google-adk-python

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Google ADK (Python) Skill

Google ADK（Python）技能

This skill provides comprehensive documentation and Python examples for the Google Agent Development Kit (ADK). It maps documentation topics to their corresponding Python code snippets.

本技能提供Google Agent Development Kit（ADK）的全面文档及Python示例，将文档主题与对应的Python代码片段关联起来。

How to Use

使用方法

Identify the user's specific interest or task and refer to the relevant reference file below. Each reference file contains links to the official documentation (Markdown) and the corresponding Python examples (raw code).

确定用户的具体兴趣或任务，然后参考下方对应的参考文件。每个参考文件都包含官方文档（Markdown格式）的链接以及对应的Python示例（原始代码）。

Topics

主题

1. Getting Started

1. 入门指南

For installation, quickstarts, and basic agent setup.

Reference: references/get-started.md

涵盖安装、快速上手及基础Agent设置。

参考文档：references/get-started.md

2. Agents & Models

2. Agent与模型

For creating different types of agents (LLM, Workflow, Loop, Parallel, Sequential) and configuring specific models (Gemini, Anthropic, etc.).

Agents Reference: references/agents.md
Models Reference: references/models.md

涵盖创建不同类型的Agent（LLM、Workflow、Loop、Parallel、Sequential）以及配置特定模型（Gemini、Anthropic等）。

Agent参考文档：references/agents.md
模型参考文档：references/models.md

3. Tools (Basic & Advanced)

3. 工具（基础与进阶）

For integrating tools like Google Search, Code Execution, BigQuery, third-party services (GitHub, Jira, etc.), MCP, and Grounding.

Basic Tools Reference: references/tools.md
Advanced Tools Reference: references/advanced-tools.md

涵盖集成Google Search、代码执行、BigQuery、第三方服务（GitHub、Jira等）、MCP及Grounding等工具。

基础工具参考文档：references/tools.md
进阶工具参考文档：references/advanced-tools.md

4. Streaming

4. 流处理

For building real-time, low-latency streaming agents (audio/video).

Reference: references/streaming.md

涵盖构建实时、低延迟的流处理Agent（音频/视频）。

参考文档：references/streaming.md

5. Callbacks

5. 回调

For hooking into agent lifecycle events (before/after agent, model, tool execution).

Reference: references/callbacks.md

涵盖挂钩Agent生命周期事件（Agent、模型、工具执行前后）。

参考文档：references/callbacks.md

6. Runtime & Architecture

6. 运行时与架构

For deep dives into the Runtime, Sessions, Memory, Context, Events, Artifacts, and Plugins.

Reference: references/runtime-arch.md

深入讲解Runtime、会话、内存、上下文、事件、工件及插件相关内容。

参考文档：references/runtime-arch.md

7. Deployment & Operations

7. 部署与运维

For deploying agents (Cloud Run, GKE) and observability (Logging, Tracing, Evaluation).

Reference: references/deploy-ops.md

涵盖Agent部署（Cloud Run、GKE）及可观测性（日志、追踪、评估）。

参考文档：references/deploy-ops.md

8. Tutorials & Samples

8. 教程与示例

For end-to-end tutorials and complete agent samples (e.g., YouTube Shorts Assistant, Weather Agent).

Reference: references/tutorials.md

涵盖端到端教程及完整的Agent示例（如YouTube Shorts助手、天气Agent）。

参考文档：references/tutorials.md

9. API Reference

9. API参考

For REST API details.

Reference: references/api.md

涵盖REST API详情。

参考文档：references/api.md

10. General Information

10. 通用信息

For project info, community, release notes, and limitations.

Reference: references/general.md

涵盖项目信息、社区、发布说明及限制条件。

参考文档：references/general.md

Instructions

说明

When a user asks about a specific topic, load the corresponding reference file to get the URLs for the documentation and code.
You can read the content of the linked files using
```
web_fetch
```
or
```
run_shell_command
```
with
```
curl
```
if you need to provide the actual content to the user.
Always prefer providing the Python example code when explaining a concept.

当用户询问特定主题时，加载对应的参考文件以获取文档和代码的URL。
如果需要向用户提供实际内容，可使用
```
web_fetch
```
或带
```
curl
```
的
```
run_shell_command
```
读取链接文件的内容。
解释概念时，优先提供Python示例代码。