From 701d5c29cddc9e177cfcd3284b2e781b54d97fb1 Mon Sep 17 00:00:00 2001 From: nowadays0421 Date: Sat, 3 Jun 2023 11:45:44 +0800 Subject: [PATCH] rename --- ...-part2.ipynb => 10.Evaluation-part2.ipynb} | 0 ... Models, the Chat Format and Tokens.ipynb} | 0 .../3.Classification.ipynb | 330 ++++++++++++++++++ ...ck Outputs.ipynb => 7.Check Outputs.ipynb} | 0 ...{7.Evaluation.ipynb => 8.Evaluation.ipynb} | 0 ...n-part1.ipynb => 9.Evaluation-part1.ipynb} | 0 6 files changed, 330 insertions(+) rename content/Building Systems with the ChatGPT API/{9.Evaluation-part2.ipynb => 10.Evaluation-part2.ipynb} (100%) rename content/Building Systems with the ChatGPT API/{1.Language Models, the Chat Format and Tokens.ipynb => 2.Language Models, the Chat Format and Tokens.ipynb} (100%) create mode 100644 content/Building Systems with the ChatGPT API/3.Classification.ipynb rename content/Building Systems with the ChatGPT API/{6.Check Outputs.ipynb => 7.Check Outputs.ipynb} (100%) rename content/Building Systems with the ChatGPT API/{7.Evaluation.ipynb => 8.Evaluation.ipynb} (100%) rename content/Building Systems with the ChatGPT API/{8.Evaluation-part1.ipynb => 9.Evaluation-part1.ipynb} (100%) diff --git a/content/Building Systems with the ChatGPT API/9.Evaluation-part2.ipynb b/content/Building Systems with the ChatGPT API/10.Evaluation-part2.ipynb similarity index 100% rename from content/Building Systems with the ChatGPT API/9.Evaluation-part2.ipynb rename to content/Building Systems with the ChatGPT API/10.Evaluation-part2.ipynb diff --git a/content/Building Systems with the ChatGPT API/1.Language Models, the Chat Format and Tokens.ipynb b/content/Building Systems with the ChatGPT API/2.Language Models, the Chat Format and Tokens.ipynb similarity index 100% rename from content/Building Systems with the ChatGPT API/1.Language Models, the Chat Format and Tokens.ipynb rename to content/Building Systems with the ChatGPT API/2.Language Models, the Chat Format and Tokens.ipynb diff --git a/content/Building Systems with the ChatGPT API/3.Classification.ipynb b/content/Building Systems with the ChatGPT API/3.Classification.ipynb new file mode 100644 index 0000000..5198713 --- /dev/null +++ b/content/Building Systems with the ChatGPT API/3.Classification.ipynb @@ -0,0 +1,330 @@ +{ + "cells": [ + { + "attachments": {}, + "cell_type": "markdown", + "id": "63651c26", + "metadata": {}, + "source": [ + "第三章 评估输入——分类" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "87d9de1d", + "metadata": {}, + "source": [ + "## Setup\n", + "加载 API_KEY 并封装一个调用 API 的函数" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "55ee24ab", + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "import openai\n", + "from dotenv import load_dotenv, find_dotenv\n", + "_ = load_dotenv(find_dotenv()) # read local .env file\n", + "os.environ['OPENAI_API_KEY']" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "0318b89e", + "metadata": {}, + "outputs": [], + "source": [ + "def get_completion_from_messages(messages, \n", + " model=\"gpt-3.5-turbo\", \n", + " temperature=0, \n", + " max_tokens=500):\n", + " response = openai.ChatCompletion.create(\n", + " model=model,\n", + " messages=messages,\n", + " temperature=temperature, \n", + " max_tokens=max_tokens,\n", + " )\n", + " return response.choices[0].message[\"content\"]" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "af0ff2b2", + "metadata": {}, + "source": [ + "在本节中，我们将专注于评估输入的任务，这对于确保系统的质量和安全性非常重要。\n", + "\n", + "对于需要处理不同情况下的许多独立指令集的任务，首先对查询类型进行分类，然后根据该分类确定要使用哪些指令会很有好处。\n", + "\n", + "这可以通过定义固定的类别和hard-coding与处理给定类别任务相关的指令来实现。\n", + "\n", + "例如，在构建客户服务助手时，首先对查询类型进行分类，然后根据该分类确定要使用哪些指令可能比较重要。\n", + "\n", + "因此，例如，如果用户要求关闭其帐户，您可能会给出不同的辅助指令，而如果用户询问特定产品，则可能会添加其他产品信息。\n", + "\n", + "让我们看一个例子，帮助我们理解的更清晰。" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "f2b55807", + "metadata": {}, + "source": [ + "#### 对用户指令进行分类" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "c3216166", + "metadata": {}, + "source": [ + "在这里，我们有我们的系统消息，它是对整个系统的指导，并且我们正在使用这个分隔符。\n", + "\n", + "分隔符只是一种分隔指令或输出不同部分的方式，并且它有助于模型确定不同的部分。\n", + "\n", + "因此，对于这个例子，我们将使用#作为分隔符。\n", + "\n", + "这是一个很好的分隔符，因为它实际上被表示为一个token。" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "id": "3b406ba8", + "metadata": {}, + "outputs": [], + "source": [ + "delimiter = \"####\"" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "049d0d82", + "metadata": {}, + "source": [ + "这是我们的系统消息，我们正在以下面的方式询问模型。" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "id": "29e2d170", + "metadata": {}, + "outputs": [], + "source": [ + "system_message = f\"\"\"\n", + "You will be provided with customer service queries. \\\n", + "The customer service query will be delimited with \\\n", + "{delimiter} characters.