{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# 组件配置\n\nAutoGen组件能够以声明式的方式进行通用配置。这既支持基于配置的体验（如AutoGen Studio），也适用于许多其他场景。\n\n提供此功能的系统称为\"组件配置\"。在AutoGen中，组件就是可以从配置对象创建，并能转储为配置对象的实体。通过这种方式，您可以在代码中定义组件，然后从中获取配置对象。\n\n该系统是通用的，允许以相同方式配置AutoGen外部定义的组件（如扩展）。\n\n## 与状态有何不同？\n\n这是需要澄清的重要概念。当我们序列化对象时，必须包含构成该对象的所有数据（包括消息历史等）。从序列化状态反序列化时，必须得到完全相同的对象。但组件配置不同。\n\n组件配置应被视为对象的蓝图，可以多次复制以创建多个相同配置的实例。\n\n## 使用方法\n\n如果您有一个Python组件并想获取其配置，只需对其调用{py:meth}`~autogen_core.ComponentToConfig.dump_component`方法。生成的对象可以传回{py:meth}`~autogen_core.ComponentLoader.load_component`以恢复组件。\n\n### 从配置加载组件\n\n要从配置对象加载组件，可以使用{py:meth}`~autogen_core.ComponentLoader.load_component`方法。该方法接收配置对象并返回组件对象。建议在所需接口上调用此方法。例如加载模型客户端：\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "from autogen_core.models import ChatCompletionClient\n",
        "\n",
        "config = {\n",
        "    \"provider\": \"openai_chat_completion_client\",\n",
        "    \"config\": {\"model\": \"gpt-4o\"},\n",
        "}\n",
        "\n",
        "client = ChatCompletionClient.load_component(config)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## 创建组件类\n\n要为给定类添加组件功能：\n\n1. 在类继承列表中添加{py:meth}`~autogen_core.Component`调用\n2. 实现{py:meth}`~autogen_core.ComponentToConfig._to_config`和{py:meth}`~autogen_core.ComponentFromConfig._from_config`方法\n\n例如：\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "from autogen_core import Component, ComponentBase\n",
        "from pydantic import BaseModel\n",
        "\n",
        "\n",
        "class Config(BaseModel):\n",
        "    value: str\n",
        "\n",
        "\n",
        "class MyComponent(ComponentBase[Config], Component[Config]):\n",
        "    component_type = \"custom\"\n",
        "    component_config_schema = Config\n",
        "\n",
        "    def __init__(self, value: str):\n",
        "        self.value = value\n",
        "\n",
        "    def _to_config(self) -> Config:\n",
        "        return Config(value=self.value)\n",
        "\n",
        "    @classmethod\n",
        "    def _from_config(cls, config: Config) -> \"MyComponent\":\n",
        "        return cls(value=config.value)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## 密钥管理\n\n如果配置对象的字段是密钥值，应使用[`SecretStr`](https://docs.pydantic.dev/latest/api/types/#pydantic.types.SecretStr)标记，这将确保该值不会被转储到配置对象中。\n\n例如：\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {},
      "outputs": [],
      "source": [
        "from pydantic import BaseModel, SecretStr\n",
        "\n",
        "\n",
        "class ClientConfig(BaseModel):\n",
        "    endpoint: str\n",
        "    api_key: SecretStr"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": ".venv",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.12.5"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}