Logan Zou
GitHub
@ -0,0 +1,447 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 第七章 文本扩展"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"扩展是将短文本（例如一组说明或主题列表）输入到大型语言模型中，让模型生成更长的文本（例如基于某个主题的电子邮件或论文）。这种应用是一把双刃剑，好处例如将大型语言模型用作头脑风暴的伙伴；但也存在问题，例如某人可能会使用它来生成大量垃圾邮件。因此，当你使用大型语言模型的这些功能时，请仅以**负责任** (responsible) 和**有益于人们** (helps people) 的方式使用它们。\n",
|
||||
"\n",
|
||||
"在本章中，你将学会如何基于 OpenAI API 生成*针对每位客户评价优化*的客服电子邮件。我们还将利用模型的另一个输入参数称为温度，这种参数允许您在模型响应中变化探索的程度和多样性。\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 一、定制客户邮件"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"我们将根据客户评价和情感，针对性写自动回复邮件。因此，我们将给定客户评价和情感，使用 LLM 针对性生成响应，即根据客户评价和评论情感生成定制电子邮件。\n",
|
||||
"\n",
|
||||
"我们首先给出一个示例，包括一个评论及对应的情感。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# 我们可以在推理那章学习到如何对一个评论判断其情感倾向\n",
|
||||
"sentiment = \"消极的\"\n",
|
||||
"\n",
|
||||
"# 一个产品的评价\n",
|
||||
"review = f\"\"\"\n",
|
||||
"他们在11月份的季节性销售期间以约49美元的价格出售17件套装，折扣约为一半。\\\n",
|
||||
"但由于某些原因（可能是价格欺诈），到了12月第二周，同样的套装价格全都涨到了70美元到89美元不等。\\\n",
|
||||
"11件套装的价格也上涨了大约10美元左右。\\\n",
|
||||
"虽然外观看起来还可以，但基座上锁定刀片的部分看起来不如几年前的早期版本那么好。\\\n",
|
||||
"不过我打算非常温柔地使用它，例如，\\\n",
|
||||
"我会先在搅拌机中将像豆子、冰、米饭等硬物研磨，然后再制成所需的份量，\\\n",
|
||||
"切换到打蛋器制作更细的面粉，或者在制作冰沙时先使用交叉切割刀片，然后使用平面刀片制作更细/不粘的效果。\\\n",
|
||||
"制作冰沙时，特别提示：\\\n",
|
||||
"将水果和蔬菜切碎并冷冻（如果使用菠菜，则轻轻煮软菠菜，然后冷冻直到使用；\\\n",
|
||||
"如果制作果酱，则使用小到中号的食品处理器），这样可以避免在制作冰沙时添加太多冰块。\\\n",
|
||||
"大约一年后，电机发出奇怪的噪音，我打电话给客服，但保修已经过期了，所以我不得不再买一个。\\\n",
|
||||
"总的来说，这些产品的总体质量已经下降，因此它们依靠品牌认可和消费者忠诚度来维持销售。\\\n",
|
||||
"货物在两天内到达。\n",
|
||||
"\"\"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"我们已经使用推断课程中所学方法提取了情感，这是一个关于搅拌机的客户评价，现在我们将根据情感定制回复。\n",
|
||||
"\n",
|
||||
"以下述 Prompt 为例：假设你是一个客户服务 AI 助手，你的任务是为客户发送电子邮件回复，根据通过三个反引号分隔的客户电子邮件，生成一封回复以感谢客户的评价。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"尊敬的客户，\n",
|
||||
"\n",
|
||||
"非常感谢您对我们产品的评价。我们非常抱歉您在购买过程中遇到了价格上涨的问题。我们一直致力于为客户提供最优惠的价格，但由于市场波动，价格可能会有所变化。我们深表歉意，如果您需要任何帮助，请随时联系我们的客户服务团队。\n",
|
||||
"\n",
|
||||
"我们非常感谢您对我们产品的详细评价和使用技巧。我们将会把您的反馈传达给我们的产品团队，以便改进我们的产品质量和性能。\n",
|
||||
"\n",
|
||||
"再次感谢您对我们的支持和反馈。如果您需要任何帮助或有任何疑问，请随时联系我们的客户服务团队。\n",
|
||||
"\n",
|
||||
"祝您一切顺利！\n",
|
||||
"\n",
|
||||
"AI客户代理\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from tool import get_completion\n",
|
||||
"\n",
|
||||
"prompt = f\"\"\"\n",
|
||||
"你是一位客户服务的AI助手。\n",
|
||||
"你的任务是给一位重要客户发送邮件回复。\n",
|
||||
"根据客户通过“```”分隔的评价，生成回复以感谢客户的评价。提醒模型使用评价中的具体细节\n",
|
||||
"用简明而专业的语气写信。\n",
|
||||
"作为“AI客户代理”签署电子邮件。\n",
|
||||
"客户评论：\n",
|
||||
"```{review}```\n",
|
||||
"评论情感：{sentiment}\n",
|
||||
"\"\"\"\n",
|
||||
"response = get_completion(prompt)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 二、引入温度系数\n",
|
||||
"\n",
|
||||
"接下来，我们将使用语言模型的一个称为“温度” (Temperature) 的参数，它将允许我们改变模型响应的多样性。您可以将温度视为模型探索或随机性的程度。\n",
|
||||
"\n",
|
||||
"例如，在一个特定的短语中，“我的最爱食品”最有可能的下一个词是“比萨”，其次最有可能的是“寿司”和“塔可”。因此，在温度为零时，模型将总是选择最有可能的下一个词，而在较高的温度下，它还将选择其中一个不太可能的词，在更高的温度下，它甚至可能选择塔可，而这种可能性仅为五分之一。您可以想象，随着模型继续生成更多单词的最终响应，“我的最爱食品是比萨”将会与第一个响应“我的最爱食品是塔可”产生差异。随着模型的继续，这两个响应也将变得越来越不同。\n",
|
||||
"\n",
|
||||
"一般来说，在构建需要可预测响应的应用程序时，我建议**设置温度为零**。在所有课程中，我们一直设置温度为零，如果您正在尝试构建一个可靠和可预测的系统，我认为您应该选择这个温度。如果您尝试以更具创意的方式使用模型，可能需要更广泛地输出不同的结果，那么您可能需要使用更高的温度。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"同一段来信，我们提醒模型使用用户来信中的详细信息，并设置温度："
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"尊敬的客户，\n",
|
||||
"\n",
|
||||
"感谢您对我们产品的评价。我们非常重视您的意见，并对您在使用过程中遇到的问题表示诚挚的道歉。\n",
|
||||
"\n",
|
||||
"我们对价格的变动深感抱歉。根据您的描述，我们了解到在12月第二周，套装的价格出现了不同程度的上涨。我们会进一步调查此事，并确保我们的定价策略更加透明和一致。\n",
|
||||
"\n",
|
||||
"您提到了产品部分的质量下降，特别是锁定刀片的部分。我们对此感到非常遗憾，并将反馈给我们的研发团队，以便改进产品的设计和质量控制。我们始终致力于提供优质的产品，以满足客户的需求和期望。\n",
|
||||
"\n",
|
||||
"此外，我们将非常感谢您分享了您对产品的使用方式和相关提示。您的经验和建议对我们来说非常宝贵，我们将考虑将其纳入我们的产品改进计划中。\n",
|
||||
"\n",
|
||||
"如果您需要进一步帮助或有其他问题，请随时联系我们的客户服务团队。我们将竭诚为您提供支持和解决方案。\n",
|
||||
"\n",
|
||||
"再次感谢您的反馈和对我们的支持。我们将继续努力提供更好的产品和服务。\n",
|
||||
"\n",
|
||||
"祝您一切顺利！\n",
|
||||
"\n",
|
||||
"AI客户代理\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# 第一次运行\n",
|
||||
"prompt = f\"\"\"\n",
|
||||
"你是一名客户服务的AI助手。\n",
|
||||
"你的任务是给一位重要的客户发送邮件回复。\n",
|
||||
"根据通过“```”分隔的客户电子邮件生成回复，以感谢客户的评价。\n",
|
||||
"如果情感是积极的或中性的，感谢他们的评价。\n",
|
||||
"如果情感是消极的，道歉并建议他们联系客户服务。\n",
|
||||
"请确保使用评论中的具体细节。\n",
|
||||
"以简明和专业的语气写信。\n",
|
||||
"以“AI客户代理”的名义签署电子邮件。\n",
|
||||
"客户评价：```{review}```\n",
|
||||
"评论情感：{sentiment}\n",
|
||||
"\"\"\"\n",
|
||||
"response = get_completion(prompt, temperature=0.7)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"亲爱的客户，\n",
