更新代码

This commit is contained in:
wisdom-pan
2023-06-03 15:43:58 +08:00
parent e51ecc1b03
commit 818a4661f8
2 changed files with 0 additions and 804 deletions

View File

@ -1,424 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "51e47840",
"metadata": {},
"source": [
"# 第四章 基于LangChain的文档问答\n",
"本章内容主要利用langchain构建向量数据库可以在文档上方或关于文档回答问题因此给定从PDF文件、网页或某些公司的内部文档收集中提取的文本使用llm回答有关这些文档内容的问题"
]
},
{
"cell_type": "markdown",
"id": "ef807f79",
"metadata": {},
"source": [
"## 一、环境配置\n",
"\n",
"安装langchain设置chatGPT的OPENAI_API_KEY\n",
"* 安装langchain\n",
"```\n",
"pip install --upgrade langchain\n",
"```\n",
"* 安装docarray\n",
"```\n",
"pip install docarray\n",
"```\n",
"* 设置API-KEY环境变量\n",
"```\n",
"export OPENAI_API_KEY='api-key'\n",
"\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "af3ffa97",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"from dotenv import load_dotenv, find_dotenv\n",
"_ = load_dotenv(find_dotenv()) # 读取系统中的环境变量"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "49081091",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"False"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"load_dotenv(find_dotenv())\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "3bcb095f",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"os.environ[\"OPENAI_API_KEY\"] = \"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\"\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "46595e8c",
"metadata": {},
"outputs": [],
"source": [
"#导入检索QA链在文档上进行检索\n",
"from langchain.chains import RetrievalQA\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.document_loaders import CSVLoader\n",
"from langchain.vectorstores import DocArrayInMemorySearch\n",
"from IPython.display import display, Markdown"
]
},
{
"cell_type": "markdown",
"id": "e511efa5",
"metadata": {},
"source": [
"## 使用 LangChain 完成一次问答"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "3ab4b9d1",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'\\n\\n人工智能是一种重要的现代科技它可以大大改善人类生活减轻人类负担提升工作效率。它可以帮助人们提高生产力更有效地管理组织并且可以提供更为准确的数据帮助人们更好地决策。另外人工智能可以帮助科学家发现新的药物改善医疗服务以及发展新的环保技术。总之人工智能是一项重要的科技具有广泛的应用前景。'"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.llms import OpenAI\n",
"\n",
"llm = OpenAI(model_name=\"text-davinci-003\",max_tokens=1024)\n",
"llm(\"怎么评价人工智能\")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "884399f1",
"metadata": {},
"outputs": [],
"source": [
"file = 'OutdoorClothingCatalog_1000.csv'\n",
"loader = CSVLoader(file_path=file)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "52ec965a",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0</th>\n",
" <th>1</th>\n",
" <th>2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>NaN</td>\n",
" <td>name</td>\n",
" <td>description</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.0</td>\n",
" <td>Women's Campside Oxfords</td>\n",
" <td>This ultracomfortable lace-to-toe Oxford boast...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.0</td>\n",
" <td>Recycled Waterhog Dog Mat, Chevron Weave</td>\n",
" <td>Protect your floors from spills and splashing ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2.0</td>\n",
" <td>Infant and Toddler Girls' Coastal Chill Swimsu...</td>\n",
" <td>She'll love the bright colors, ruffles and exc...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>3.0</td>\n",
" <td>Refresh Swimwear, V-Neck Tankini Contrasts</td>\n",
" <td>Whether you're going for a swim or heading out...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>996</th>\n",
" <td>995.0</td>\n",
" <td>Men's Classic Denim, Standard Fit</td>\n",
" <td>Crafted from premium denim that will last wash...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>997</th>\n",
" <td>996.0</td>\n",
" <td>CozyPrint Sweater Fleece Pullover</td>\n",
" <td>The ultimate sweater fleece - made from superi...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>998</th>\n",
" <td>997.0</td>\n",
" <td>Women's NRS Endurance Spray Paddling Pants</td>\n",
" <td>These comfortable and affordable splash paddli...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999</th>\n",
" <td>998.0</td>\n",
" <td>Women's Stop Flies Hoodie</td>\n",
" <td>This great-looking hoodie uses No Fly Zone Tec...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1000</th>\n",
" <td>999.0</td>\n",
" <td>Modern Utility Bag</td>\n",
