Google expands Duet AI capabilities across cloud services

Google will add that feature Generation AIAt the annual Google Cloud Next conference, the company announced that Duet AI, the underlying assistant, is built into most cloud services, including data analytics, databases, infrastructure and application management.

Duet AIwas introduced at Google I/O in May and initially offered developer features such as code and chat assistance. Currently, Google refactors and translates code, context-aware code generation, APIs administration and application management.

Code refactoring is an essential step in modernizing applications, Google said, allowing enterprise users to command Duet AI in natural language from within the development environment to generate new code in the programming language of their choice. He added that he had.

Using AI to help refactor and translate code is becoming more popular. Last week, IBM also released a new feature in Code Assistant that allows enterprises to: Refactor and convert COBOL code to Java For Z mainframe systems.

Duet AI is accessible across your development environment including Google Cloud Console, Cloud Workstation, and Cloud Shell Editor. Additionally, Duet AI is also available through the Cloud Code IDE extension for third-party development environments. Visual Studio Code JetBrains IDEs such as CLion, GoLand, IntelliJ, PyCharm, Rider, WebStorm.

Google doesn’t explicitly state which programming languages ​​Duet AI supports, but it does provide examples of what it uses to translate C++ code into: goand support for third-party IDEs to work with .Net, Java, python, C.and C++among other languages.

Duet AI can also be code-aware, Google said, adding that it has begun working with some companies to enable generative AI-based assistants to be trained and customized with company-specific knowledge from libraries and code bases. I was. The assistant generates context-aware suggestions.

“For example, if you ask Duet AI to generate code for a function that finds all products under $10 in a company’s product catalog, it will generate a function based on the company’s classes and methods used to interact with the product catalog. will be generated.”

Google is also adding Duet AI to its integration services, including the Apigee API Management suite and Application Integration suite, to help developers design, create, and publish APIs using natural language prompts.

Duet AI for managing infrastructure and applications

To help businesses better manage their applications and infrastructure, Google is adding Duet AI to its cloud offerings.

“Duet AI helps automate deployments, ensure proper application configuration, quickly understand and debug problems, and create more secure and reliable applications,” the company said, adding that the assistant will help developers, sites Reliability engineers troubleshoot problems by identifying correlations between applications, which they add help operators monitor performance.

Added Duet AI to the Cloud Monitoring service, allowing enterprise users to generate PromQL using natural language prompts (Prometheus query language) to analyze time-series metrics such as CPU utilization over time.

“Duet AI facilitates root cause analysis by providing intuitive explanations of complex log entries in the Log Explorer and suggestions on how to fix issues revealed in error reports. You can also,” Google said.

The new features are in preview and will be generally available later this year.

Duet AI in BigQuery and Looker

Additionally, Google is adding Duet AI to its data warehousing platform. BigQueryto provide contextual assistance in writing SQL and python To access and analyze data.

The company says the assistant can generate complete functions, code blocks, auto-suggest code completion, explain code and SQL queries, and BigQuery’s Duet AI helps data analysts understand the data and its usage patterns. He added that the focus is on making

Additionally, the assistant generates vector embeddings in BigQuery to semantic search The same is true for suggested queries, according to Google.

The cloud service provider is also adding Duet AI to its business insights platform, Looker.

“Looker’s Duet AI enables conversational data analysis, automatic generation of presentations, intelligent text summarization based on reports, use of natural language to create calculations and visualizations, and rapid generation of LookML models. ,” said the company. He added that later this year, he plans to add a new His Duet AI experience to Looker that can analyze data in a collaborative notebook experience.

These features are also in preview. The company has not set a release date.

Duet AI in database and migration services

Google is also adding Duet AI to its database and migration services, starting with its distributed relational database service. Google cloud spanner.

“Cloud Spanner’s Duet AI enables you to generate code to structure, modify, and query data using natural language,” the company said, adding that these capabilities also extend to AlloyDB and Cloud SQL. added.

In addition, Duet AI is Google’s Database migration service (DMS) automates the conversion of database code such as stored procedures, functions, triggers, packages and customer PL or SQL code that cannot be converted with traditional conversion technologies.

Later this year, enterprises will be able to migrate Oracle’s last mile to AlloyDB and Oracle to Cloud SQL-for-PostgreSQL using DMS’s Duet AI, the company said.

AlloyDB AI to help build generative AI apps using data in PostgreSQL

Google also has a suite of integrated features called AlloyDB AI. AlloyDB for PostgreSQL A database service for enabling developers to build generative AI-based applications using real-time data.

AlloyDB AI, which is currently in preview, builds on the basic vector support available in standard PostgreSQL, the company said, adding that it can introduce simple features. PostgreSQL A function that generates data embeddings.

“In just one line, SQLgives you access to Google’s embedding models, including both local models for low-latency in-database embedding generation (available in Technology Preview of AlloyDB Omni) and richer remote models. Vertex AI“Andi Gutmans, vice president of engineering for Google Cloud Databases, said in a statement.

“These models can be used to automatically create embeddings through inference on the generated columns or to generate embeddings on-the-fly in response to user input,” Guttmans added.

AlloyDB AI also uses its capabilities to enhance vector support queries.ScaNN technologyThe company said, adding that this allows support for more vector dimensions and saves storage space.

The new feature suite also includes integrations with the following features: Lang chain and Vertex AI extension.

AlloyDB AI can be downloaded using: AlloyDB Omniwhich is currently in public preview.

In July, Google Added support for the popular pgvector extensionSupports building generative AI applications with AlloyDB and Cloud SQL.