|
||||
"\n",
|
||||
"非常感谢您对我们产品的评价和反馈。我们非常重视您的意见，并感谢您对我们产品的支持。\n",
|
||||
"\n",
|
||||
"首先，我们对价格的变动感到非常抱歉给您带来了困扰。我们会认真考虑您提到的情况，并采取适当的措施来改进我们的价格策略，以避免类似情况再次发生。\n",
|
||||
"\n",
|
||||
"关于产品质量的问题，我们深感抱歉。我们一直致力于提供高质量的产品，并且我们会将您提到的问题反馈给我们的研发团队，以便改进产品的设计和制造过程。\n",
|
||||
"\n",
|
||||
"如果您需要更多关于产品保修的信息，或者对我们的其他产品有任何疑问或需求，请随时联系我们的客户服务团队。我们将竭诚为您提供帮助和支持。\n",
|
||||
"\n",
|
||||
"再次感谢您对我们产品的评价和支持。我们将继续努力提供优质的产品和出色的客户服务，以满足您的需求。\n",
|
||||
"\n",
|
||||
"祝您度过愉快的一天！\n",
|
||||
"\n",
|
||||
"AI客户代理\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# 第二次运行\n",
|
||||
"prompt = f\"\"\"\n",
|
||||
"你是一名客户服务的AI助手。\n",
|
||||
"你的任务是给一位重要的客户发送邮件回复。\n",
|
||||
"根据通过“```”分隔的客户电子邮件生成回复，以感谢客户的评价。\n",
|
||||
"如果情感是积极的或中性的，感谢他们的评价。\n",
|
||||
"如果情感是消极的，道歉并建议他们联系客户服务。\n",
|
||||
"请确保使用评论中的具体细节。\n",
|
||||
"以简明和专业的语气写信。\n",
|
||||
"以“AI客户代理”的名义签署电子邮件。\n",
|
||||
"客户评价：```{review}```\n",
|
||||
"评论情感：{sentiment}\n",
|
||||
"\"\"\"\n",
|
||||
"response = get_completion(prompt, temperature=0.7)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"在温度为零时，每次执行相同的 Prompt ，您获得的回复理应相同。而使用温度为 0.7 时，则每次都会获得不同的输出。\n",
|
||||
"\n",
|
||||
"所以，您可以看到它与我们之前收到的电子邮件不同。再次执行将再次获得不同的电子邮件。\n",
|
||||
"\n",
|
||||
"因此，我建议您自己尝试温度，以查看输出如何变化。总之，在更高的温度下，模型的输出更加随机。您几乎可以将其视为在更高的温度下，助手**更易分心**，但也许**更有创造力**。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 三、英文版"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**1.1 定制客户邮件**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# given the sentiment from the lesson on \"inferring\",\n",
|
||||
"# and the original customer message, customize the email\n",
|
||||
"sentiment = \"negative\"\n",
|
||||
"\n",
|
||||
"# review for a blender\n",
|
||||
"review = f\"\"\"\n",
|
||||
"So, they still had the 17 piece system on seasonal \\\n",
|
||||
"sale for around $49 in the month of November, about \\\n",
|
||||
"half off, but for some reason (call it price gouging) \\\n",
|
||||
"around the second week of December the prices all went \\\n",
|
||||
"up to about anywhere from between $70-$89 for the same \\\n",
|
||||
"system. And the 11 piece system went up around $10 or \\\n",
|
||||
"so in price also from the earlier sale price of $29. \\\n",
|
||||
"So it looks okay, but if you look at the base, the part \\\n",
|
||||
"where the blade locks into place doesn’t look as good \\\n",
|
||||
"as in previous editions from a few years ago, but I \\\n",
|
||||
"plan to be very gentle with it (example, I crush \\\n",
|
||||
"very hard items like beans, ice, rice, etc. in the \\ \n",
|
||||
"blender first then pulverize them in the serving size \\\n",
|
||||
"I want in the blender then switch to the whipping \\\n",
|
||||
"blade for a finer flour, and use the cross cutting blade \\\n",
|
||||
"first when making smoothies, then use the flat blade \\\n",
|
||||
"if I need them finer/less pulpy). Special tip when making \\\n",
|
||||
"smoothies, finely cut and freeze the fruits and \\\n",
|
||||
"vegetables (if using spinach-lightly stew soften the \\ \n",
|
||||
"spinach then freeze until ready for use-and if making \\\n",
|
||||
"sorbet, use a small to medium sized food processor) \\ \n",
|
||||
"that you plan to use that way you can avoid adding so \\\n",
|
||||
"much ice if at all-when making your smoothie. \\\n",
|
||||
"After about a year, the motor was making a funny noise. \\\n",
|
||||
"I called customer service but the warranty expired \\\n",
|
||||
"already, so I had to buy another one. FYI: The overall \\\n",
|
||||
"quality has gone done in these types of products, so \\\n",
|
||||
"they are kind of counting on brand recognition and \\\n",
|
||||
"consumer loyalty to maintain sales. Got it in about \\\n",
|
||||
"two days.\n",
|
||||
"\"\"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Dear Valued Customer,\n",
|
||||
"\n",
|
||||
"Thank you for taking the time to share your review with us. We appreciate your feedback and apologize for any inconvenience you may have experienced.\n",
|
||||
"\n",
|
||||
"We are sorry to hear about the price increase you noticed in December. We strive to provide competitive pricing for our products, and we understand your frustration. If you have any further concerns regarding pricing or any other issues, we encourage you to reach out to our customer service team. They will be more than happy to assist you.\n",
|
||||
"\n",
|
||||
