§ tools · storyline

Adds vertex.interactions() for Gemini Interactions API on Vertex AI

Google adds vertex.interactions() method to Vertex AI SDK for Gemini Interactions API with multimodal output support.

Jul 2 · 02:19:19 · primary fetch1 sourceupdated Jul 2 · 02:19:22

Patch Changes d20f0dc: Add `vertex.interactions()` for the Gemini Interactions API on Vertex AI. Targets the location-scoped `.../locations/{region}/interactions` resource using the existing Vertex OAuth credentials, enabling multimodal-output models such as `gemini-omni-flash-preview` (video output) through Vertex.

The `GoogleInteractionsLanguageModel` is now exported from `@ai-sdk/google/internal` for provider reuse.

read full article on github.com ↗

§ sources2 publications · timeline below

github.comVercel AI SDK — google v4.0.6primary02:19:19
github.comVercel AI SDK — google-vertex v5.0.802:19:22

§ how this story moved

02:19:19primary — Vercel AI SDK — Releases publishes the launch post.
02:19:22Vercel AI SDK — Releases picks up coverage.