| Google Adds Vibe Querying To BigQuery |
| Written by Kay Ewbank |
| Wednesday, 28 January 2026 |
|
Google has announced a way to write SQL queries using natural language in BigQuery. They describe it as making 'vibe querying' a reality. Google BigQuery is a distributed, serverless SQL engine that provides a way to query petabytes of data. It has built-in machine learning and is serverless.
The new feature, called Comments to SQL, is AI-powered and can be used to embed natural language expressions directly within your SQL statements, which the system then translates into executable SQL code. Google says that by automating the translation, users can write complex queries faster and spend less time writing boilerplate code. One example given is that of needing to calculate the business days between two dates, including weekends. Rather than having to look up the exact functions to calculate business days between two dates, AI can generate the SQL date function for the natural language expression: " How many business days are there between January 1st and March 15th, excluding weekends?" The new feature relies on the integration of natural language expressions into SQL queries by enclosing them within comments. For example: /* average trip distance by day of week */. BigQuery's AI then analyzes the surrounding SQL context to accurately interpret the comments. The feature can cope with the use of natural language expressions within various SQL clauses, including SELECT, FROM, WHERE, ORDER BY, and GROUP BY. It can also handle multiple expressions within a single SQL statement to build complex queries. For instance, you could use SELECT /* average trip distance, total fare */ FROM /* NYC taxi ride public data of 2020 */ WHERE /* day of week is Saturday */ GROUP BY /* pickup location */. After the initial SQL is generated, you can refine your natural language expressions and see how the SQL output changes. The new feature is included in BigQuery Studio as the SQL Generation Widget. The developers say some of the more complex cases it might be useful for start with time series analysis with conditional aggregations, where it can handle time-series aggregation, conditional counting, and date extraction within a single query. It can also handle multi-table joins and complex filtering including date range filtering, and string-based filtering, combined with ordering. Another suggested use is for handling window functions for ranking, which are typically complex to write manually. You can also group data by date parts. A final suggestion is cohort analysis with date aggregations and user segmentation. Cohort analysis involves date truncation, grouping, and pivoting to display user retention over time. Vibe Querying is available in BigQuery now.
More InformationRelated ArticlesGoogle Announces BigQuery-Managed AI Functions Google Announces BigQuery Metastore To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Facebook or Linkedin. 
Comments
or email your comment to: comments@i-programmer.info |