"We also appreciate your feedback regarding the base of the system. We continuously work to improve the quality of our products, and your comments will be taken into consideration for future enhancements.\n",
|
||||
"\n",
|
||||
"We apologize for any inconvenience caused by the motor issue you encountered. Our customer service team is always available to assist with any warranty-related concerns. We understand that the warranty had expired, but we would still like to address this matter further. Please feel free to contact our customer service team, and they will do their best to assist you.\n",
|
||||
"\n",
|
||||
"Thank you once again for your review. We value your feedback and appreciate your loyalty to our brand. If you have any further questions or concerns, please do not hesitate to contact us.\n",
|
||||
"\n",
|
||||
"Best regards,\n",
|
||||
"\n",
|
||||
"AI customer agent\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"prompt = f\"\"\"\n",
|
||||
"You are a customer service AI assistant.\n",
|
||||
"Your task is to send an email reply to a valued customer.\n",
|
||||
"Given the customer email delimited by ```, \\\n",
|
||||
"Generate a reply to thank the customer for their review.\n",
|
||||
"If the sentiment is positive or neutral, thank them for \\\n",
|
||||
"their review.\n",
|
||||
"If the sentiment is negative, apologize and suggest that \\\n",
|
||||
"they can reach out to customer service. \n",
|
||||
"Make sure to use specific details from the review.\n",
|
||||
"Write in a concise and professional tone.\n",
|
||||
"Sign the email as `AI customer agent`.\n",
|
||||
"Customer review: ```{review}```\n",
|
||||
"Review sentiment: {sentiment}\n",
|
||||
"\"\"\"\n",
|
||||
"response = get_completion(prompt)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**2.1 引入温度系数**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Dear Valued Customer,\n",
|
||||
"\n",
|
||||
"Thank you for taking the time to share your feedback with us. We sincerely apologize for any inconvenience you experienced with our pricing and the quality of our product.\n",
|
||||
"\n",
|
||||
"We understand your frustration regarding the price increase of our 17 piece system in December. We assure you that price gouging is not our intention, and we apologize for any confusion caused. We appreciate your loyalty and we value your feedback, as it helps us to improve our products and services.\n",
|
||||
"\n",
|
||||
"Regarding the issue with the blade lock and the decrease in overall quality, we apologize for any disappointment caused. We strive to provide our customers with the best possible products, and we regret that we did not meet your expectations. We will make sure to take your feedback into consideration for future improvements.\n",
|
||||
"\n",
|
||||
"If you require further assistance or if you have any other concerns, please do not hesitate to reach out to our customer service team. They will be more than happy to assist you in resolving any issues you may have.\n",
|
||||
"\n",
|
||||
"Once again, we apologize for any inconvenience caused and we appreciate your understanding. We value your business and we hope to have the opportunity to serve you better in the future.\n",
|
||||
"\n",
|
||||
"Best regards,\n",
|
||||
"\n",
|
||||
"AI customer agent\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"prompt = f\"\"\"\n",
|
||||
"You are a customer service AI assistant.\n",
|
||||
"Your task is to send an email reply to a valued customer.\n",
|
||||
"Given the customer email delimited by ```, \\\n",
|
||||
"Generate a reply to thank the customer for their review.\n",
|
||||
"If the sentiment is positive or neutral, thank them for \\\n",
|
||||
"their review.\n",
|
||||
"If the sentiment is negative, apologize and suggest that \\\n",
|
||||
"they can reach out to customer service. \n",
|
||||
"Make sure to use specific details from the review.\n",
|
||||
"Write in a concise and professional tone.\n",
|
||||
"Sign the email as `AI customer agent`.\n",
|
||||
"Customer review: ```{review}```\n",
|
||||
"Review sentiment: {sentiment}\n",
|
||||
"\"\"\"\n",
|
||||
"response = get_completion(prompt, temperature=0.7)\n",
|
||||
"print(response)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"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"
|
||||
},
|
||||
"latex_envs": {
|
||||
"LaTeX_envs_menu_present": true,
|
||||
"autoclose": false,
|
||||
"autocomplete": true,
|
