Write SQL with Gemini assistance

Preview — Gemini in Spanner

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

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

This document describes how you can use Gemini, an AI-powered collaborator in Google Cloud, to help you do the following in Spanner:

• Generate SQL queries using natural language prompts.
• Complete SQL statements in the query editor.
• Explain SQL queries in the query editor.

Gemini doesn't use your prompts or its responses as data to train its models. For more information, see How Gemini for Google Cloud uses your data.

This document is intended for database administrators and data engineers who are familiar with Spanner, SQL, and data analysis. If you're new to Spanner, see Create and query a database by using the Google Cloud console.

Before you begin

1. Ensure that you have set up Gemini in Databases.
2. To complete the tasks in this document, ensure that you have the necessary Identity and Access Management (IAM) permissions.

3. In the Google Cloud console, go to the Spanner page.

   Go to Spanner

4. Select an instance from the list.

5. Select a database.

6. In the navigation menu, click Spanner Studio.

7. In the taskbar, click pen_spark Gemini to view Gemini features in Spanner.

8. Select the Gemini features that you want to enable—for example, SQL completion and Comment-to-query generation. You can select and try features for yourself without affecting others working in your project.

9. Optional: If you want to follow along with the examples in this document, first create the Singers table as described in Create a schema for your database.

To disable Gemini features in Spanner, repeat these steps, and then deselect the Gemini features that you want to disable.

Required roles

To get the permissions that you need to complete the tasks in this document, ask your administrator to grant you the Spanner Database Reader (roles/spanner.databaseReader) IAM role on the project. For more information about granting roles, see Manage access.

You might also be able to get the required permissions through custom roles or other predefined roles.

Generate SQL queries using natural language prompts

You can give Gemini natural language comments (or prompts) to generate queries that are based on your schema. For example, you can prompt Gemini to generate SQL in response to the following prompts:

• "Create a table that tracks customer satisfaction survey results."
• "Add a date column called birthday to the Singers table."
• "How many singers were born in the 90s?"

Note: When you enter a prompt for Gemini in Spanner, information about your database's schema is included with the prompt. This can include table and column names, data types, and column descriptions. Your database schema and data remain in Spanner and aren't sent to Gemini.

To generate SQL in Spanner with Gemini assistance, follow these steps:

1. In the Google Cloud console, go to the Spanner page.

   Go to Spanner

2. Select an instance from the list.

3. Select a database.

4. In the navigation pane, click Spanner Studio. The Explorer pane displays a list of objects in your database.

5. To query your database, click the New SQL editor tab. Make sure that SQL generation is enabled.

6. To generate SQL, type a comment in the query editor starting with -- followed by a single-line comment, and then press Return.

   For example, if you enter the prompt -- add a row to table singers and press Return, then Gemini generates SQL that's similar to the following:

   INSERT INTO Singers (SingerId, FirstName, LastName, BirthDate)
   VALUES (1, Alex, 'M.', '1977-10-16');
   

   To continue the example using the Singers table, if you enter the prompt -- show all singers born in the 70s, then Gemini generates SQL that's similar to the following:

   SELECT *
   FROM Singers
   WHERE Singers.BirthDate
   BETWEEN '1970-01-01' AND '1979-12-31'
   
   

   Note: Gemini might suggest different syntax each time that you enter the same prompt.

7. Review the generated SQL and take any of the following actions:

   • To accept SQL generated by Gemini, press Tab, and then click Run to execute the suggested SQL.
   • To edit the SQL generated by Gemini, press Tab, edit the SQL, and then click Run.
   • To dismiss the suggestion, press Esc or continue typing.

Complete SQL statements in the query editor

To help you write SQL code, Gemini in Spanner provides AI-assisted code completion suggestions. With Gemini enabled, when you enter text in the Spanner Studio query editor, Gemini predicts and autofills SQL code.

Inline code suggestions

To use inline code suggestions, follow these steps:

1. In the Google Cloud console, go to the Spanner page.

   Go to Spanner

2. Select an instance from the list.

3. Select a database.

4. In the navigation pane, click Spanner Studio.

5. To query your database, click New SQL editor tab. Make sure that SQL completion is enabled.

6. Enter a query and a space or newline at the end of the line. As you enter text, Gemini shows suggested SQL that's based on the supported objects in the selected database's schema.

   For example, to add a row to the Singers table, begin to write the following SQL: INSERT INTO Singers.

   Gemini suggests SQL that's similar to the following:

   INSERT INTO Singers
   (SingerId, FirstName, LastName, BirthDate)
   VALUES
     (1, 'Marc', 'Singer', '1970-03-24')
   

   Note: Gemini might suggest different SQL syntax each time that you enter the same SQL statement.

7. Review the SQL suggestion and take any of the following actions:

   • To accept SQL generated by Gemini, press Tab, and then click Run to execute the suggested SQL.
   • To edit the SQL generated by Gemini, press Tab, edit the SQL, and then click Run.
   • To dismiss the suggestion, press Esc or continue typing.

Help me code tool

To use the Help me code tool, follow these steps:

1. In the Google Cloud console, go to the Spanner page.

   Go to Spanner

2. Select an instance from the list.

3. Select a database.

4. In the navigation pane, click Spanner Studio.

5. To query your database, click the New tab.

6. Click pen_spark Help me code next to the query editor.

7. In the Help me code window, enter a prompt. For example, add a row to table singers and click Generate.

   Gemini generates SQL that's similar to the following:

   INSERT INTO Singers (SingerId, FirstName, LastName, BirthDate)
   VALUES (1, Alex, 'M.', '1977-10-16');
   

   Note: Gemini might suggest different syntax each time that you enter the same prompt.

8. Review the generated SQL and take any of the following actions:

   • To accept SQL generated by Gemini, click Insert to insert the statement into the query editor. Then click Run to execute the suggested SQL.
   • To ask Gemini to generate a new query, click Edit. After you've edited your prompt, click Update. You can then decide to accept the new generated statement or dismiss the suggestion.
   • To dismiss the suggestion, close the Help me code window.

Explain SQL statements in the query editor

You can use Gemini in Spanner to explain SQL queries in natural language. This explanation can help you understand the syntax, underlying schema, and business context for complex or long queries.

1. In the Google Cloud console, go to the Spanner page.

   Go to Spanner

2. Select an instance from the list.

3. Select a database.

4. In the navigation pane, click Spanner Studio.

5. To query your database, click the New tab.

6. In the query editor, paste the query.

7. Highlight the query that you want Gemini to explain, and then click spark Explain this query.

   The SQL explanation appears in the Gemini pane.

What's next

• Read Gemini in Google Cloud overview.
• Learn how Gemini uses your data.
• Learn how to analyze your data in Google Cloud using Gemini.