" <td>This US-made crossbody bag is built with the s...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1001 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
" 0 1 \\\n",
"0 NaN name \n",
"1 0.0 Women's Campside Oxfords \n",
"2 1.0 Recycled Waterhog Dog Mat, Chevron Weave \n",
"3 2.0 Infant and Toddler Girls' Coastal Chill Swimsu... \n",
"4 3.0 Refresh Swimwear, V-Neck Tankini Contrasts \n",
"... ... ... \n",
"996 995.0 Men's Classic Denim, Standard Fit \n",
"997 996.0 CozyPrint Sweater Fleece Pullover \n",
"998 997.0 Women's NRS Endurance Spray Paddling Pants \n",
"999 998.0 Women's Stop Flies Hoodie \n",
"1000 999.0 Modern Utility Bag \n",
"\n",
" 2 \n",
"0 description \n",
"1 This ultracomfortable lace-to-toe Oxford boast... \n",
"2 Protect your floors from spills and splashing ... \n",
"3 She'll love the bright colors, ruffles and exc... \n",
"4 Whether you're going for a swim or heading out... \n",
"... ... \n",
"996 Crafted from premium denim that will last wash... \n",
"997 The ultimate sweater fleece - made from superi... \n",
"998 These comfortable and affordable splash paddli... \n",
"999 This great-looking hoodie uses No Fly Zone Tec... \n",
"1000 This US-made crossbody bag is built with the s... \n",
"\n",
"[1001 rows x 3 columns]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"file = 'OutdoorClothingCatalog_1000.csv'\n",
"\n",
"data = pd.read_csv(file,header=None)\n",
"data"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "efc6c592",
"metadata": {},
"outputs": [],
"source": [
"from langchain.indexes import VectorstoreIndexCreator"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "5e90139b",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mCanceled future for execute_request message before replies were done"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31m在当前单元格或上一个单元格中执行代码时 Kernel 崩溃。请查看单元格中的代码,以确定故障的可能原因。有关详细信息,请单击 <a href='https://aka.ms/vscodeJupyterKernelCrash'>此处</a>。有关更多详细信息,请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"index = VectorstoreIndexCreator(\n",
" vectorstore_cls=DocArrayInMemorySearch\n",
").from_loaders([loader])"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "8249a523",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mCanceled future for execute_request message before replies were done"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31m在当前单元格或上一个单元格中执行代码时 Kernel 崩溃。请查看单元格中的代码,以确定故障的可能原因。有关详细信息,请单击 <a href='https://aka.ms/vscodeJupyterKernelCrash'>此处</a>。有关更多详细信息,请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
]
}
],
"source": [
"from docarray import DocumentArray\n",
"\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "3b160609",
"metadata": {},
"outputs": [],
"source": [
"query =\"Please list all your shirts with sun protection \\\n",
"in a table in markdown and summarize each one.\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "cf61d864",
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'index' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[2], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mindex\u001b[49m\u001b[38;5;241m.\u001b[39mquery(query)\n",
"\u001b[0;31mNameError\u001b[0m: name 'index' is not defined"
]
}
],
"source": [
"response = index.query(query)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0737f809",
"metadata": {},
"outputs": [],
"source": [
"display(Markdown(response))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "chatGPT",
"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": "3.9.16"
},
"vscode": {
"interpreter": {
"hash": "4d8dc73ac51fd938ce7dec941fbf542c26232b3529b0c2a6ebc607bfa3d5aa69"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -1,380 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "e1ce673f",
"metadata": {},
"source": [
"# Summarize"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "abbc4934",
"metadata": {},
"outputs": [],
"source": [
"import openai\n",
"import os\n",
"\n",
"from dotenv import load_dotenv, find_dotenv\n",
"_ = load_dotenv(find_dotenv()) # read local .env file\n",
"\n",
"openai.api_key = os.getenv('OPENAI_API_KEY')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "19f13be6",
"metadata": {},
"outputs": [],
"source": [
"def get_completion(prompt, model=\"gpt-3.5-turbo\"): # Andrew mentioned that the prompt/ completion paradigm is preferable for this class\n",
" messages = [{\"role\": \"user\", \"content\": prompt}]\n",
" response = openai.ChatCompletion.create(\n",
" model=model,\n",
" messages=messages,\n",
