5 practical Gemini API uses for developers

Опубликовано 22 мая 2025, 3:06

Explore practical uses of the Gemini API for developers, like how to build innovative applications with Gemini's features. We'll cover image understanding for tasks like object recognition and scene description; creating multimodal interactions that combine voice, text, and images for more natural user experiences; and how to automate complex workflows through function calling. We’ll also share how to use the long context window to enable complex reasoning, and multi-step problem solving.

Resources:
Gemini API → ai.google.dev/gemini-api
Gemini API Cookbook on GitHub → goo.gle/cookbook
GenList demo → goo.gle/genlist-demo
Live API - Web Console → goo.gle/3SvUZji
Gemini 2.0 - Multi-tool with the Multimodal Live API → goo.gle/gemini-maps-plots
Gemini 2.0: Browser as a tool → goo.gle/gemini-browser-tool

Speaker: Mark McDonald

Check out all the keynote sessions from Google I/O 2025 → goo.gle/io25-keynote-sessions
Check out the AI session track from Google I/O 2025 → goo.gle/io25-ai-yt
Check out all of the sessions from Google I/O 2025→ goo.gle/io25-sessions-yt

Subscribe to Google for Developers → goo.gle/developers

Event: Google I/O 2025

Products Mentioned: AI/Machine Learning