\n", + "Classify each query into a primary category \\\n", + "and a secondary category. \n", + "Provide your output in json format with the \\\n", + "keys: primary and secondary.\n", + "\n", + "Primary categories: Billing, Technical Support, \\\n", + "Account Management, or General Inquiry.\n", + "\n", + "Billing secondary categories:\n", + "Unsubscribe or upgrade\n", + "Add a payment method\n", + "Explanation for charge\n", + "Dispute a charge\n", + "\n", + "Technical Support secondary categories:\n", + "General troubleshooting\n", + "Device compatibility\n", + "Software updates\n", + "\n", + "Account Management secondary categories:\n", + "Password reset\n", + "Update personal information\n", + "Close account\n", + "Account security\n", + "\n", + "General Inquiry secondary categories:\n", + "Product information\n", + "Pricing\n", + "Feedback\n", + "Speak to a human\n", + "\n", + "\"\"\"" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "e6a932ce", + "metadata": {}, + "source": [ + "现在我们来看一个用户消息的例子，我们将使用以下内容。" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "id": "2b2df0bf", + "metadata": {}, + "outputs": [], + "source": [ + "user_message = f\"\"\"\\ \n", + "I want you to delete my profile and all of my user data\"\"\"" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "3a2c1cf0", + "metadata": {}, + "source": [ + "将这个消息格式化为一个消息列表，系统消息和用户消息使用####\"进行分隔。\n", + "\n", + "让我们想一想，作为人类，这句话什么意思：\"我想让您删除我的个人资料。\"\n", + "\n", + "这句话看上去属于\"Account Management\"类别，也许是属于\"Close account\"这一项。 " + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "id": "6e2b9049", + "metadata": {}, + "outputs": [], + "source": [ + "messages = [ \n", + "{'role':'system', \n", + " 'content': system_message}, \n", + "{'role':'user', \n", + " 'content': f\"{delimiter}{user_message}{delimiter}\"}, \n", + "]" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "4b295207", + "metadata": {}, + "source": [ + "让我们看看模型是如何思考的\n", + "\n", + "模型的分类是\"Account Management\"作为\"primary\"，\"Close account\"作为\"secondary\"。\n", + "\n", + "请求结构化输出（如JSON）的好处是，您可以轻松地将其读入某个对象中，\n", + "\n", + "例如Python中的字典，或者如果您使用其他语言，则可以使用其他对象作为输入到后续步骤中。" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "id": "77328388", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{\n", + " \"primary\": \"General Inquiry\",\n", + " \"secondary\": \"Product information\"\n", + "}\n" + ] + } + ], + "source": [ + "response = get_completion_from_messages(messages)\n", + "print(response)" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "2f6b353b", + "metadata": {}, + "source": [ + "我将向您展示另一个示例，但您也可以随时暂停视频，自己尝试提问，并查看模型如何对其进行分类。\n", + "\n", + "这是另一个用户消息: \"告诉我更多关于你们的平板电视\"\n", + "\n", + "我们只是有相同的消息列表，模型的响应，然后我们打印它。\n", + "\n", + "结果这里是我们的第二个分类，看起来应该是正确的。" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "id": "edf8fbe9", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{\n", + " \"primary\": \"General Inquiry\",\n", + " \"secondary\": \"Product information\"\n", + "}\n" + ] + } + ], + "source": [ + "user_message = f\"\"\"\\\n", + "Tell me more about your flat screen tvs\"\"\"\n", + "messages = [ \n", + "{'role':'system', \n", + " 'content': system_message}, \n", + "{'role':'user', \n", + " 'content': f\"{delimiter}{user_message}{delimiter}\"}, \n", + "] \n", + "response = get_completion_from_messages(messages)\n", + "print(response)" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "8f87f68d", + "metadata": {}, + "source": [ + "所以总的来说，根据客户咨询的分类，我们现在可以提供一套更具体的指令来处理后续步骤。\n", + "\n", + "在这种情况下，我们可能会添加关于电视的额外信息，而不同情况下，我们可能希望提供关闭账户的链接或类似的内容。\n", + "\n", + "我们将在以后的视频中了解更多有关处理输入的不同方法。\n", + "\n", + "在下一个视频中，我们将探讨更多评估输入的方法，特别是确保用户以负责任的方式使用系统的方法。" + ] + } + ], + "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": "3.8.16" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/content/Building Systems with the ChatGPT API/6.Check Outputs.ipynb b/content/Building Systems with the ChatGPT API/7.Check Outputs.ipynb similarity index 100% rename from content/Building Systems with the ChatGPT API/6.Check Outputs.ipynb rename to content/Building Systems with the ChatGPT API/7.Check Outputs.ipynb diff --git a/content/Building Systems with the ChatGPT API/7.Evaluation.ipynb b/content/Building Systems with the ChatGPT API/8.Evaluation.ipynb similarity index 100% rename from content/Building Systems with the ChatGPT API/7.Evaluation.ipynb rename to content/Building Systems with the ChatGPT API/8.Evaluation.ipynb diff --git a/content/Building Systems with the ChatGPT API/8.Evaluation-part1.ipynb b/content/Building Systems with the ChatGPT API/9.Evaluation-part1.ipynb similarity index 100% rename from content/Building Systems with the ChatGPT API/8.Evaluation-part1.ipynb rename to content/Building Systems with the ChatGPT API/9.Evaluation-part1.ipynb