" temperature=0, # this is the degree of randomness of the model's output\n",
" )\n",
" return response.choices[0].message[\"content\"]"
]
},
{
"cell_type": "markdown",
"id": "a9a77385",
"metadata": {},
"source": [
"## 对文本做总结"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "37f412b5",
"metadata": {},
"outputs": [],
"source": [
"prod_review = \"\"\"\n",
"Got this panda plush toy for my daughter's birthday, \\\n",
"who loves it and takes it everywhere. It's soft and \\ \n",
"super cute, and its face has a friendly look. It's \\ \n",
"a bit small for what I paid though. I think there \\ \n",
"might be other options that are bigger for the \\ \n",
"same price. It arrived a day earlier than expected, \\ \n",
"so I got to play with it myself before I gave it \\ \n",
"to her.\n",
"\"\"\""
]
},
{
"cell_type": "markdown",
"id": "13d70836",
"metadata": {},
"source": [
"## 以单词/句子/字符限制进行总结"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "10c0c7e8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Soft and cute panda plush toy loved by daughter, but a bit small for the price. Arrived early.\n"
]
}
],
"source": [
"prompt = f\"\"\"\n",
"Your task is to generate a short summary of a product \\\n",
"review from an ecommerce site. \n",
"\n",
"Summarize the review below, delimited by triple \n",
"backticks, in at most 30 words. \n",
"\n",
"Review: ```{prod_review}```\n",
"\"\"\"\n",
"\n",
"response = get_completion(prompt)\n",
"print(response)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "64da0bc6",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The panda plush toy arrived a day earlier than expected, but the customer felt it was a bit small for the price paid.\n"
]
}
],
"source": [
"prompt = f\"\"\"\n",
"Your task is to generate a short summary of a product \\\n",
"review from an ecommerce site to give feedback to the \\\n",
"Shipping deparmtment. \n",
"\n",
"Summarize the review below, delimited by triple \n",
"backticks, in at most 30 words, and focusing on any aspects \\\n",
"that mention shipping and delivery of the product. \n",
"\n",
"Review: ```{prod_review}```\n",
"\"\"\"\n",
"\n",
"response = get_completion(prompt)\n",
"print(response)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "4e9f7803",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The panda plush toy is soft, cute, and loved by the recipient, but the price may be too high for its size.\n"
]
}
],
"source": [
"prompt = f\"\"\"\n",
"Your task is to generate a short summary of a product \\\n",
"review from an ecommerce site to give feedback to the \\\n",
"pricing deparmtment, responsible for determining the \\\n",
"price of the product. \n",
"\n",
"Summarize the review below, delimited by triple \n",
"backticks, in at most 30 words, and focusing on any aspects \\\n",
"that are relevant to the price and perceived value. \n",
"\n",
"Review: ```{prod_review}```\n",
"\"\"\"\n",
"\n",
"response = get_completion(prompt)\n",
"print(response)"
]
},
{
"cell_type": "markdown",
"id": "b6ed513e",
"metadata": {},
"source": [
"## 使用提取代替总结"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "a2035734",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The product arrived a day earlier than expected.\n"
]
}
],
"source": [
"prompt = f\"\"\"\n",
"Your task is to extract relevant information from \\ \n",
"a product review from an ecommerce site to give \\\n",
"feedback to the Shipping department. \n",
"\n",
"From the review below, delimited by triple quotes \\\n",
"extract the information relevant to shipping and \\ \n",
"delivery. Limit to 30 words. \n",
"\n",
"Review: ```{prod_review}```\n",
"\"\"\"\n",
"\n",
"response = get_completion(prompt)\n",
"print(response)"
]
},
{
"cell_type": "markdown",
"id": "32e0345b",
"metadata": {},
"source": [
"## 对多个文本做总结"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "f2d9dd87",
"metadata": {},
"outputs": [],
"source": [
"review_1 = prod_review \n",
"\n",
"# review for a standing lamp\n",
"review_2 = \"\"\"\n",
"Needed a nice lamp for my bedroom, and this one \\\n",
"had additional storage and not too high of a price \\\n",
"point. Got it fast - arrived in 2 days. The string \\\n",
"to the lamp broke during the transit and the company \\\n",
"happily sent over a new one. Came within a few days \\\n",
"as well. It was easy to put together. Then I had a \\\n",
"missing part, so I contacted their support and they \\\n",
