Source URL: https://cloud.google.com/blog/products/data-analytics/gemini-in-bigquery-features-are-now-ga/
Source: Cloud Blog
Title: Get started with the new generally available features of Gemini in BigQuery
Feedly Summary: According to Google’s Data and AI Trends Report
2024, 84% of organizations believe that generative AI will expedite their access to insights, and notably 52% of non-technical users are already leveraging generative AI to extract valuable insights.
With Google’s Data Cloud, we’re on a mission to bring our decades of research and investments in AI to revolutionize data management and analytics, enabling organizations to reimagine experiences and build data agents grounded in their proprietary data. At Google Cloud Next 2024, we introduced the preview of Gemini in BigQuery, which delivers AI-powered experiences such as data discovery and exploration, data preparation and engineering, analysis and insight generation covering the data journey, as well as intelligent recommendations to enhance user productivity and optimize costs.
“Gemini in BigQuery has transformed our query generation process. The integration into BigQuery makes it easy to generate SQL templates and has helped boost the efficiency of our label and feature engineering, including crucial machine learning model monitoring queries. Gemini’s ability to understand complex data structures and deliver accurate queries has made our workflow smoother and faster than ever.” – Martijn Wieriks, Chief Data Officer, Julo
Today, we are announcing general availability of several Gemini in BigQuery features, including SQL code generation and explanation, Python code generation, data canvas, data insights and partitioning, and clustering recommendations.
Let’s take a closer look at some of the functionality you can enjoy today with Gemini in BigQuery.
What makes Gemini in BigQuery different?
Gemini in BigQuery brings the best of Google’s capabilities across data management and AI infrastructure with state-of-the-art models optimized for your business needs.
Context aware: decodes your intent, understands your goals and proactively engages with you to accelerate your workflows
Grounded in your data: continuously learns and adapts to your business data to uncover new opportunities and anticipate issues
Integrated experience: directly accessible within the BigQuery interface, providing a seamless experience across the analytics workflows
Getting started with data insights
The data analysis journey first begins with data discovery and assessing which insights you can get from your data assets. Imagine having a library of insightful questions tailored specifically to your data – questions you didn’t even know you should ask! Data Insights eliminates the guesswork with pre-validated, ready-to-run queries offering immediate insights. For instance, if you’re working with a table containing customer churn data, Data Insights might prompt you to explore the factors contributing to churn within specific customer segments — an angle you might not have thought to investigate.
These actionable queries are built into BigQuery Studio, providing the insights, right where you need them, to advance your analysis with a single-click.
Gemini in BigQuery suggests executable queries as natural language insights for tables that you can run with a single click
Enhance productivity with SQL and Python code assistance
Gemini for BigQuery helps you write and modify SQL or Python code using straightforward natural language prompts, referencing relevant schemas and metadata. This helps reduce errors and inconsistencies in your code while empowering users to craft complex, accurate queries, even if they have limited coding experience.
“Gemini in BigQuery helps our data teams deliver insight more quickly and reduce the cycle time of data pipelines and analysis. SQL code generation and text-embedding using AI enhances productivity and allows more time to focus on high impact initiatives. Ultimately, this will help us achieve our mission of providing behavioral intelligence to our clients.” – Okayasu, Chief Data Scientist at Unerry, Inc.
Gemini in BigQuery comprehends the structure and relationships within your data, so you can receive tailored code suggestions from a straightforward natural-language prompt. For example, you can ask it to:
"Generate a SQL query to calculate the total sales for each product in the table."
"Write Python code to correlate between product sales and number of customer reviews using pandas”
“Calculate the average trip length by subscriber type”
SQL code generation using Gemini in BigQuery
Gemini in BigQuery can also provide explanations and insights to help you understand complex SQL and Python queries, making it easier for users of all skill levels to understand the logic behind the code. This is especially beneficial for those who are new to SQL and Python, or working with unfamiliar datasets.
