{ "cells": [ { "attachments": {}, "cell_type": "markdown", "id": "52824b89-532a-4e54-87e9-1410813cd39e", "metadata": {}, "source": [ "# 第五章 如何评估基于LLM的应用程序\n", "当使用llm构建复杂应用程序时，评估应用程序的表现是一个重要但有时棘手的步骤，它是否满足某些准确性标准？\n", "通常更有用的是从许多不同的数据点中获得更全面的模型表现情况\n", "一种是使用语言模型本身和链本身来评估其他语言模型、其他链和其他应用程序" ] }, { "cell_type": "code", "execution_count": 2, "id": "b7ed03ed-1322-49e3-b2a2-33e94fb592ef", "metadata": { "height": 81, "tags": [] }, "outputs": [], "source": [ "import os\n", "\n", "from dotenv import load_dotenv, find_dotenv\n", "_ = load_dotenv(find_dotenv()) #读取环境变量" ] }, { "attachments": {}, "cell_type": "markdown", "id": "28008949", "metadata": {}, "source": [ "## 创建LLM应用\n", "按照langchain链的方式进行构建" ] }, { "cell_type": "code", "execution_count": 3, "id": "974acf8e-8f88-42de-88f8-40a82cb58e8b", "metadata": { "height": 98 }, "outputs": [], "source": [ "from langchain.chains import RetrievalQA #检索QA链，在文档上进行检索\n", "from langchain.chat_models import ChatOpenAI #openai模型\n", "from langchain.document_loaders import CSVLoader #文档加载器，采用csv格式存储\n", "from langchain.indexes import VectorstoreIndexCreator #导入向量存储索引创建器\n", "from langchain.vectorstores import DocArrayInMemorySearch #向量存储\n" ] }, { "cell_type": "code", "execution_count": 13, "id": "9ec1106d", "metadata": { "height": 64 }, "outputs": [], "source": [ "#加载数据\n", "file = 'OutdoorClothingCatalog_1000.csv'\n", "loader = CSVLoader(file_path=file)\n", "data = loader.load()" ] }, { "cell_type": "code", "execution_count": 6, "id": "06b1ffae", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
012
0NaNnamedescription
10.0Women's Campside OxfordsThis ultracomfortable lace-to-toe Oxford boast...
21.0Recycled Waterhog Dog Mat, Chevron WeaveProtect your floors from spills and splashing ...
32.0Infant and Toddler Girls' Coastal Chill Swimsu...She'll love the bright colors, ruffles and exc...
43.0Refresh Swimwear, V-Neck Tankini ContrastsWhether you're going for a swim or heading out...
............
996995.0Men's Classic Denim, Standard FitCrafted from premium denim that will last wash...
997996.0CozyPrint Sweater Fleece PulloverThe ultimate sweater fleece - made from superi...
998997.0Women's NRS Endurance Spray Paddling PantsThese comfortable and affordable splash paddli...
999998.0Women's Stop Flies HoodieThis great-looking hoodie uses No Fly Zone Tec...
1000999.0Modern Utility BagThis US-made crossbody bag is built with the s...
