Gemini in BigQuery

Overview

This learning path provides a journey into leveraging Gemini within BigQuery for advanced data and AI workflows. Starting with foundational productivity enhancements, it progresses to building generative AI applications and culminates in mastering Retrieval Augmented Generation to mitigate AI inaccuracies. By completing this path, learners will gain practical skills in utilizing Gemini to streamline data processes, create innovative AI solutions, and ensure reliable AI outputs within the BigQuery environment.

Syllabus

Course 1: Boost Productivity with Gemini in BigQuery
Course 2: Work with Gemini Models in BigQuery
Course 3: Create Embeddings, Vector Search, and RAG with BigQuery

Courses

0 reviews
4 hours 8 minutes
View details

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.
0 reviews
5 hours 27 minutes
View details

This course explores Gemini in BigQuery, a suite of AI-driven features to assist data-to-AI workflow. These features include data exploration and preparation, code generation and troubleshooting, and workflow discovery and visualization. Through conceptual explanations, a practical use case, and hands-on labs, the course empowers data practitioners to boost their productivity and expedite the development pipeline.
0 reviews
2 hours 30 minutes
View details

This course explores a Retrieval Augmented Generation (RAG) solution in BigQuery to mitigate AI hallucinations. It introduces a RAG workflow that encompasses creating embeddings, searching a vector space, and generating improved answers. The course explains the conceptual reasons behind these steps and their practical implementation with BigQuery. By the end of the course, learners will be able to build a RAG pipeline using BigQuery and generative AI models like Gemini and embedding models to address their own AI hallucination use cases.