Workflows · Skill

Gemini cookbook

The Gemini cookbook search-grounding notebook streams a company report using the Gemini API and Google Search.

+ Follow

Builder facts

  • Notebook runtime. The Colab example uses the Google Gen AI Python SDK and reads GEMINI_API_KEY from Colab Secrets. Source ↗
  • Grounding. The notebook enables the Google Search tool, streams model output and renders Search Suggestions from grounding metadata. Source ↗
  • Report extraction. The notebook buffers the report after a delimiter in the streamed output and renders it as Markdown. Source ↗
  • Billing. The default Gemini 3.8 Flash model requires a Paid Tier key for Google Search grounding. The model’s text generation and Search grounding have separate rates. Source ↗

Sources checked

Publisher update ·

Search-grounding notebook adds Gemini 4 Hydrogen ↗

The notebook added Gemini 4 Hydrogen to the model picker and kept Gemini 3.8 Flash as the default.

Change timeline

0 stories

No verified releases in this timeline yet.