AI Camp Seattle Gemini Deep Dive, March 31, 2025

Workshop Guide:

• AI Studio - Google AI Studio
• Create an API Key - Create a free API Key
• Search Grounding - Grounding using Search as a tool
• Multimodal Live API Quickstart - This notebook demonstrates simple usage of the Gemini 2.0 Multimodal Live API. For an overview of new capabilities refer to the Gemini 2.0 docs.
• Spatial Understanding - This notebook introduces object detection and spatial understanding with the Gemini API like in the Spatial understanding example from AI Studio and demonstrated in the Building with Gemini 2.0: Spatial understanding video.
• Gemini 2.0 - Multimodal Live API - This notebook provides examples of how to use tools with the multimodal live API with Gemini 2.0.
• Gemini Thinking - Gemini 2.5 Pro Experimental and Gemini Flash 2.0 Thinking are models that are trained to generate the "thinking process" the model goes through as part of its response. As a result, those models are capable of stronger reasoning capabilities in its responses than previous models.
• Gemini Deep Research - Explore Deep Research in Gemini
• Code Execution - The Gemini API code execution feature enables the model to generate and run Python code based on plain-text instructions that you give it, and even output graphs.
• Imagen - The imagen-3.0-generate-002 model is Google's highest quality text-to-image model, featuring a number of new and improved capabilities.
• Embeddings - The Gemini API generates state-of-the-art text embeddings. An embedding is a list of floating point numbers that represent the meaning of a word, sentence, or paragraph. You can use embeddings in many downstream applications like document search.
• Gemini 2.5 Pro - Available in AI Studio and the Gemini app.

Google Gemini Cookbook - Even more examples and quickstarts