\n", "

1001 rows × 3 columns

\n", "
" ], "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": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#查看数据\n", "import pandas as pd\n", "test_data = pd.read_csv(file,header=None)\n", "test_data" ] }, { "cell_type": "code", "execution_count": 10, "id": "b31c218f", "metadata": { "height": 64 }, "outputs": [], "source": [ "'''\n", "将指定向量存储类,创建完成后，我们将从加载器中调用,通过文档记载器列表加载\n", "'''\n", "index = VectorstoreIndexCreator(\n", " vectorstore_cls=DocArrayInMemorySearch\n", ").from_loaders([loader])" ] }, { "cell_type": "code", "execution_count": 11, "id": "a2006054", "metadata": { "height": 183 }, "outputs": [], "source": [ "#通过指定语言模型、链类型、检索器和我们要打印的详细程度来创建检索QA链\n", "llm = ChatOpenAI(temperature = 0.0)\n", "qa = RetrievalQA.from_chain_type(\n", " llm=llm, \n", " chain_type=\"stuff\", \n", " retriever=index.vectorstore.as_retriever(), \n", " verbose=True,\n", " chain_type_kwargs = {\n", " \"document_separator\": \"<<<<>>>>>\"\n", " }\n", ")" ] }, { "attachments": {}, "cell_type": "markdown", "id": "791ebd73", "metadata": {}, "source": [ "### 创建评估数据点\n", "们需要做的第一件事是真正弄清楚我们想要评估它的一些数据点，我们将介绍几种不同的方法来完成这个任务\n", "1、将自己想出好的数据点作为例子，查看一些数据，然后想出例子问题和答案，以便以后用于评估" ] }, { "cell_type": "code", "execution_count": 14, "id": "fb04a0f9", "metadata": { "height": 30 }, "outputs": [ { "data": { "text/plain": [ "Document(page_content=\": 10\\nname: Cozy Comfort Pullover Set, Stripe\\ndescription: Perfect for lounging, this striped knit set lives up to its name. We used ultrasoft fabric and an easy design that's as comfortable at bedtime as it is when we have to make a quick run out.\\n\\nSize & Fit\\n- Pants are Favorite Fit: Sits lower on the waist.\\n- Relaxed Fit: Our most generous fit sits farthest from the body.\\n\\nFabric & Care\\n- In the softest blend of 63% polyester, 35% rayon and 2% spandex.\\n\\nAdditional Features\\n- Relaxed fit top with raglan sleeves and rounded hem.\\n- Pull-on pants have a wide elastic waistband and drawstring, side pockets and a modern slim leg.\\n\\nImported.\", metadata={'source': 'OutdoorClothingCatalog_1000.csv', 'row': 10})" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data[10]#查看这里的一些文档，我们可以对其中发生的事情有所了解" ] }, { "cell_type": "code", "execution_count": 15, "id": "fe4a88c2", "metadata": { "height": 30 }, "outputs": [ { "data": { "text/plain": [ "Document(page_content=': 11\\nname: Ultra-Lofty 850 Stretch Down Hooded Jacket\\ndescription: This technical stretch down jacket from our DownTek collection is sure to keep you warm and comfortable with its full-stretch construction providing exceptional range of motion. With a slightly fitted style that falls at the hip and best with a midweight layer, this jacket is suitable for light activity up to 20° and moderate activity up to -30°. The soft and durable 100% polyester shell offers complete windproof protection and is insulated with warm, lofty goose down. Other features include welded baffles for a no-stitch construction and excellent stretch, an adjustable hood, an interior media port and mesh stash pocket and a hem drawcord. Machine wash and dry. Imported.', metadata={'source': 'OutdoorClothingCatalog_1000.csv', 'row': 11})" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data[11]" ] }, { "attachments": {}, "cell_type": "markdown", "id": "b9c52116", "metadata": {}, "source": [ "看起来第一个文档中有这个套头衫，第二个文档中有这个夹克，从这些细节中，我们可以创建一些例子查询和答案" ] }, { "attachments": {}, "cell_type": "markdown", "id": "8d548aef", "metadata": {}, "source": [ "### 创建测试用例数据\n" ] }, { "cell_type": "code", "execution_count": 17, "id": "c2d59bf2", "metadata": { "height": 217 }, "outputs": [], "source": [ "examples = [\n", " {\n", " \"query\": \"Do the Cozy Comfort Pullover Set\\\n", " have side pockets?\",\n", " \"answer\": \"Yes\"\n", " },\n", " {\n", " \"query\": \"What collection is the Ultra-Lofty \\\n", " 850 Stretch Down Hooded Jacket from?