Results for “multimodal-streaming”

5 skills

Google Cloud Solution Agentic AI Bidirectional Streaming

Designs and implements a Google Cloud solution for live, bidirectional multimodal streaming workloads with AI agents, covering requirements discovery, architecture design, and deployment planning.

More results

Gemini Interactions API

Call the Gemini API for text generation, chat, multimodal understanding, image/video/audio generation, streaming, function calling, structured output, and managed agents using the Interactions API in Python and TypeScript.

Debug and modify agent streaming behavior, covering SSE and plain-text transports, ChatKit events, and session continuity.

Build applications with Gemini API hosted models, including multimodal content, function calling, and structured outputs, using the latest SDKs and model specifications.

Gemini Interactions API

Writes Python and TypeScript code that calls the Gemini Interactions API for text generation, chat, multimodal understanding, image generation, streaming, research, function calling, and structured output, including migration from the legacy generateContent API.