"very quickly got me the missing piece! Seems to me \\\n",
"to be a great company that cares about their customers \\\n",
"and products. \n",
"\"\"\"\n",
"\n",
"# review for an electric toothbrush\n",
"review_3 = \"\"\"\n",
"My dental hygienist recommended an electric toothbrush, \\\n",
"which is why I got this. The battery life seems to be \\\n",
"pretty impressive so far. After initial charging and \\\n",
"leaving the charger plugged in for the first week to \\\n",
"condition the battery, I've unplugged the charger and \\\n",
"been using it for twice daily brushing for the last \\\n",
"3 weeks all on the same charge. But the toothbrush head \\\n",
"is too small. Ive seen baby toothbrushes bigger than \\\n",
"this one. I wish the head was bigger with different \\\n",
"length bristles to get between teeth better because \\\n",
"this one doesnt. Overall if you can get this one \\\n",
"around the $50 mark, it's a good deal. The manufactuer's \\\n",
"replacements heads are pretty expensive, but you can \\\n",
"get generic ones that're more reasonably priced. This \\\n",
"toothbrush makes me feel like I've been to the dentist \\\n",
"every day. My teeth feel sparkly clean! \n",
"\"\"\"\n",
"\n",
"# review for a blender\n",
"review_4 = \"\"\"\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 doesnt 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",
"\"\"\"\n",
"\n",
"reviews = [review_1, review_2, review_3, review_4]"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "43d84e1f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0 Soft and cute panda plush toy loved by daughter, but a bit small for the price. Arrived early. \n",
"\n",
"1 Affordable lamp with storage, fast shipping, and excellent customer service. Easy to assemble and missing parts were quickly replaced. \n",
"\n",
"2 Good battery life, small toothbrush head, but effective cleaning. Good deal if bought around $50. \n",
"\n"
]
},
{
"ename": "RateLimitError",
"evalue": "Rate limit reached for default-gpt-3.5-turbo in organization org-SoADSeM578ReGFBjktovCGZG on requests per min. Limit: 3 / min. Please try again in 20s. Contact us through our help center at help.openai.com if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method.",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mRateLimitError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[12], line 12\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(\u001b[38;5;28mlen\u001b[39m(reviews)):\n\u001b[1;32m 2\u001b[0m prompt \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\"\"\u001b[39m\n\u001b[1;32m 3\u001b[0m \u001b[38;5;124m Your task is to generate a short summary of a product \u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124m \u001b[39m\n\u001b[1;32m 4\u001b[0m \u001b[38;5;124m review from an ecommerce site. \u001b[39m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[38;5;124m Review: ```\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mreviews[i]\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m```\u001b[39m\n\u001b[1;32m 10\u001b[0m \u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\"\"\u001b[39m\n\u001b[0;32m---> 12\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mget_completion\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprompt\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 13\u001b[0m \u001b[38;5;28mprint\u001b[39m(i, response, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
"Cell \u001b[0;32mIn[4], line 3\u001b[0m, in \u001b[0;36mget_completion\u001b[0;34m(prompt, model)\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mget_completion\u001b[39m(prompt, model\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mgpt-3.5-turbo\u001b[39m\u001b[38;5;124m\"\u001b[39m): \u001b[38;5;66;03m# Andrew mentioned that the prompt/ completion paradigm is preferable for this class\u001b[39;00m\n\u001b[1;32m 2\u001b[0m messages \u001b[38;5;241m=\u001b[39m [{\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrole\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124muser\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontent\u001b[39m\u001b[38;5;124m\"\u001b[39m: prompt}]\n\u001b[0;32m----> 3\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mopenai\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mChatCompletion\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 4\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5\u001b[0m \u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6\u001b[0m \u001b[43m \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# this is the degree of randomness of the model's output\u001b[39;49;00m\n\u001b[1;32m 7\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 8\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m response\u001b[38;5;241m.\u001b[39mchoices[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mmessage[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontent\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n",
