration Service conversion workspaces is now available in Preview as part of Gemini in Databases. For more information, see:

• Convert Oracle code and schema with Gemini assistance for Oracle to AlloyDB for PostgreSQL
• Convert Oracle code and schema with Gemini assistance for Oracle to CloudSQL for PostgreSQL

Available now in Preview, you can enable the collection and storage of user input, contextual information, and responses when you use Gemini for Google Cloud. For more information, see View Gemini for Google Cloud logs.

Database Center, which is part of Gemini in Databases, now has the following features in Public Preview:

• New health issues
• CSV export
• All Resources page
• Additional resource metadata

For more information, see Database Center release notes.

Added a tips card in chat showing useful keyboard shortcuts for using the VS Code Gemini Code Assist plug-in.

Added a diff button to code snippets in chat so that code returned from Gemini Code Assist can be easily compared to the code in the VS Code editor.

Updated Gemini Code Assist to use Gemini 1.5 Flash model (with 32k token window), with improved support for code explanation, unit test generation, and code transformations. Automatically triggered code completions use an 8k token window.

You can now create Gemini-enhanced translation rules to use with the BigQuery interactive SQL translator. Translation rules let you customize and adjust the results of the interactive translator as you migrate your SQL queries into BigQuery. This feature is in preview.

Added ability to provide direct links to Cloud console pages that are relevant to users' prompts. Also improved response formatting to better handle longer responses.

Enabled contextualization in responses by incorporating a set of basic user data and their environment data into the prompts. Also, expanded data sources for grounding and improved response accuracy via RAG.

The Code Transformation features in Gemini Code Assist are now available in Public Preview for Cloud Shell. For more information, see Use Code Transformation features.

The Transform Code features in Gemini Code Assist are now available in Public Preview for Workstations and Cloud Shell.

Gemini in Security Command Center is released to General Availability. For more information, see Gemini features in Security Command Center.

The following Gemini in BigQuery features are now available in Public Preview:

• Data insights: an automated and intuitive way to explore and understand your data.
• Data canvas: a graphic interface that lets you discover, transform, query, and visualize data using natural language.
• SQL and Python code assistance: Gemini-assisted code generation, completion, and explanation.
• Materialized views, partitioning, and clustering recommendations: recommendations to reduce cost and improve performance.
• Autotune and troubleshoot serverless Spark: optimize and explain Spark workloads.

To learn how to enable and activate Gemini in BigQuery features, see Set up Gemini in BigQuery.

The following Gemini in Databases features are now available in Public Preview:

• Database Center: an AI-assisted dashboard that gives you one centralized view across your entire database fleet.
• Cloud SQL Studio: lets authorized users interact directly with the SQL database and run SQL queries from the Google Cloud console to access and manipulate data.
• Monitor active queries: monitor and troubleshoot the queries that are active in your database.
• Index advisor: a fully managed index advisor that tracks the queries your database handles regularly.
• 4-week query metric retention in the Query Insights dashboard.
• 15 new database insight recommendations.

To learn how to enable and activate Gemini in Databases, see Set up Gemini in Databases.

The following Gemini in Databases features are now available in Public Preview:

• Database Center: an AI-assisted dashboard that gives you one centralized view across your entire database fleet.
• AlloyDB Studio (GA): lets authorized users interact directly with the SQL database and run SQL queries from the Google Cloud console to access and manipulate data.
• Monitor active queries: monitor and troubleshoot the queries that are active in your database.
• Index advisor: a fully managed index advisor that tracks the queries your database handles regularly.
• Enhanced Query Insights: an assistive query performance diagnostics platform that lets you detect, troubleshoot, and prevent database and query performance problems in near real-time.
• 4-week query metric retention in the Query Insights dashboard.
• 5 new database insight recommendations.

To learn how to enable and activate Gemini in Databases, see Set up Gemini in Databases.

The following Gemini in Databases features are now available in Public Preview:

• Spanner Studio (GA): lets users interact with the SQL database and run SQL queries from the Google Cloud console to access and manipulate data.
• Spanner now supports the use of Gemini models with GoogleSQL and PostgreSQL machine learning prediction functions.

To learn how to enable and activate Gemini in Databases, see Set up Gemini in Databases.

The Gemini Code Assist code generation feature now allows users to generate code repeatedly at the same cursor location.

Retrieval-augmented generation is rolling out in the Intellij Duet AI plug-in as an experiment to select users to improve code suggestions for their repository.

Added thumbs up and thumbs down buttons in the Intellij Duet AI plug-in chat window for quick response quality feedback .

The context source panel in the VSCode Duet AI plug-in chat window now displays which file was included in the user's chat request.

Local code customization is enabled in the VSCode Duet AI plug-in as an experiment to select users to improve code suggestions. Additional files in the user's local directory will open when the user requests code generation. Local files are scored and included in the response based on relevance to the user's active context.

You can now use Duet AI to help you create a synthetic monitor in Cloud Monitoring. This feature is in Public Preview. For more information, see Create a synthetic monitor.

You don't need to switch between using REST and gRPC when using Duet AI. Duet AI does this for you.

Duet AI added multi-file support for code generation.

VPC Service Controls for Duet AI is Generally Available.

Duet AI for VS Code provides an indication that code generation is in progress.

Duet AI for VS Code is available in Cloud Shell Editor.

Duet AI for Cloud Workstations is available.

Chat in Duet AI in Google Cloud can be opened in a new browser tab while maintaining your current chat session.