Google makes more Gemini templates available to developers


Google is expansion the range of large Gemini language models that it now makes available to developers on its Vertex AI platform.

Gemini 1.0 Pro (which was still known as Gemini Pro 1.0 only a week ago – because Google is very good at branding) is now generally available after being in public preview for a while. Meanwhile, Google says that Gemini 1.0 Ultra (which you may also remember in its previous form as Gemini Ultra 1.0) is now generally available “via a greenlist,” which isn’t exactly how it typically works general availability.

Google also today announced Gemini 1.5 Pro (not Gemini Pro 1.5, of course), an update to its existing Gemini Pro model that the company says performs at the level of Gemini 1.0 Ultra, its current flagship model. Perhaps more importantly, this model can handle a context of a million tokens. That’s approximately 1 hour of video, 30,000 lines of code, and over 700,000 words. This model, which also uses what Google describes as a “new expert blending approach,” is currently in private preview.

In Vertex, Google is also now adding support for adapter-based tuning, with support for techniques like reinforcement learning from human feedback and distillation coming soon. Additionally, developers can now more easily enrich their models with up-to-date data, and for more complex workflows, they can now also call functions. This will allow the developer to connect the Gemini model to external APIs.

As for other developer tools, Google says it now offers access to the Gemini API from the Dart SDK so developers can easily use it in their Dart and Flutter apps. This also makes it easier for developers to use the Gemini API. with the IDX projectits experimental web-based integrated development platform, and adding integration to Firebase, its mobile development platform, as an extension.


Leave a Comment

Your email address will not be published. Required fields are marked *