"File \u001b[0;32m~/opt/anaconda3/envs/chatGPT/lib/python3.9/site-packages/openai/api_resources/chat_completion.py:25\u001b[0m, in \u001b[0;36mChatCompletion.create\u001b[0;34m(cls, *args, **kwargs)\u001b[0m\n\u001b[1;32m 23\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[1;32m 24\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 25\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 26\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m TryAgain \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 27\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m timeout \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m time\u001b[38;5;241m.\u001b[39mtime() \u001b[38;5;241m>\u001b[39m start \u001b[38;5;241m+\u001b[39m timeout:\n",
"File \u001b[0;32m~/opt/anaconda3/envs/chatGPT/lib/python3.9/site-packages/openai/api_resources/abstract/engine_api_resource.py:153\u001b[0m, in \u001b[0;36mEngineAPIResource.create\u001b[0;34m(cls, api_key, api_base, api_type, request_id, api_version, organization, **params)\u001b[0m\n\u001b[1;32m 127\u001b[0m \u001b[38;5;129m@classmethod\u001b[39m\n\u001b[1;32m 128\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcreate\u001b[39m(\n\u001b[1;32m 129\u001b[0m \u001b[38;5;28mcls\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 136\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mparams,\n\u001b[1;32m 137\u001b[0m ):\n\u001b[1;32m 138\u001b[0m (\n\u001b[1;32m 139\u001b[0m deployment_id,\n\u001b[1;32m 140\u001b[0m engine,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 150\u001b[0m api_key, api_base, api_type, api_version, organization, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mparams\n\u001b[1;32m 151\u001b[0m )\n\u001b[0;32m--> 153\u001b[0m response, _, api_key \u001b[38;5;241m=\u001b[39m \u001b[43mrequestor\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 154\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mpost\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 155\u001b[0m \u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 156\u001b[0m \u001b[43m \u001b[49m\u001b[43mparams\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 157\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 158\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 159\u001b[0m \u001b[43m \u001b[49m\u001b[43mrequest_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrequest_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 160\u001b[0m \u001b[43m \u001b[49m\u001b[43mrequest_timeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrequest_timeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 161\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 163\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m stream:\n\u001b[1;32m 164\u001b[0m \u001b[38;5;66;03m# must be an iterator\u001b[39;00m\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(response, OpenAIResponse)\n",
"File \u001b[0;32m~/opt/anaconda3/envs/chatGPT/lib/python3.9/site-packages/openai/api_requestor.py:226\u001b[0m, in \u001b[0;36mAPIRequestor.request\u001b[0;34m(self, method, url, params, headers, files, stream, request_id, request_timeout)\u001b[0m\n\u001b[1;32m 205\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mrequest\u001b[39m(\n\u001b[1;32m 206\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 207\u001b[0m method,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 214\u001b[0m request_timeout: Optional[Union[\u001b[38;5;28mfloat\u001b[39m, Tuple[\u001b[38;5;28mfloat\u001b[39m, \u001b[38;5;28mfloat\u001b[39m]]] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 215\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[Union[OpenAIResponse, Iterator[OpenAIResponse]], \u001b[38;5;28mbool\u001b[39m, \u001b[38;5;28mstr\u001b[39m]:\n\u001b[1;32m 216\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrequest_raw(\n\u001b[1;32m 217\u001b[0m method\u001b[38;5;241m.