Gemini Nano Prompt API Demo

A starting point for a client-side, LLM in the browser, for online and offline Javascript use.

NOT YET FOR MOBILE, DO NOT TRY YET ON MOBILE!

By Jeremy Ellis uses at your own risk
Github for these gitpages at https://github.com/hpssjellis/my-examples-of-web-llm
Main Demo index at https://hpssjellis.github.io/my-examples-of-web-llm/public/index.html

This page demonstrates the core features of the Gemini Nano Prompt API (`LanguageModel` API) available in Chrome 138+. Ensure you have enabled the necessary flags in chrome://flags:

• #prompt-api-for-gemini-nano (set to Enabled)
• #optimization-guide-on-device-model (set to Enabled BypassPrefRequirement)
• #prompt-api-for-gemini-nano-multimodal-input (for multimodal input)
• #summarization-api-for-gemini-nano (for summarization)
• #writer-api-for-gemini-nano (for writing)
• #rewriter-api-for-gemini-nano (for rewriting)

The Gemini Nano model will download the first time you use it. That will be about 4.0 GB of download and will need about 20 GB saving space for the final folders.

Output:

No output yet. Click a button to begin.