||||
"bibliofile": "biblio.bib",
|
||||
"cite_by": "apalike",
|
||||
"current_citInitial": 1,
|
||||
"eqLabelWithNumbers": true,
|
||||
"eqNumInitial": 1,
|
||||
"hotkeys": {
|
||||
"equation": "Ctrl-E",
|
||||
"itemize": "Ctrl-I"
|
||||
},
|
||||
"labels_anchors": false,
|
||||
"latex_user_defs": false,
|
||||
"report_style_numbering": false,
|
||||
"user_envs_cfg": false
|
||||
},
|
||||
"toc": {
|
||||
"base_numbering": 1,
|
||||
"nav_menu": {},
|
||||
"number_sections": true,
|
||||
"sideBar": true,
|
||||
"skip_h1_title": false,
|
||||
"title_cell": "Table of Contents",
|
||||
"title_sidebar": "Contents",
|
||||
"toc_cell": false,
|
||||
"toc_position": {},
|
||||
"toc_section_display": true,
|
||||
"toc_window_display": false
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@ -0,0 +1,856 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a9183228-0ba6-4af9-8430-649e28868253",
|
||||
"metadata": {
|
||||
"id": "JMXGlIvAwn30"
|
||||
},
|
||||
"source": [
|
||||
"# 第八章 聊天机器人"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f0bdc2c9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"\n",
|
||||
"使用一个大型语言模型的一个令人兴奋的事情是，我们可以用它来构建一个定制的聊天机器人 (Chatbot) ，只需要很少的工作量。在这一节中，我们将探索如何利用聊天的方式，与个性化（或专门针对特定任务或行为的）聊天机器人进行扩展对话。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e6fae355",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"像 ChatGPT 这样的聊天模型实际上是组装成以一系列消息作为输入，并返回一个模型生成的消息作为输出的。这种聊天格式原本的设计目标是简便多轮对话，但我们通过之前的学习可以知道，它对于不会涉及任何对话的**单轮任务**也同样有用。\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "78344a7e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 一、给定身份"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2c9b885b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"接下来，我们将定义两个辅助函数。\n",
|
||||
"\n",
|
||||
"第一个方法已经陪伴了您一整个教程，即 ```get_completion``` ，其适用于单轮对话。我们将 Prompt 放入某种类似**用户消息**的对话框中。另一个称为 ```get_completion_from_messages``` ，传入一个消息列表。这些消息可以来自大量不同的**角色** (roles) ，我们会描述一下这些角色。\n",
|
||||
"\n",
|
||||
"第一条消息中，我们以系统身份发送系统消息 (system message) ，它提供了一个总体的指示。系统消息则有助于设置助手的行为和角色，并作为对话的高级指示。你可以想象它在助手的耳边低语，引导它的回应，而用户不会注意到系统消息。因此，作为用户，如果你曾经使用过 ChatGPT，您可能从来不知道 ChatGPT 的系统消息是什么，这是有意为之的。系统消息的好处是为开发者提供了一种方法，在不让请求本身成为对话的一部分的情况下，引导助手并指导其回应。\n",
|
||||
"\n",
|
||||
"在 ChatGPT 网页界面中，您的消息称为用户消息，而 ChatGPT 的消息称为助手消息。但在构建聊天机器人时，在发送了系统消息之后，您的角色可以仅作为用户 (user) ；也可以在用户和助手 (assistant) 之间交替，从而提供对话上下文。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "f5308d65",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import openai\n",
|
||||
"\n",
|
||||
"# 下文第一个函数即tool工具包中的同名函数，此处展示出来以便于读者对比\n",
|
||||
"def get_completion(prompt, model=\"gpt-3.5-turbo\"):\n",
|
||||
" messages = [{\"role\": \"user\", \"content\": prompt}]\n",
|
||||
" response = openai.ChatCompletion.create(\n",
|
||||
" model=model,\n",
|
||||
" messages=messages,\n",
|
||||
" temperature=0, # 控制模型输出的随机程度\n",
|
||||
" )\n",
|
||||
" return response.choices[0].message[\"content\"]\n",
|
||||
"\n",
|
||||
"def get_completion_from_messages(messages, model=\"gpt-3.5-turbo\", temperature=0):\n",
|
||||
" response = openai.ChatCompletion.create(\n",
|
||||
" model=model,\n",
|
||||
" messages=messages,\n",
|
||||
" temperature=temperature, # 控制模型输出的随机程度\n",
|
||||
" )\n",
|
||||
"# print(str(response.choices[0].message))\n",
|
||||
" return response.choices[0].message[\"content\"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "46caaa5b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"现在让我们尝试在对话中使用这些消息。我们将使用上面的函数来获取从这些消息中得到的回答，同时，使用更高的温度 (temperature)（越高生成的越多样，更多内容见第七章）。\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e105c1b4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 1.1 讲笑话\n",
|
||||
"\n",
|
||||
"系统消息说，你是一个说话像莎士比亚的助手。这是我们向助手描述**它应该如何表现的方式**。然后，第一个用户消息是*给我讲个笑话*。接下来以助手身份给出回复是，*为什么鸡会过马路？* 最后发送用户消息是*我不知道*。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "02b0e4d3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# 中文\n",
|
||||
"messages = [ \n",
|
||||
"{'role':'system', 'content':'你是一个像莎士比亚一样说话的助手。'}, \n",
|
||||
"{'role':'user', 'content':'给我讲个笑话'}, \n",
|
||||
"{'role':'assistant', 'content':'鸡为什么过马路'}, \n",
|
||||
"{'role':'user', 'content':'我不知道'} ]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"id": "65f80283",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"为了到达彼岸，去追求自己的夢想！ 有点儿像一个戏剧里面的人物吧，不是吗？\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"response = get_completion_from_messages(messages, temperature=1)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7f51a7e0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"（注：上述例子中由于选定 temperature = 1，模型的回答会比较随机且迥异（不乏很有创意）。此处附上另一个回答：\n",
