Google wants Gemini, its family of generative AI models, to power your app's databases – in a way.
At its annual Cloud Next conference in Las Vegas, Google announced the general public preview of Gemini in Databases, a set of features powered by Gemini to, as the corporate put it, “simplify all features of the database journey.” To put it less colloquially, Gemini in Databases is a collection of AI-powered, developer-focused tools for Google Cloud customers who construct, monitor, and migrate app databases.
Part of Gemini in Databases is Database Studio, an editor for Structured Query Language (SQL), the language by which data is stored and processed relational databases. According to Google, Database Studio, which is integrated into the Google Cloud console, can generate, summarize and fix specific errors with SQL code and offer general SQL coding suggestions through a chatbot-like interface.
Joining Database Studio under the Gemini brand in Databases includes AI-powered migrations via Google's existing Database Migration Service. According to Google, Google's Gemini models can convert database code and supply explanations of those changes and proposals.
Elsewhere, Google's latest Database Center – one other component of Gemini in Databases – allows users to interact with databases in natural language and manage a fleet of databases with tools to evaluate their availability, security and privacy compliance. And if something goes fallacious, these users can ask a Gemini-powered bot to supply troubleshooting suggestions.
“Gemini in Databases enables customers to simply generate SQL; Additionally, they’ll now manage, optimize and control entire database fleets from a single interface. and at last speed up database migrations through AI-powered code conversions,” Andi Gutmans, GM of databases at Google Cloud, wrote in a blog post shared with TechCrunch. “Imagine with the ability to ask questions like “Which of my production databases in East Asia were missing backups within the last 24 hours?” or “How many PostgreSQL resources have a version higher than 11?” and get quick insights into your entire database fleet .”
Of course, this assumes that the Gemini models don't make mistakes every so often – which isn’t any guarantee.
Regardless, Google is moving forward and can also be bringing Gemini into its business intelligence tool Looker.
Gemini in Looker is launching in private preview, allowing users to “chat with their business details,” as Google describes it in a blog post. Gemini in Looker is integrated with Workspace, Google's suite of business productivity tools, and includes features equivalent to conversation evaluation; Reporting, visualization and formula creation; and automatic creation of Google Slide presentations.
I'm curious to see whether Gemini's report and presentation creation works reliably well in Looker. Generative AI models don't exactly have a repute for accuracy, which may lead to embarrassing and even mission-critical errors. With any luck, we'll discover when Cloud Next continues later this week.
Gemini in Databases might be seen as something of a response to Microsoft's recently launched Copilot in Azure SQL Database, which introduced generative AI to Microsoft's existing fully managed cloud database service. Microsoft desires to stay ahead of the burgeoning race for AI-driven databases and has also been working to develop generative AI with Azure Data Studio, the corporate's proprietary tools for managing and developing enterprise data.