googlecloudplatform--generative-ai/gemini

Generative AI

Gemini

YouTube Video: Introduction to Gemini on Vertex AI

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

Gemini API in Vertex AI

On Google Cloud, the Gemini API in Vertex AI provides a unified interface for interacting with multimodal Gemini models, such as:

Using this repository

• agent-engine/: Learn how to use the Agent Engine with Gemini.
• agents/: Samples of how to build agents with Gemini.
• autocal/: Learn about Autocal with Gemini.
• batch-prediction/: Learn how to use batch prediction with Gemini.
• chat-completions/: Learn about chat completions with the Gemini API.
• code-execution/: Learn about code execution with Gemini.
• context-caching/: Learn about context caching with Gemini.
• controlled-generation/: Learn about controlled generation with Gemini.
• evaluation/: Learn how to evaluate Gemini models.
• function-calling/: Learn how to use function calling with Gemini.
• getting-started/: Get started with the Gemini API.
• global-endpoint/: Learn how to use the global endpoint for Gemini.
• grounding/: Learn about grounding with Gemini.
• logprobs/: Learn about logprobs with Gemini.
• long-context/: Learn about long context with Gemini.
• mcp/: Learn about the Multi-turn Conversation Platform (MCP) with Gemini.
• model-optimizer/: Learn about the Model Optimizer for Gemini.
• multimodal-dataset/: Learn how to work with multimodal datasets for Gemini.
• multimodal-live-api/: Learn how to use the Multimodal Live API with Gemini.
• nano-banana/: Learn about Nano Banana with Gemini.
• orchestration/: Learn about orchestration with Gemini.
• prompts/: Learn about prompt design for Gemini.
• rag-engine/: Learn about the RAG Engine with Gemini.
• reasoning-engine/: Learn about the Reasoning Engine with Gemini.
• responsible-ai/: Learn about responsible AI with Gemini.
• sample-apps/: Sample applications using the Gemini API.
• thinking/: Learn about the thinking process of Gemini.
• tuning/: Learn how to tune Gemini models.
• url-context/: Learn how to use URL context with Gemini.
• use-cases/: Explore various use cases for Gemini.

Contributing

Contributions welcome! See the Contributing Guide.

Getting help

Please use the issues page to provide suggestions, feedback or submit a bug report.

Disclaimer

This repository itself is not an officially supported Google product. The code in this repository is for demonstrative purposes only.