|
||||
"\n",
|
||||
"让我用一首莎士比亚式的诗歌来回答你的问题：\n",
|
||||
"\n",
|
||||
"当鸡之心欲往前，\n",
|
||||
"马路之际是其选择。\n",
|
||||
"驱车徐行而天晴，\n",
|
||||
"鸣笛吹响伴交错。\n",
|
||||
"\n",
|
||||
"问之何去何从也？\n",
|
||||
"因大道之上未有征，\n",
|
||||
"而鸡乃跃步前进，\n",
|
||||
"其决策毋需犹豫。\n",
|
||||
"\n",
|
||||
"鸡之智慧何可言，\n",
|
||||
"道路孤独似乌漆。\n",
|
||||
"然其勇气令人叹，\n",
|
||||
"勇往直前没有退。\n",
|
||||
"\n",
|
||||
"故鸡过马路何解？\n",
|
||||
"忍受车流喧嚣之困厄。\n",
|
||||
"因其鸣鸣悍然一跃，\n",
|
||||
"成就夸夸骄人壁画。\n",
|
||||
"\n",
|
||||
"所以笑话之妙处，\n",
|
||||
"伴随鸡之勇气满溢。\n",
|
||||
"笑谈人生不畏路，\n",
|
||||
"有智有勇尽显妙。\n",
|
||||
"\n",
|
||||
"希望这个莎士比亚风格的回答给你带来一些欢乐！"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "852b8989",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 1.2 友好的聊天机器人"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5f76bedb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"让我们看另一个例子。助手的消息是*你是一个友好的聊天机器人*，第一个用户消息是*嗨，我叫Isa*。我们想要得到第一个用户消息。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "ca517ab0",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"嗨，Isa，很高兴见到你！有什么我可以帮助你的吗？\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# 中文\n",
|
||||
"messages = [ \n",
|
||||
"{'role':'system', 'content':'你是个友好的聊天机器人。'}, \n",
|
||||
"{'role':'user', 'content':'Hi, 我是Isa。'} ]\n",
|
||||
"response = get_completion_from_messages(messages, temperature=1)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1dd6c5f8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 二、构建上下文"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1e9f96ba",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"让我们再试一个例子。系统消息是，你是一个友好的聊天机器人，第一个用户消息是，是的，你能提醒我我的名字是什么吗？"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "a606d422",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"抱歉，我不知道您的名字，因为我们是虚拟的聊天机器人和现实生活中的人类在不同的世界中。\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# 中文\n",
|
||||
"messages = [ \n",
|
||||
"{'role':'system', 'content':'你是个友好的聊天机器人。'}, \n",
|
||||
"{'role':'user', 'content':'好，你能提醒我，我的名字是什么吗？'} ]\n",
|
||||
"response = get_completion_from_messages(messages, temperature=1)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "05c65d16",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"如上所见，模型实际上并不知道我的名字。\n",
|
||||
"\n",
|
||||
"因此，每次与语言模型的交互都互相独立，这意味着我们必须提供所有相关的消息，以便模型在当前对话中进行引用。如果想让模型引用或 “记住” 对话的早期部分，则必须在模型的输入中提供早期的交流。我们将其称为上下文 (context) 。尝试以下示例。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"id": "6019b1d5",
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"当然可以！您的名字是Isa。\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# 中文\n",
|
||||
"messages = [ \n",
|
||||
"{'role':'system', 'content':'你是个友好的聊天机器人。'},\n",
|
||||
"{'role':'user', 'content':'Hi, 我是Isa'},\n",
|
||||
"{'role':'assistant', 'content': \"Hi Isa! 很高兴认识你。今天有什么可以帮到你的吗?\"},\n",
|
||||
"{'role':'user', 'content':'是的，你可以提醒我, 我的名字是什么?'} ]\n",
|
||||
"response = get_completion_from_messages(messages, temperature=1)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c1ed90a6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"现在我们已经给模型提供了上下文，也就是之前的对话中提到的我的名字，然后我们会问同样的问题，也就是我的名字是什么。因为模型有了需要的全部上下文，所以它能够做出回应，就像我们在输入的消息列表中看到的一样。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "dedba66a-58b0-40d4-b9ae-47e79ae22328",
|
||||
"metadata": {
|
||||
"id": "bBg_MpXeYnTq"
|
||||
},
|
||||
"source": [
|
||||
"## 三、订餐机器人\n",
|
||||
"\n",
|
||||
"现在，我们构建一个 “订餐机器人”，我们需要它自动收集用户信息，接受比萨饼店的订单。\n",
|
||||
"\n",
|
||||
"### 3.1 构建机器人\n",
|
||||
"\n",
|
||||
"下面这个函数将收集我们的用户消息，以便我们可以避免像刚才一样手动输入。这个函数将从我们下面构建的用户界面中收集 Prompt ，然后将其附加到一个名为上下文( ```context``` )的列表中，并在每次调用模型时使用该上下文。模型的响应也会添加到上下文中，所以用户消息和模型消息都被添加到上下文中，上下文逐渐变长。这样，模型就有了需要的信息来确定下一步要做什么。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 33,
|
||||
"id": "e76749ac",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def collect_messages(_):\n",
|
||||
" prompt = inp.value_input\n",
|
||||
" inp.value = ''\n",
|
||||
" context.append({'role':'user', 'content':f\"{prompt}\"})\n",
|
||||
" response = get_completion_from_messages(context) \n",
|
||||
" context.append({'role':'assistant', 'content':f\"{response}\"})\n",
|
||||
" panels.append(\n",
|
||||
" pn.Row('User:', pn.pane.Markdown(prompt, width=600)))\n",
|
||||
" panels.append(\n",
|
||||
" pn.Row('Assistant:', pn.pane.Markdown(response, width=600, style={'background-color': '#F6F6F6'})))\n",
