Get examples of how to use tools like Google Search, function calling, and code execution with the Multimodal Live API and Gemini 2.0 Flash Experimental. You can now use multiple tools in a single API call. ↓
Google AI Developers
Technology, Information and Internet
AI for every developer. So what will you build?
About us
Our goal is to equip developers with the most advanced models to build new applications, helpful tools to write better and faster code, and make it easy to integrate across platforms and devices.
- Website
-
https://ai.google.dev
External link for Google AI Developers
- Industry
- Technology, Information and Internet
- Company size
- 10,001+ employees
Updates
-
Use Google Search as a tool in Gemini 2.0 Flash Experimental, including visualizing results in a graph. Give it a try in this notebook. ↓
cookbook/gemini-2/search_tool.ipynb at main · google-gemini/cookbook
github.com
-
Discover Gemini’s spatial understanding in the third dimension! This notebook focuses on more advanced real-world understanding, including pointing and 3D spatial understanding. ↓
cookbook/gemini-2/spatial_understanding_3d.ipynb at main · google-gemini/cookbook
github.com
-
Explore Gemini's image and spatial understanding capabilities. Use 2D and 3D object detection, pointing, and more with Gemini 2.0 Flash Experimental in this introductory notebook. ↓ 🔎
cookbook/gemini-2/spatial_understanding.ipynb at main · google-gemini/cookbook
github.com
-
💡 Learn how to use Gemini 2.0's Multimodal Live API to build applications that interact with users through voice, visuals, and screen sharing. All in real-time. → https://goo.gle/4gtcj2W
-
-
Explore the capabilities of Gemini 2.0 Flash Experimental with the spatial understanding starter app in Google AI Studio. Start experimenting with 2D and 3D bounding boxes in addition to object detection. → https://goo.gle/3ZSvtIm
-
-
Jump right into the Multimodal Live API! This notebook provides a baseline introduction to the Gemini 2.0 Multimodal Live API. ↓
cookbook/gemini-2/live_api_starter.ipynb at main · google-gemini/cookbook
github.com
-
Stream audio and video directly into your apps with the Multimodal Live API in Google AI Studio. Get started building with this boilerplate: https://goo.gle/49zbvqC
-
Get started building with the Multimodal Live API. Create real-time apps with audio and video streaming inputted from cameras or screens. ↓
cookbook/gemini-2/live_api_starter.py at main · google-gemini/cookbook
github.com
-
The new Google Gen AI SDK provides a unified interface to Gemini 2.0 through the Gemini API. Check out the cookbook to get started ↓
cookbook/gemini-2/get_started.ipynb at main · google-gemini/cookbook
github.com