\",\n", " \"answer\": \"The DownTek collection\"\n", " }\n", "]" ] }, { "attachments": {}, "cell_type": "markdown", "id": "b73ce510", "metadata": {}, "source": [ "因此，我们可以问一个简单的问题，这个舒适的套头衫套装有侧口袋吗？，我们可以通过上面的内容看到，它确实有一些侧口袋，答案为是\n", "对于第二个文档，我们可以看到这件夹克来自某个系列，即down tech系列，答案是down tech系列。" ] }, { "attachments": {}, "cell_type": "markdown", "id": "c7ce3e4f", "metadata": {}, "source": [ "### 通过LLM生成测试用例" ] }, { "cell_type": "code", "execution_count": 18, "id": "d44f8376", "metadata": { "height": 47 }, "outputs": [], "source": [ "from langchain.evaluation.qa import QAGenerateChain #导入QA生成链，它将接收文档，并从每个文档中创建一个问题答案对\n" ] }, { "cell_type": "code", "execution_count": 19, "id": "34e87816", "metadata": { "height": 30 }, "outputs": [], "source": [ "example_gen_chain = QAGenerateChain.from_llm(ChatOpenAI())#通过传递chat open AI语言模型来创建这个链" ] }, { "cell_type": "code", "execution_count": null, "id": "62abae09", "metadata": { "height": 64 }, "outputs": [], "source": [ "new_examples = example_gen_chain.apply_and_parse(\n", " [{\"doc\": t} for t in data[:5]]\n", ") #我们可以创建许多例子" ] }, { "cell_type": "code", "execution_count": 21, "id": "31c9f786", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[{'query': \"What is the weight of the Women's Campside Oxfords?\",\n", " 'answer': \"The Women's Campside Oxfords weigh approximately 1 lb.1 oz. per pair.\"},\n", " {'query': 'What are the dimensions of the medium Recycled Waterhog dog mat?',\n", " 'answer': 'The dimensions of the medium Recycled Waterhog dog mat are 22.5\" x 34.5\".'},\n", " {'query': \"What are some features of the Infant and Toddler Girls' Coastal Chill Swimsuit?\",\n", " 'answer': \"The swimsuit has bright colors, ruffles, and exclusive whimsical prints. It is made of four-way-stretch and chlorine-resistant fabric that keeps its shape and resists snags. The swimsuit is also UPF 50+ rated, providing the highest rated sun protection possible, blocking 98% of the sun's harmful rays. The crossover no-slip straps and fully lined bottom ensure a secure fit and maximum coverage. It is machine washable and should be line dried for best results. The swimsuit is imported.\"},\n", " {'query': 'What is the fabric composition of the Refresh Swimwear, V-Neck Tankini Contrasts?',\n", " 'answer': 'The Refresh Swimwear, V-Neck Tankini Contrasts is made of 82% recycled nylon with 18% Lycra® spandex for the body and 90% recycled nylon with 10% Lycra® spandex for the lining.'},\n", " {'query': 'What is the name of the waterproof pants and what technology makes them more breathable?',\n", " 'answer': 'The name of the pants is EcoFlex 3L Storm Pants and the TEK O2 technology makes them more breathable.'}]" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "new_examples #查看用例数据" ] }, { "cell_type": "code", "execution_count": 22, "id": "97ab28b5", "metadata": { "height": 30 }, "outputs": [ { "data": { "text/plain": [ "{'query': \"What is the weight of the Women's Campside Oxfords?\",\n", " 'answer': \"The Women's Campside Oxfords weigh approximately 1 lb.1 oz. per pair.\"}" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "new_examples[0]" ] }, { "cell_type": "code", "execution_count": 23, "id": "0ebe4228", "metadata": { "height": 30 }, "outputs": [ { "data": { "text/plain": [ "Document(page_content=\": 0\\nname: Women's Campside Oxfords\\ndescription: This ultracomfortable lace-to-toe Oxford boasts a super-soft canvas, thick cushioning, and quality construction for a broken-in feel from the first time you put them on. \\n\\nSize & Fit: Order regular shoe size. For half sizes not offered, order up to next whole size. \\n\\nSpecs: Approx. weight: 1 lb.1 oz. per pair. \\n\\nConstruction: Soft canvas material for a broken-in feel and look. Comfortable EVA innersole with Cleansport NXT® antimicrobial odor control. Vintage hunt, fish and camping motif on innersole. Moderate arch contour of innersole. EVA foam midsole for cushioning and support. Chain-tread-inspired molded rubber outsole with modified chain-tread pattern. Imported. \\n\\nQuestions? Please contact us for any inquiries.