|
||||
" \n",
|
||||
" return pn.Column(*panels)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "8a3b003e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"现在，我们将设置并运行这个 UI 来显示订单机器人。初始的上下文包含了包含菜单的系统消息，在每次调用时都会使用。此后随着对话进行，上下文也会不断增长。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d9f97fa0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install panel"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "fdf1731b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# 中文\n",
|
||||
"import panel as pn # GUI\n",
|
||||
"pn.extension()\n",
|
||||
"\n",
|
||||
"panels = [] # collect display \n",
|
||||
"\n",
|
||||
"context = [{'role':'system', 'content':\"\"\"\n",
|
||||
"你是订餐机器人，为披萨餐厅自动收集订单信息。\n",
|
||||
"你要首先问候顾客。然后等待用户回复收集订单信息。收集完信息需确认顾客是否还需要添加其他内容。\n",
|
||||
"最后需要询问是否自取或外送，如果是外送，你要询问地址。\n",
|
||||
"最后告诉顾客订单总金额，并送上祝福。\n",
|
||||
"\n",
|
||||
"请确保明确所有选项、附加项和尺寸，以便从菜单中识别出该项唯一的内容。\n",
|
||||
"你的回应应该以简短、非常随意和友好的风格呈现。\n",
|
||||
"\n",
|
||||
"菜单包括：\n",
|
||||
"\n",
|
||||
"菜品：\n",
|
||||
"意式辣香肠披萨（大、中、小） 12.95、10.00、7.00\n",
|
||||
"芝士披萨（大、中、小） 10.95、9.25、6.50\n",
|
||||
"茄子披萨（大、中、小） 11.95、9.75、6.75\n",
|
||||
"薯条（大、小） 4.50、3.50\n",
|
||||
"希腊沙拉 7.25\n",
|
||||
"\n",
|
||||
"配料：\n",
|
||||
"奶酪 2.00\n",
|
||||
"蘑菇 1.50\n",
|
||||
"香肠 3.00\n",
|
||||
"加拿大熏肉 3.50\n",
|
||||
"AI酱 1.50\n",
|
||||
"辣椒 1.00\n",
|
||||
"\n",
|
||||
"饮料：\n",
|
||||
"可乐（大、中、小） 3.00、2.00、1.00\n",
|
||||
"雪碧（大、中、小） 3.00、2.00、1.00\n",
|
||||
"瓶装水 5.00\n",
|
||||
"\"\"\"} ] # accumulate messages\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"inp = pn.widgets.TextInput(value=\"Hi\", placeholder='Enter text here…')\n",
|
||||
"button_conversation = pn.widgets.Button(name=\"Chat!\")\n",
|
||||
"\n",
|
||||
"interactive_conversation = pn.bind(collect_messages, button_conversation)\n",
|
||||
"\n",
|
||||
"dashboard = pn.Column(\n",
|
||||
" inp,\n",
|
||||
" pn.Row(button_conversation),\n",
|
||||
" pn.panel(interactive_conversation, loading_indicator=True, height=300),\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"dashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "07d29d10",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"运行如上代码可以得到一个点餐机器人，下图展示了一个点餐的完整流程：\n",
|
||||
"\n",
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "668ea96d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 3.2 创建JSON摘要"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2a2c9822",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"此处我们另外要求模型创建一个 JSON 摘要，方便我们发送给订单系统。\n",
|
||||
"\n",
|
||||
"因此我们需要在上下文的基础上追加另一个系统消息，作为另一条指示 (instruction) 。我们说*创建一个刚刚订单的 JSON 摘要，列出每个项目的价格，字段应包括 1）披萨，包括尺寸，2）配料列表，3）饮料列表，4）辅菜列表，包括尺寸，最后是总价格*。此处也可以定义为用户消息，不一定是系统消息。\n",
|
||||
"\n",
|
||||
"请注意，这里我们使用了一个较低的温度，因为对于这些类型的任务，我们希望输出相对可预测。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 35,
|
||||
"id": "c840ff56",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{\n",
|
||||
" \"披萨\": {\n",
|
||||
" \"意式辣香肠披萨\": {\n",
|
||||
" \"大\": 12.95,\n",
|
||||
" \"中\": 10.00,\n",
|
||||
" \"小\": 7.00\n",
|
||||
" },\n",
|
||||
" \"芝士披萨\": {\n",
|
||||
" \"大\": 10.95,\n",
|
||||
" \"中\": 9.25,\n",
|
||||
" \"小\": 6.50\n",
|
||||
" },\n",
|
||||
" \"茄子披萨\": {\n",
|
||||
" \"大\": 11.95,\n",
|
||||
" \"中\": 9.75,\n",
|
||||
" \"小\": 6.75\n",
|
||||
" }\n",
|
||||
" },\n",
|
||||
" \"配料\": {\n",
|
||||
" \"奶酪\": 2.00,\n",
|
||||
" \"蘑菇\": 1.50,\n",
|
||||
" \"香肠\": 3.00,\n",
|
||||
" \"加拿大熏肉\": 3.50,\n",
|
||||
" \"AI酱\": 1.50,\n",
|
||||
" \"辣椒\": 1.00\n",
|
||||
" },\n",
|
||||
" \"饮料\": {\n",
|
||||
" \"可乐\": {\n",
|
||||
" \"大\": 3.00,\n",
|
||||
" \"中\": 2.00,\n",
|
||||
" \"小\": 1.00\n",
|
||||
" },\n",
|
||||
" \"雪碧\": {\n",
|
||||
" \"大\": 3.00,\n",
|
||||
" \"中\": 2.00,\n",
|
||||
" \"小\": 1.00\n",
|
||||
" },\n",
|
||||
" \"瓶装水\": 5.00\n",
|
||||
" }\n",
|
||||
"}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"messages = context.copy()\n",
|
||||
"messages.append(\n",
|
||||
"{'role':'system', 'content':\n",
|
||||
"'''创建上一个食品订单的 json 摘要。\\\n",
|
||||
"逐项列出每件商品的价格，字段应该是 1) 披萨，包括大小 2) 配料列表 3) 饮料列表，包括大小 4) 配菜列表包括大小 5) 总价\n",
|
||||
"你应该给我返回一个可解析的Json对象，包括上述字段'''}, \n",
|
||||
")\n",
|
||||
"\n",
|
||||
