This workshop teaches how to build with Gemini using the Gemini API and Python SDK.
Prerequisites: You need an API key from Google AI Studio. Everything can be done on the free tier.
| Topic | Description | Code |
|---|---|---|
| ⚙️ 00 Setup & API key | Get started with the Gemini API and Python SDK | Setup README |
| 📒 01 Text prompting | Learn about text prompting, chats, token usage, parameters |  |
| 🖼️ 02 Multimodal capabilities | Prompt with images, videos, audio, PDFs, and code, and perform TTS | |
| 🔨 03 Thinking and tools | Learn about thinking configurations, structured outputs, and tools | |
| 🎙️ 04 Live API | Talk to Gemini live and stream audio & video | Live API code |
| 🔧 05 MCP | Connect Gemini to a locally running and remote MCP server | MCP code |
| 🤔 06 Gemini 2.5 comparisons | Compare Gemini 2.5 Pro, Flash, and Flash-Lite on a few tasks | |
If you have questions or feedback, reach out on X @patloeber.