Google Gemini for Developers

Learn best practices, patterns and processes for developers and DevOps teams who design and implement LLM-based applications using Google Gemini.

Introduction

• Build LLM-based applications with Google Gemini
• What you should know
• Using cloud services

1. Gemini Dev Environments

• Understanding Google Gemini
• Use Google AI Studio
• Use Vertex AI Studio
• Use Colab Notebooks
• Use Gemini Code Assist in cloud workstations

2. Gemini Prompts

• Use Google AI Studio to test prompts
• Use system instructions with prompts
• Design and test language model prompts
• Design and test multimodal prompts
• Design prompts in Cloud Code for APIs

3. Gemini Notebooks and APIs

• Using the Gemini API: Set up
• Using the Gemini API: Testing prompts
• Using function calling with Gemini
• Programming multimodal use cases
• Use the Gemini File API
• Use embeddings with Gemini
• Set up a RAG pattern with Gemini
• Implement a RAG pattern with Gemini

4. Gemini Model Evaluation

• Understand model grounding
• Ground a model with Google Search
• Ground with a semantic retriever
• Understand model evaluation
• Perform model evaluation
• Fine-tune a Gemini model

5. Gemini Applications

• Use Vertex AI Model Garden
• Deploy a GenAI cloud architecture: Document summaries
• Deploy a GenAI cloud architecture: Knowledge base
• Preview of Vertex AI Agent Builder

Conclusion

• Next steps