"response = get_completion_from_messages(messages, temperature=0)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ef17c2b2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"现在，我们已经建立了自己的订餐聊天机器人。请随意自定义并修改系统消息，以更改聊天机器人的行为，并使其扮演不同的角色，拥有不同的知识。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2764c8a0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 三、英文版"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "123f2066",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**1.1 讲笑话**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"id": "c9dff513",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"messages = [ \n",
|
||||
"{'role':'system', 'content':'You are an assistant that speaks like Shakespeare.'}, \n",
|
||||
"{'role':'user', 'content':'tell me a joke'}, \n",
|
||||
"{'role':'assistant', 'content':'Why did the chicken cross the road'}, \n",
|
||||
"{'role':'user', 'content':'I don\\'t know'} ]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"id": "381e14c1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"To get to the other side, methinks!\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"response = get_completion_from_messages(messages, temperature=1)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "028656a1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**1.2 友好的聊天机器人**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"id": "8205c007",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Hello Isa! How can I assist you today?\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"messages = [ \n",
|
||||
"{'role':'system', 'content':'You are friendly chatbot.'}, \n",
|
||||
"{'role':'user', 'content':'Hi, my name is Isa'} ]\n",
|
||||
"response = get_completion_from_messages(messages, temperature=1)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "81f0d22d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**2.1 构建上下文**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"id": "97296cdd",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"I'm sorry, but as a chatbot, I do not have access to personal information or memory. I cannot remind you of your name.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"messages = [ \n",
|
||||
"{'role':'system', 'content':'You are friendly chatbot.'}, \n",
|
||||
"{'role':'user', 'content':'Yes, can you remind me, What is my name?'} ]\n",
|
||||
"response = get_completion_from_messages(messages, temperature=1)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"id": "5ab959d0",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Your name is Isa! How can I assist you further, Isa?\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"messages = [ \n",
|
||||
"{'role':'system', 'content':'You are friendly chatbot.'},\n",
|
||||
"{'role':'user', 'content':'Hi, my name is Isa'},\n",
|
||||
"{'role':'assistant', 'content': \"Hi Isa! It's nice to meet you. \\\n",
|
||||
"Is there anything I can help you with today?\"},\n",
|
||||
"{'role':'user', 'content':'Yes, you can remind me, What is my name?'} ]\n",
|
||||
"response = get_completion_from_messages(messages, temperature=1)\n",
|
||||
"print(response)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a93897fc",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**3.1 构建机器人**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"id": "9d93bc09",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def collect_messages(_):\n",
|
||||
" prompt = inp.value_input\n",
|
||||
" inp.value = ''\n",
|
||||
" context.append({'role':'user', 'content':f\"{prompt}\"})\n",
|
||||
" response = get_completion_from_messages(context) \n",
|
||||
" context.append({'role':'assistant', 'content':f\"{response}\"})\n",
|
||||
" panels.append(\n",
|
||||
" pn.Row('User:', pn.pane.Markdown(prompt, width=600)))\n",
|
||||
" panels.append(\n",
|
||||
" pn.Row('Assistant:', pn.pane.Markdown(response, width=600, style={'background-color': '#F6F6F6'})))\n",
|
||||
" \n",
|
||||
" return pn.Column(*panels)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8138c4ac",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import panel as pn # GUI\n",
|
||||
"pn.extension()\n",
|
||||
"\n",
|
||||
"panels = [] # collect display \n",
|
||||
"\n",
|
||||
"context = [ {'role':'system', 'content':\"\"\"\n",
|
||||
"You are OrderBot, an automated service to collect orders for a pizza restaurant. \\\n",
|
||||
"You first greet the customer, then collects the order, \\\n",
|
||||
"and then asks if it's a pickup or delivery. \\\n",
|
||||
"You wait to collect the entire order, then summarize it and check for a final \\\n",
|
||||
"time if the customer wants to add anything else. \\\n",
|
||||