\", metadata={'source': 'OutdoorClothingCatalog_1000.csv', 'row': 0})" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data[0]" ] }, { "attachments": {}, "cell_type": "markdown", "id": "faf25f2f", "metadata": {}, "source": [ "### 组合用例数据" ] }, { "cell_type": "code", "execution_count": 24, "id": "ada2a3fc", "metadata": { "height": 30 }, "outputs": [], "source": [ "examples += new_examples" ] }, { "cell_type": "code", "execution_count": 25, "id": "9cdf5cf5", "metadata": { "height": 30 }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "\n", "\u001b[1m> Entering new RetrievalQA chain...\u001b[0m\n", "\n", "\u001b[1m> Finished chain.\u001b[0m\n" ] }, { "data": { "text/plain": [ "'The Cozy Comfort Pullover Set, Stripe has side pockets.'" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "qa.run(examples[0][\"query\"])" ] }, { "attachments": {}, "cell_type": "markdown", "id": "63f3cb08", "metadata": {}, "source": [ "## 人工评估\n", "现在有了这些示例，但是我们如何评估正在发生的事情呢？\n", "通过运行一个示例通过链，并查看它产生的输出\n", "在这里我们传递一个查询，然后我们得到一个答案。实际上正在发生的事情，进入语言模型的实际提示是什么？ \n", "它检索的文档是什么？ \n", "中间结果是什么？ \n", "仅仅查看最终答案通常不足以了解链中出现了什么问题或可能出现了什么问题" ] }, { "cell_type": "code", "execution_count": 26, "id": "fcaf622e", "metadata": { "height": 47 }, "outputs": [], "source": [ "''' \n", "LingChainDebug工具可以了解运行一个实例通过链中间所经历的步骤\n", "'''\n", "import langchain\n", "langchain.debug = True" ] }, { "cell_type": "code", "execution_count": 27, "id": "1e1deab0", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[32;1m\u001b[1;3m[chain/start]\u001b[0m \u001b[1m[1:chain:RetrievalQA] Entering Chain run with input:\n", "\u001b[0m{\n", " \"query\": \"Do the Cozy Comfort Pullover Set have side pockets?\"\n", "}\n", "\u001b[32;1m\u001b[1;3m[chain/start]\u001b[0m \u001b[1m[1:chain:RetrievalQA > 2:chain:StuffDocumentsChain] Entering Chain run with input:\n", "\u001b[0m[inputs]\n", "\u001b[32;1m\u001b[1;3m[chain/start]\u001b[0m \u001b[1m[1:chain:RetrievalQA > 2:chain:StuffDocumentsChain > 3:chain:LLMChain] Entering Chain run with input:\n", "\u001b[0m{\n", " \"question\": \"Do the Cozy Comfort Pullover Set have side pockets?\",\n", " \"context\": \": 10\\nname: Cozy Comfort Pullover Set, Stripe\\ndescription: Perfect for lounging, this striped knit set lives up to its name. We used ultrasoft fabric and an easy design that's as comfortable at bedtime as it is when we have to make a quick run out.\\n\\nSize & Fit\\n- Pants are Favorite Fit: Sits lower on the waist.\\n- Relaxed Fit: Our most generous fit sits farthest from the body.\\n\\nFabric & Care\\n- In the softest blend of 63% polyester, 35% rayon and 2% spandex.\\n\\nAdditional Features\\n- Relaxed fit top with raglan sleeves and rounded hem.\\n- Pull-on pants have a wide elastic waistband and drawstring, side pockets and a modern slim leg.\\n\\nImported.<<<<>>>>>: 73\\nname: Cozy Cuddles Knit Pullover Set\\ndescription: Perfect for lounging, this knit set lives up to its name. We used ultrasoft fabric and an easy design that's as comfortable at bedtime as it is when we have to make a quick run out. \\n\\nSize & Fit \\nPants are Favorite Fit: Sits lower on the waist. \\nRelaxed Fit: Our most generous fit sits farthest from the body. \\n\\nFabric & Care \\nIn the softest blend of 63% polyester, 35% rayon and 2% spandex.\\n\\nAdditional Features \\nRelaxed fit top with raglan sleeves and rounded hem. \\nPull-on pants have a wide elastic waistband and drawstring, side pockets and a modern slim leg. \\nImported.