Cloud Hero: GenAI Search and Conversation

Overview

This course introduces learners to generative AI using Vertex AI and Gemini. Participants will explore how to build and deploy AI models, work with multimodal data, and integrate search and embedding functionalities into applications. The course includes hands-on labs to develop practical skills in prompt engineering, model configuration, and application integration.

Prerequisites

Participants should have some prior experience with Vertex AI.

Target audience

This course is designed for someone who has general familiarity with Vertex AI, but is looking to incorporate generative AI search, as well as multimodal functions into their applications.

Objectives

By the end of this course, learners will be able to:

• Create and manage applications using prompts
• Design and engineer effective prompts, including multimodal prompts
• Generate text and control reasoning with Gemini
• Configure model parameters and system instructions
• Process multimodal data such as audio, code, and video
• Implement advanced features like function calling and code execution
• Integrate search and embedding functionalities into applications

Outline

Getting Started with Vertex AI Studio

• Create applications from prompts
• Design effective prompts
• Engineer and manage prompts
• Use multimodal prompts

Getting Started with the Vertex AI Gemini 1.5 Pro Model

• Generate text and control reasoning with thinking levels
• Configure model parameters and system instructions
• Process multimodal data including audio, code, and video
• Implement advanced features like function calling and code execution

Integrate Search in Applications using Vertex AI Agent Builder

• Index public website data, structured and unstructured data
• Perform search on indexed data
• Configure the display of search results
• Integrate Agent Search with web applications

Introduction to Vertex AI Embeddings: Text and Multimodal

• Use Agent Platform Text Embeddings API
• Use Agent Platform Multimodal Embeddings API (images and video)
• Build simple search with e-commerce data
• Find products based on text query, image, or video

Exams and assessments

There are no exams or assessments associated with this course.

Hands-on learning

The course includes practical labs where learners create applications, design prompts, configure models, process multimodal data, and integrate search and embedding features into real-world scenarios.