Gemini in BigQuery for Data Practitioners
(1 day)
Course Description
This course demonstrates how to use AI/ML models for generative AI tasks in BigQuery. Through a practical use case involving customer relationship management, you learn the workflow of solving a business problem with Gemini models. To facilitate comprehension, the course also provides step-by-step guidance through coding solutions using both SQL queries and Python notebooks.
Learning Objectives
- Define the features of Gemini in BigQuery that aid the data-to-AI pipeline.
- Explore data with Insights and Table Explorer.
- Develop code with Gemini assistance.
- Discover and visualize workflow with data canvas.
- Explain the workflow of using AI/ML models for predictive and generative tasks in BigQuery.
- Create a solution for leveraging Gemini models in BigQuery with SQL queries and Jupyter Notebooks.
Who Should Attend
Data analysts, data engineers, and other data professionals who wish to use Gemini in BigQuery to boost productivity and understand their unstructured data.
Prerequisites
Prior experience with programming languages including SQL and/or Python. • Basic knowledge of ML and generative AI.
Course Outline
Module 1: Gemini on BigQuery
- Gemini on Google Cloud
- Overview of Gemini on BigQuery
- Introduction to course use case
Module 2: Data Exploration and Preparation
- Data exploration and preparation
- Insights
- Table Explorer
- Lab: Explore Data with Gemini in BigQuery
Module 3: Code Development with Gemini
- Gemini for writing code
- Troubleshooting and testing with Gemini
- Prompting best practices
- Lab: Develop Code with Gemini in BigQuery
Module 4: Data Canvas
- Introduction to Data Canvas
- Data Canvas capabilities
- Prompting best practices for Data Canvas
- Lab: Use Data Canvas to Visualize and Design Queries
Module 5: Working with Gemini Models in BigQuery
- BigQuery ML
- Using Gemini in your SQL queries
- Gemini in BigQuery Notebooks
- Lab: Analyze Customer Reviews with SQL
- Lab: Analyze Customer Reviews with Python Notebooks