SQL code explanation using Gemini in BigQuery
Reimagined analytics workflows with natural language
Gemini in BigQuery includes data canvas, an innovative natural language-based interface for data exploration, curation, wrangling, analysis, and visualization. Data canvas enables you to explore and structure your data journeys through a graphical workflow, for smooth and intuitive data exploration and analysis.
"For any sort of investigation or exploratory exercise you know will result in multiple queries, there really is no replacement. It’s saved us so much time and mental capacity" – Scott Schaen, VP of Analytics, Wunderkind
For example, to analyze revenue across retail stores, you could use simple natural language prompts to gather data from various sources such as a POS system, integrate with inventory, CRM or external data, uncover relationships between factors like store location, product categories, and revenue, or develop reports and visualizations for stakeholders — all within a single user interface. Refer to this blog and watch the demo below for a deep dive into BigQuery data canvas.
Collaborative Data Exploration with BigQuery Data Canvas and Looker Studio
Optimize analytics for performance and speed
As data volumes grow, data administrators and other analytics professionals face challenges in effectively managing capacity and improving query performance. To address these challenges, Gemini in BigQuery offers AI-powered recommendations for partitioning and clustering your tables. These recommendations aim to optimize your tables for faster results and lower query costs without requiring any modifications to your queries.
Getting started
General availability of Gemini in BigQuery features will be rolled out in phases over the next few months starting today with SQL code generation and explanation, Python code generation, data canvas, data insights and partitioning and clustering recommendations.
At this time, generally available (GA) features are available to all customers at no additional cost. Please refer to the pricing details for more information.
AI Summary and Description: Yes
Summary: Google’s Data and AI Trends Report 2024 highlights the increasing reliance on generative AI for insights, with a significant number of non-technical users engaging with these tools. The introduction of Gemini in BigQuery showcases innovations in AI-driven data management and analytics that enhance user productivity, reduce errors in coding, and facilitate a seamless experience for data exploration and insight generation.
Detailed Description:
The provided text discusses the implications, features, and benefits of Google’s newly introduced Gemini within BigQuery, which aligns closely with the fields of AI, specifically AI Security, Cloud Computing, and Information Security. The advancements presented in the report emphasize not only the growing trend of generative AI but also the innovative solutions intended to optimize data management and analytics workflows.
Key Insights and Features:
– **Generative AI Utilization**:
– 84% of organizations see generative AI as a tool to expedite insight acquisition.
– 52% of non-technical users are already leveraging generative AI for data insights, indicating a democratization of data analytics.
– **Gemini in BigQuery Overview**:
– Gemini integrates AI capabilities with data infrastructure, offering tools tailored for enhanced business performance.
– It supports complex data structures, contributing to smoother query generation processes.
– **Innovative Functionalities**:
– **SQL and Python Code Generation**:
– Enhances productivity through natural language prompts, making it easier to craft complex queries, even for less experienced users.
– Pre-validated queries help users gain immediate insights without extensive coding knowledge.
– **Data Insights**:
– Offers a library of insightful questions to guide users in data exploration.
– Helps identify unexplored analytical avenues, fostering proactive data investigation.
– **Natural Language Processing**:
– Gemini’s natural language understanding facilitates user interactions, streamlining data analysis and exploration.
– Offers contextual awareness to optimize workflows and user intent during data tasks.
– **Performance Optimization**:
– AI-driven recommendations for partitioning and clustering help manage increasing data volumes efficiently.
– Targeted optimizations lead to improved query performance and reduced operational costs.
– **User-Centric Design**:
– Features like Data Canvas provide a graphical interface for intuitive data manipulation and exploration.
– Combined with tools for visualization and report generation, these features enable collaborative work environments.
The introduction of Gemini in BigQuery signifies a strategic move by Google to not only enhance data analytics but also to integrate safety and compliance measures to safeguard sensitive information while leveraging AI. This advancement is particularly relevant for security, privacy, and compliance professionals as organizations increasingly leverage generative AI tools for data insights while navigating the complexities of governance and data protection.