Name		Name	Last commit message	Last commit date
parent directory ..
batch-prediction		batch-prediction
chat-completions		chat-completions
context-caching		context-caching
controlled-generation		controlled-generation
evaluation		evaluation
function-calling		function-calling
getting-started		getting-started
grounding		grounding
long-context		long-context
orchestration		orchestration
prompts		prompts
qa-ops		qa-ops
rag-engine		rag-engine
reasoning-engine		reasoning-engine
responsible-ai		responsible-ai
sample-apps		sample-apps
tuning		tuning
use-cases		use-cases
README.md		README.md

README.md

Generative AI - Gemini

Welcome to the Google Cloud Generative AI - Gemini folder.

Gemini

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.

Gemini API in Vertex AI

On Google Cloud, the Gemini API in Vertex AI provides a unified interface for interacting with Gemini models. There are currently two models available in the Gemini API:

Gemini Pro model (gemini-pro): Designed to handle natural language tasks, multi-turn text and code chat, and code generation.
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.

The notebooks and samples in this folder focus on using the Vertex AI SDK for Python to call the Gemini API in Vertex AI.

Using this repository

	Description
`getting-started/`	Get started with the Gemini API in Vertex AI: `gemini-1.5-pro` model `gemini-1.5-flash` model
`sample-apps/`	Discover sample apps using Gemini
`use-cases/`	Explore industry use-cases enabled by Gemini (e.g. retail, education)
`evaluation/`	Learn how to evaluate Gemini with Vertex AI Model Evaluation for Generative AI
`function-calling/`	Learn how to use the function calling feature of Gemini
`grounding/`	Learn how to use the grounding feature of Gemini
`knowledge-engine/`	Discover how to utilize the Knowledge Engine feature of Vertex AI
`prompts/`	Learn how to create and use effective prompts with Gemini.
`qa-ops/`	Learn about the question-answer operations available in Gemini
`reasoning-engine/`	Discover how to utilize the Reasoning Engine feature of Vertex AI
`responsible-ai/`	Learn best practices for responsible AI and security with the Gemini API in Vertex AI.
`tuning/`	Learn how to tune and customize the Gemini models for specific use-cases.