\u001b[39mlower(),\n\u001b[1;32m 218\u001b[0m url,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 224\u001b[0m request_timeout\u001b[38;5;241m=\u001b[39mrequest_timeout,\n\u001b[1;32m 225\u001b[0m )\n\u001b[0;32m--> 226\u001b[0m resp, got_stream \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_interpret_response\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresult\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 227\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m resp, got_stream, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapi_key\n",
"File \u001b[0;32m~/opt/anaconda3/envs/chatGPT/lib/python3.9/site-packages/openai/api_requestor.py:620\u001b[0m, in \u001b[0;36mAPIRequestor._interpret_response\u001b[0;34m(self, result, stream)\u001b[0m\n\u001b[1;32m 612\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m (\n\u001b[1;32m 613\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_interpret_response_line(\n\u001b[1;32m 614\u001b[0m line, result\u001b[38;5;241m.\u001b[39mstatus_code, result\u001b[38;5;241m.\u001b[39mheaders, stream\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 615\u001b[0m )\n\u001b[1;32m 616\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m line \u001b[38;5;129;01min\u001b[39;00m parse_stream(result\u001b[38;5;241m.\u001b[39miter_lines())\n\u001b[1;32m 617\u001b[0m ), \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 618\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 619\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m (\n\u001b[0;32m--> 620\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_interpret_response_line\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 621\u001b[0m \u001b[43m \u001b[49m\u001b[43mresult\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcontent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mutf-8\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 622\u001b[0m \u001b[43m \u001b[49m\u001b[43mresult\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstatus_code\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 623\u001b[0m \u001b[43m \u001b[49m\u001b[43mresult\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 624\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 625\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m 626\u001b[0m \u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m 627\u001b[0m )\n",
"File \u001b[0;32m~/opt/anaconda3/envs/chatGPT/lib/python3.9/site-packages/openai/api_requestor.py:683\u001b[0m, in \u001b[0;36mAPIRequestor._interpret_response_line\u001b[0;34m(self, rbody, rcode, rheaders, stream)\u001b[0m\n\u001b[1;32m 681\u001b[0m stream_error \u001b[38;5;241m=\u001b[39m stream \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124merror\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m resp\u001b[38;5;241m.\u001b[39mdata\n\u001b[1;32m 682\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m stream_error \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;241m200\u001b[39m \u001b[38;5;241m<\u001b[39m\u001b[38;5;241m=\u001b[39m rcode \u001b[38;5;241m<\u001b[39m \u001b[38;5;241m300\u001b[39m:\n\u001b[0;32m--> 683\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_error_response(\n\u001b[1;32m 684\u001b[0m rbody, rcode, resp\u001b[38;5;241m.\u001b[39mdata, rheaders, stream_error\u001b[38;5;241m=\u001b[39mstream_error\n\u001b[1;32m 685\u001b[0m )\n\u001b[1;32m 686\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m resp\n",
"\u001b[0;31mRateLimitError\u001b[0m: Rate limit reached for default-gpt-3.5-turbo in organization org-SoADSeM578ReGFBjktovCGZG on requests per min. Limit: 3 / min. Please try again in 20s. Contact us through our help center at help.openai.com if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method."
]
}
],
"source": [
"for i in range(len(reviews)):\n",
" prompt = f\"\"\"\n",
" Your task is to generate a short summary of a product \\ \n",
" review from an ecommerce site. \n",
"\n",
" Summarize the review below, delimited by triple \\\n",
" backticks in at most 20 words. \n",
"\n",
" Review: ```{reviews[i]}```\n",
" \"\"\"\n",
"\n",
" response = get_completion(prompt)\n",
" print(i, response, \"\\n\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a7aa40f3",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 5
}