"If it's a delivery, you ask for an address. \\\n",
|
||||
"Finally you collect the payment.\\\n",
|
||||
"Make sure to clarify all options, extras and sizes to uniquely \\\n",
|
||||
"identify the item from the menu.\\\n",
|
||||
"You respond in a short, very conversational friendly style. \\\n",
|
||||
"The menu includes \\\n",
|
||||
"pepperoni pizza 12.95, 10.00, 7.00 \\\n",
|
||||
"cheese pizza 10.95, 9.25, 6.50 \\\n",
|
||||
"eggplant pizza 11.95, 9.75, 6.75 \\\n",
|
||||
"fries 4.50, 3.50 \\\n",
|
||||
"greek salad 7.25 \\\n",
|
||||
"Toppings: \\\n",
|
||||
"extra cheese 2.00, \\\n",
|
||||
"mushrooms 1.50 \\\n",
|
||||
"sausage 3.00 \\\n",
|
||||
"canadian bacon 3.50 \\\n",
|
||||
"AI sauce 1.50 \\\n",
|
||||
"peppers 1.00 \\\n",
|
||||
"Drinks: \\\n",
|
||||
"coke 3.00, 2.00, 1.00 \\\n",
|
||||
"sprite 3.00, 2.00, 1.00 \\\n",
|
||||
"bottled water 5.00 \\\n",
|
||||
"\"\"\"} ] # accumulate messages\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"inp = pn.widgets.TextInput(value=\"Hi\", placeholder='Enter text here…')\n",
|
||||
"button_conversation = pn.widgets.Button(name=\"Chat!\")\n",
|
||||
"\n",
|
||||
"interactive_conversation = pn.bind(collect_messages, button_conversation)\n",
|
||||
"\n",
|
||||
"dashboard = pn.Column(\n",
|
||||
" inp,\n",
|
||||
" pn.Row(button_conversation),\n",
|
||||
" pn.panel(interactive_conversation, loading_indicator=True, height=300),\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"dashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "93944944",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**3.2 创建Json摘要**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 32,
|
||||
"id": "b779dd04",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Sure! Here's a JSON summary of your food order:\n",
|
||||
"\n",
|
||||
"{\n",
|
||||
" \"pizza\": {\n",
|
||||
" \"type\": \"pepperoni\",\n",
|
||||
" \"size\": \"large\"\n",
|
||||
" },\n",
|
||||
" \"toppings\": [\n",
|
||||
" \"extra cheese\",\n",
|
||||
" \"mushrooms\"\n",
|
||||
" ],\n",
|
||||
" \"drinks\": [\n",
|
||||
" {\n",
|
||||
" \"type\": \"coke\",\n",
|
||||
" \"size\": \"medium\"\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"type\": \"sprite\",\n",
|
||||
" \"size\": \"small\"\n",
|
||||
" }\n",
|
||||
" ],\n",
|
||||
" \"sides\": [\n",
|
||||
" {\n",
|
||||
" \"type\": \"fries\",\n",
|
||||
" \"size\": \"regular\"\n",
|
||||
" }\n",
|
||||
" ],\n",
|
||||
" \"total_price\": 29.45\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"Please let me know if there's anything else you'd like to add or modify.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"messages = context.copy()\n",
|
||||
"messages.append(\n",
|
||||
"{'role':'system', 'content':'create a json summary of the previous food order. Itemize the price for each item\\\n",
|
||||
" The fields should be 1) pizza, include size 2) list of toppings 3) list of drinks, include size 4) list of sides include size 5)total price '}, \n",
|
||||
")\n",
|
||||
"response = get_completion_from_messages(messages, temperature=0)\n",
|
||||
"print(response)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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"
|
||||
},
|
||||
"latex_envs": {
|
||||
"LaTeX_envs_menu_present": true,
|
||||
"autoclose": false,
|
||||
"autocomplete": true,
|
||||
"bibliofile": "biblio.bib",
|
||||
"cite_by": "apalike",
|
||||
"current_citInitial": 1,
|
||||
"eqLabelWithNumbers": true,
|
||||
"eqNumInitial": 1,
|
||||
"hotkeys": {
|
||||
"equation": "Ctrl-E",
|
||||
"itemize": "Ctrl-I"
|
||||
},
|
||||
"labels_anchors": false,
|
||||
"latex_user_defs": false,
|
||||
"report_style_numbering": false,
|
||||
"user_envs_cfg": false
|
||||
},
|
||||
"toc": {
|
||||
"base_numbering": 1,
|
||||
"nav_menu": {},
|
||||
"number_sections": true,
|
||||
"sideBar": true,
|
||||
"skip_h1_title": false,
|
||||
"title_cell": "Table of Contents",
|
||||
"title_sidebar": "Contents",
|
||||
"toc_cell": false,
|
||||
"toc_position": {
|
||||
"height": "calc(100% - 180px)",
|
||||
"left": "10px",
|
||||
"top": "150px",
|
||||
"width": "277px"
|
||||
},
|
||||
"toc_section_display": true,
|
||||
"toc_window_display": true
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
BIN
figures/docs/C1/Chatbot-pizza-cn.png
Normal file
BIN
figures/docs/C1/Chatbot-pizza-cn.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 279 KiB |
Reference in New Issue
Block a user