prompt-engineering-for-developers/docs/content/环境配置.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 环境配置"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "我们需要配置⼀个环境来运⾏ Python、Jupyter Notebook、OpenAI API key、相关库以及运⾏本书所需的代码，快速⼊⻔。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 安装Anaconda"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "通过清华源镜像来安装[Anaconda](https://mirrors.tuna.tsinghua.edu.cn/anaconda/archive)\n",
    "\n",
    "<p align=\"center\">\n",
    "  <img src=\"../../figures/docs/C0/Anaconda-file-list.png\" width=\"1000\" alt=\"Anaconda下载\">\n",
    "</p>\n",
    "\n",
    "选择对应的版本下载安装即可。\n",
    "\n",
    "\n",
    "如果已安装Anaconda，则可以跳过以下步骤。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 如果我们使用Window系统，可以下载`Anaconda3-2023.07-1-Windows-x86_64.exe`安装包直接安装即可。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 如果我们使用MacOS系统\n",
    "    1. Intel芯片：可以下载`Anaconda3-2023.07-1-MacOSX-x86_64.sh`\n",
    "    2. Apple芯片：可以下载`Anaconda3-2023.07-1-MacOSX-arm64.sh`\n",
    "    并执行以下操作："
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "shellscript"
    }
   },
   "outputs": [],
   "source": [
    "# 以Intel处理器为例，⽂件名可能会更改\n",
    "sh Anaconda3-2023.07-1-MacOSX-x86_64.sh -b"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "接下来，初始化终端Shell，以便我们可以直接运⾏conda。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "shellscript"
    }
   },
   "outputs": [],
   "source": [
    "~/anaconda3/bin/conda init"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "现在关闭并重新打开当前的shell，我们会发现在命令行的前面多了一个`(base)`,这是anaconda的一个基础`python`环境。下⾯我们使⽤以下命令来创建⼀个新的环境："
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "shellscript"
    }
   },
   "outputs": [],
   "source": [
    "# 创建一个名为chatgpt且python版本为3.9的环境\n",
    "conda create --name chatgpt python=3.9 -y"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "创建完成后，现在我们来激活 chatgpt 环境："
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "shellscript"
    }
   },
   "outputs": [],
   "source": [
    "conda activate chatgpt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 安装本书需要用到的python库"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install -q python-dotenv\n",
    "!pip install -q openai\n",
    "## 等更多的python包"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## OpenAI API key"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "在获取OpenAI API key之前我们需要[openai官网](https://openai.com/)中注册一个账号。这里假设我们已经有了openai账号，先在[openai官网](https://openai.com/)登录，登录后如下图所示：\n",
    "\n",
    "<p align=\"center\">\n",
    "  <img src=\"../../figures/docs/C0/openai-choose.png\" width=\"1000\" alt=\"openai官网登录后选择API\">\n",
    "</p>\n",
    "\n",
    "我们选择`API`，然后点击右上角的头像，选择`View API keys`，如下图所示：\n",
    "\n",
    "<p align=\"center\">\n",
    "  <img src=\"../../figures/docs/C0/openai-get-key.png\" width=\"1000\" alt=\"openai获取key\">\n",
    "</p>\n",
    "\n",
    "点击`Create new secret key`按钮创建OpenAI API key，我们将创建好的OpenAI API key复制以此形式`OPENAI_API_KEY=\"sk-...\"`保存到`.env`文件中，并将`.env`文件保存在项目根目录下。# TODO:放到哪个固定位置待确认\n",
    "\n",
    "下面是读取`.env`文件的代码"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import openai\n",
    "from dotenv import load_dotenv, find_dotenv\n",
    "\n",
    "# 读取本地/项目的环境变量。\n",
    "\n",
    "# find_dotenv()寻找并定位.env文件的路径\n",
    "# load_dotenv()读取该.env文件，并将其中的环境变量加载到当前的运行环境中  \n",
    "# 如果你设置的是全局的环境变量，这行代码则没有任何作用。\n",
    "_ = load_dotenv(find_dotenv())\n",
    "\n",
    "# 获取环境变量 OPENAI_API_KEY\n",
    "openai.api_key = os.environ['OPENAI_API_KEY']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "将读取`.env`文件的代码封装成函数供每一章节直接调用获取在OpenAI API key。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from dotenv import load_dotenv, find_dotenv\n",
    "def get_openai_key():\n",
    "    _ = load_dotenv(find_dotenv())\n",
    "    return os.environ['OPENAI_API_KEY']\n",
    "\n",
    "openai.api_key = get_openai_key()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}