<<<<>>>>>: 632\\nname: Cozy Comfort Fleece Pullover\\ndescription: The ultimate sweater fleece \\u2013 made from superior fabric and offered at an unbeatable price. \\n\\nSize & Fit\\nSlightly Fitted: Softly shapes the body. Falls at hip. \\n\\nWhy We Love It\\nOur customers (and employees) love the rugged construction and heritage-inspired styling of our popular Sweater Fleece Pullover and wear it for absolutely everything. From high-intensity activities to everyday tasks, you'll find yourself reaching for it every time.\\n\\nFabric & Care\\nRugged sweater-knit exterior and soft brushed interior for exceptional warmth and comfort. Made from soft, 100% polyester. Machine wash and dry.\\n\\nAdditional Features\\nFeatures our classic Mount Katahdin logo. Snap placket. Front princess seams create a feminine shape. Kangaroo handwarmer pockets. Cuffs and hem reinforced with jersey binding. Imported.\\n\\n \\u2013 Official Supplier to the U.S. Ski Team\\nTHEIR WILL TO WIN, WOVEN RIGHT IN. LEARN MORE<<<<>>>>>: 151\\nname: Cozy Quilted Sweatshirt\\ndescription: Our sweatshirt is an instant classic with its great quilted texture and versatile weight that easily transitions between seasons. With a traditional fit that is relaxed through the chest, sleeve, and waist, this pullover is lightweight enough to be worn most months of the year. The cotton blend fabric is super soft and comfortable, making it the perfect casual layer. To make dressing easy, this sweatshirt also features a snap placket and a heritage-inspired Mt. Katahdin logo patch. For care, machine wash and dry. Imported.\"\n", "}\n", "\u001b[32;1m\u001b[1;3m[llm/start]\u001b[0m \u001b[1m[1:chain:RetrievalQA > 2:chain:StuffDocumentsChain > 3:chain:LLMChain > 4:llm:ChatOpenAI] Entering LLM run with input:\n", "\u001b[0m{\n", " \"prompts\": [\n", " \"System: Use the following pieces of context to answer the users question. \\nIf you don't know the answer, just say that you don't know, don't try to make up an answer.\\n----------------\\n: 10\\nname: Cozy Comfort Pullover Set, Stripe\\ndescription: Perfect for lounging, this striped knit set lives up to its name. We used ultrasoft fabric and an easy design that's as comfortable at bedtime as it is when we have to make a quick run out.\\n\\nSize & Fit\\n- Pants are Favorite Fit: Sits lower on the waist.\\n- Relaxed Fit: Our most generous fit sits farthest from the body.\\n\\nFabric & Care\\n- In the softest blend of 63% polyester, 35% rayon and 2% spandex.\\n\\nAdditional Features\\n- Relaxed fit top with raglan sleeves and rounded hem.\\n- Pull-on pants have a wide elastic waistband and drawstring, side pockets and a modern slim leg.\\n\\nImported.<<<<>>>>>: 73\\nname: Cozy Cuddles Knit Pullover Set\\ndescription: Perfect for lounging, this knit set lives up to its name. We used ultrasoft fabric and an easy design that's as comfortable at bedtime as it is when we have to make a quick run out. \\n\\nSize & Fit \\nPants are Favorite Fit: Sits lower on the waist. \\nRelaxed Fit: Our most generous fit sits farthest from the body. \\n\\nFabric & Care \\nIn the softest blend of 63% polyester, 35% rayon and 2% spandex.\\n\\nAdditional Features \\nRelaxed fit top with raglan sleeves and rounded hem. \\nPull-on pants have a wide elastic waistband and drawstring, side pockets and a modern slim leg. \\nImported.<<<<>>>>>: 632\\nname: Cozy Comfort Fleece Pullover\\ndescription: The ultimate sweater fleece \\u2013 made from superior fabric and offered at an unbeatable price. \\n\\nSize & Fit\\nSlightly Fitted: Softly shapes the body. Falls at hip. \\n\\nWhy We Love It\\nOur customers (and employees) love the rugged construction and heritage-inspired styling of our popular Sweater Fleece Pullover and wear it for absolutely everything. From high-intensity activities to everyday tasks, you'll find yourself reaching for it every time.\\n\\nFabric & Care\\nRugged sweater-knit exterior and soft brushed interior for exceptional warmth and comfort. Made from soft, 100% polyester. Machine wash and dry.