Grounding Gemini Models in Vertex AI GSP1264

Overview
Gemini
Gemini is a family of generative AI models developed by Google DeepMind that is designed for multimodal use cases.

Controlled Generation
Depending on your application, you may want the model response to a prompt to be returned in a structured data format, particularly if you are using the responses for downstream processes, such as downstream modules that expect a specific format as input. The Gemini API provides the controlled generation capability to constraint the model output to a structured format. This capability is available in the following models:
Gemini 1.5 Pro
Gemini 1.5 Flash
Learn more about control generated output.

Prerequisites
Before starting this lab, you should have familiarity with the following concepts:
Basic understanding of Python programming
General knowledge of how APIs work
Running Python code in a Jupyter notebook in Vertex AI Workbench

Objectives
In this lab, you learn how to use the controlled generation capability in the Vertex AI Gemini API to generate model responses in a structured data format.

You will complete the following tasks:
Sending a prompt with a response schema
Using controlled generation in use cases requiring output constraints
#gcp #googlecloud #qwiklabs #learntoearn