Exploratory APIs are primarily intended for local prototyping. With these APIs, we're asking for feedback to confirm assumptions and determine what task APIs we build in the future. As such, exploratory APIs may never launch.
Early preview program participants will receive more detailed information about the following APIs.
Prompt API
With the Prompt API, early preview program participants can send natural language requests to Gemini Nano in Chrome.
The Prompt API explainer differs from the current implementation, as there are additional methods and enhancements we hope to implement over time.
In Chrome Extensions
With the Prompt API exposed to Chrome Extensions, you could experiment in a real environment, and we'd gain deeper insights. Based on the findings, we can refine the API to better address real-world use cases.
Our goal is to use this simpler scope to test some ideas, learn more effectively than from isolated prototypes, which would ultimately support a higher quality API.
This proposal is still in review, so we don't yet have a detailed timeline for when the Prompt API would be available in Chrome Extensions.
Summarization API
A summarization API is now available for local experimentation to our early preview program participants. With this API, you use built-in Gemini Nano to condense long-form content. Shorter content can be more accessible and useful to users for a number of use cases.
The writing assistance APIs explainer is available as a proposal for the future development. You can help this proposal move to the next stage by indicating your support with a thumbs-up reaction or by commenting with details about your use cases and context.
Use cases
There are a number of use cases for summarization:
- Overview of a meeting transcript for those joining the meeting late or those who missed the meeting entirely.
- Key points from support conversations for customer relationship management.
- Sentence or paragraph-sized summaries of multiple product reviews.
- Key points from long articles, to help readers determine if the article is relevant.
- Generating draft titles for an article.
- Summarizing questions in a forum to help experts find those which are most relevant to their field of expertise.
Do you have additional ideas for a summarization API? Share them with us on GitHub.
Language detection
A language detection API is now available for local experimentation to our early preview program participants. With this API, you use built-in Gemini Nano to identify which language is used on a web page.
Language detection is the first step for translation. Browsers often already have language detection capabilities, and this API will allow web developers to access this technology with a JavaScript API.
Do you have additional ideas? Share them with us on GitHub.
Participate in early testing
We'll wield your feedback to shape the future of these APIs, to ensure they meet the needs of developers and users.
Join our early preview program to experiment with early-stage built-in AI APIs.
In the meantime, you can learn how to use Gemini Pro on Google's servers with your websites and web apps in our quickstart for the Google AI JavaScript SDK.