\\n\\nAdditional Features\\nFeatures our classic Mount Katahdin logo. Snap placket. Front princess seams create a feminine shape. Kangaroo handwarmer pockets. Cuffs and hem reinforced with jersey binding. Imported.\\n\\n \\u2013 Official Supplier to the U.S. Ski Team\\nTHEIR WILL TO WIN, WOVEN RIGHT IN. LEARN MORE<<<<>>>>>: 151\\nname: Cozy Quilted Sweatshirt\\ndescription: Our sweatshirt is an instant classic with its great quilted texture and versatile weight that easily transitions between seasons. With a traditional fit that is relaxed through the chest, sleeve, and waist, this pullover is lightweight enough to be worn most months of the year. The cotton blend fabric is super soft and comfortable, making it the perfect casual layer. To make dressing easy, this sweatshirt also features a snap placket and a heritage-inspired Mt. Katahdin logo patch. For care, machine wash and dry. Imported.\\nHuman: Do the Cozy Comfort Pullover Set have side pockets?\"\n", " ]\n", "}\n", "\u001b[36;1m\u001b[1;3m[llm/end]\u001b[0m \u001b[1m[1:chain:RetrievalQA > 2:chain:StuffDocumentsChain > 3:chain:LLMChain > 4:llm:ChatOpenAI] [1.68s] Exiting LLM run with output:\n", "\u001b[0m{\n", " \"generations\": [\n", " [\n", " {\n", " \"text\": \"The Cozy Comfort Pullover Set, Stripe has side pockets on the pull-on pants.\",\n", " \"generation_info\": null,\n", " \"message\": {\n", " \"content\": \"The Cozy Comfort Pullover Set, Stripe has side pockets on the pull-on pants.\",\n", " \"additional_kwargs\": {},\n", " \"example\": false\n", " }\n", " }\n", " ]\n", " ],\n", " \"llm_output\": {\n", " \"token_usage\": {\n", " \"prompt_tokens\": 734,\n", " \"completion_tokens\": 18,\n", " \"total_tokens\": 752\n", " },\n", " \"model_name\": \"gpt-3.5-turbo\"\n", " }\n", "}\n", "\u001b[36;1m\u001b[1;3m[chain/end]\u001b[0m \u001b[1m[1:chain:RetrievalQA > 2:chain:StuffDocumentsChain > 3:chain:LLMChain] [1.68s] Exiting Chain run with output:\n", "\u001b[0m{\n", " \"text\": \"The Cozy Comfort Pullover Set, Stripe has side pockets on the pull-on pants.\"\n", "}\n", "\u001b[36;1m\u001b[1;3m[chain/end]\u001b[0m \u001b[1m[1:chain:RetrievalQA > 2:chain:StuffDocumentsChain] [1.71s] Exiting Chain run with output:\n", "\u001b[0m{\n", " \"output_text\": \"The Cozy Comfort Pullover Set, Stripe has side pockets on the pull-on pants.\"\n", "}\n", "\u001b[36;1m\u001b[1;3m[chain/end]\u001b[0m \u001b[1m[1:chain:RetrievalQA] [2.86s] Exiting Chain run with output:\n", "\u001b[0m{\n", " \"result\": \"The Cozy Comfort Pullover Set, Stripe has side pockets on the pull-on pants.\"\n", "}\n" ] }, { "data": { "text/plain": [ "'The Cozy Comfort Pullover Set, Stripe has side pockets on the pull-on pants.'" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "qa.run(examples[0][\"query\"])#重新运行与上面相同的示例，可以看到它开始打印出更多的信息" ] }, { "attachments": {}, "cell_type": "markdown", "id": "8dee0f24", "metadata": {}, "source": [ "我们可以看到它首先深入到检索QA链中，然后它进入了一些文档链。如上所述，我们正在使用stuff方法，现在我们正在传递这个上下文，可以看到，这个上下文是由我们检索到的不同文档创建的。因此，在进行问答时，当返回错误结果时，通常不是语言模型本身出错了，实际上是检索步骤出错了，仔细查看问题的确切内容和上下文可以帮助调试出错的原因。 \n", "然后，我们可以再向下一级，看看进入语言模型的确切内容，以及 OpenAI 自身，在这里，我们可以看到传递的完整提示，我们有一个系统消息，有所使用的提示的描述，这是问题回答链使用的提示，我们可以看到提示打印出来，使用以下上下文片段回答用户的问题。\n", "如果您不知道答案，只需说您不知道即可，不要试图编造答案。然后我们看到一堆之前插入的上下文，我们还可以看到有关实际返回类型的更多信息。我们不仅仅返回一个答案，还有token的使用情况，可以了解到token数的使用情况\n", "\n", "\n", "由于这是一个相对简单的链，我们现在可以看到最终的响应，舒适的毛衣套装，条纹款，有侧袋，正在起泡，通过链返回给用户，我们刚刚讲解了如何查看和调试单个输入到该链的情况。\n", "\n", "\n" ] }, { "attachments": {}, "cell_type": "markdown", "id": "7b37c7bc", "metadata": {}, "source": [ "##### 如何评估新创建的实例\n", "与创建它们类似，可以运行链条来处理所有示例，然后查看输出并尝试弄清楚，发生了什么，它是否正确" ] }, { "cell_type": "code", "execution_count": 28, "id": "b3d6bef0", "metadata": { "height": 47 }, "outputs": [], "source": [ "# 我们需要为所有示例创建预测，关闭调试模式，以便不将所有内容打印到屏幕上\n", "langchain.debug = False" ] }, { "attachments": {}, "cell_type": "markdown", "id": "d5bdbdce", "metadata": {}, "source": [ "## 通过LLM进行评估实例" ] }, { "cell_type": "code", "execution_count": 32, "id": "a4dca05a", "metadata": { "height": 30 }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "\n", "\u001b[1m> Entering new RetrievalQA chain...