Build a streaming agent

构建流式传输智能体

The Agent Development Kit (ADK) enables real-time, interactive experiences with your AI agents through streaming. This allows for features like live voice conversations, real-time tool use, and continuous updates from your agent.

智能体开发工具包 (ADK) 通过流式传输实现与AI智能体的实时、交互式体验。这支持实时语音对话、实时工具使用以及来自智能体的持续更新等功能。

This page provides quickstart examples to get you up and running with streaming capabilities in both Python and Java ADK.

本页面提供了快速入门示例,帮助您在 Python 和 Java ADK 中使用流式传输功能。

• Python ADK: Streaming agent

  ---

  This example demonstrates how to set up a basic streaming interaction with an agent using Python ADK. It typically involves using the Runner.run_live() method and handling asynchronous events.

  此示例演示了如何使用 Python ADK 设置与智能体的基本流式传输交互。通常涉及使用 Runner.run_live() 方法并处理异步事件。

  View Python Streaming Quickstart
  

• Java ADK: Streaming agent

  ---

  This example demonstrates how to set up a basic streaming interaction with an agent using Java ADK. It involves using the Runner.runLive() method, a LiveRequestQueue, and handling of Flowable<Event> stream.

  此示例演示了如何使用 Java ADK 设置与智能体的基本流式传输交互。涉及使用 Runner.runLive() 方法、LiveRequestQueue 和处理 Flowable<Event> 流。

  View Java Streaming Quickstart