Overview
Gemini is a family of generative AI models developed by Google DeepMind that is designed for multimodal use cases. The Gemini API gives you access to the Gemini Pro Vision and Gemini Pro models. In this lab you will understand how to integrate Vertex AI Gemini API with applications and build and deploy the developed sample application on Google Cloud Run.
Vertex AI Gemini API
The Vertex AI Gemini API provides a unified interface for interacting with Gemini models. There are currently two models available in the Gemini API:
1. Gemini Pro model (gemini-pro): Designed to handle natural language tasks, multiturn text and code chat, and code generation.
2. Gemini Pro Vision model (gemini-pro-vision): Supports multimodal prompts. You can include text, images, and video in your prompt requests and get text or code responses.
You can interact with the Gemini API using the following methods:
- Use the Vertex AI Studio for quick testing and command generation
- Use cURL commands
- Use the Vertex AI SDK
This lab focuses on integrating the Gemini Pro model with a Streamlit application and deploying the application on Google Cloud Run.
For more information, see the Generative AI on Vertex AI documentation.
Objectives
In this lab, you will learn how to:
- Integrate Vertex AI Gemini API with applications
- Build and deploy the developed sample application on Google Cloud Run
- Use the Streamlit framework to build a Cloud Run application
#gcp #googlecloud #qwiklabs #learntoearn
13 сен 2024