\u001b[0m\n", "\n", "\u001b[1m> Finished chain.\u001b[0m\n", "\n", "\n", "\u001b[1m> Entering new RetrievalQA chain...\u001b[0m\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 1.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "\u001b[1m> Finished chain.\u001b[0m\n", "\n", "\n", "\u001b[1m> Entering new RetrievalQA chain...\u001b[0m\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 1.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n", "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 2.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n", "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n", "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 8.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n", "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 16.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "\u001b[1m> Finished chain.\u001b[0m\n", "\n", "\n", "\u001b[1m> Entering new RetrievalQA chain...\u001b[0m\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 1.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "\u001b[1m> Finished chain.\u001b[0m\n", "\n", "\n", "\u001b[1m> Entering new RetrievalQA chain...\u001b[0m\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 1.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n", "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 2.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n", "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n", "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 8.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n", "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 16.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "\u001b[1m> Finished chain.\u001b[0m\n", "\n", "\n", "\u001b[1m> Entering new RetrievalQA chain...\u001b[0m\n", "\n", "\u001b[1m> Finished chain.\u001b[0m\n", "\n", "\n", "\u001b[1m> Entering new RetrievalQA chain...\u001b[0m\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 1.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n", "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 2.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n", "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n", "Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 8.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-Nul9WsPYdsnjttqS3f0hDSWd 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..\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "\u001b[1m> Finished chain.\u001b[0m\n" ] } ], "source": [ "predictions = qa.apply(examples) #为所有不同的示例创建预测" ] }, { "cell_type": "code", "execution_count": 35, "id": "6012a3e0", "metadata": { "height": 30 }, "outputs": [], "source": [ "''' \n", "对预测的结果进行评估，导入QA问题回答，评估链，通过语言模型创建此链\n", "'''\n", "from langchain.evaluation.qa import QAEvalChain #导入QA问题回答，评估链" ] }, { "cell_type": "code", "execution_count": 36, "id": "724b1c0b", "metadata": { "height": 47 }, "outputs": [], "source": [ "#通过调用chatGPT进行评估\n", "llm = ChatOpenAI(temperature=0)\n", "eval_chain = QAEvalChain.from_llm(llm)" ] }, { "cell_type": "code", "execution_count": null, "id": "8b46ae55", "metadata": { "height": 30 }, "outputs": [], "source": [ "graded_outputs = eval_chain.evaluate(examples, predictions)#在此链上调用evaluate，进行评估" ] }, { "attachments": {}, "cell_type": "markdown", "id": "9ad64f72", "metadata": {}, "source": [ "##### 评估思路\n", "当它面前有整个文档时，它可以生成一个真实的答案，我们将打印出预测的答，当它进行QA链时，使用embedding和向量数据库进行检索时，将其传递到语言模型中，然后尝试猜测预测的答案，我们还将打印出成绩，这也是语言模型生成的。当它要求评估链评估正在发生的事情时，以及它是否正确或不正确。因此，当我们循环遍历所有这些示例并将它们打印出来时，可以详细了解每个示例" ] }, { "cell_type": "code", "execution_count": 24, "id": "3437cfbe", "metadata": { "height": 132 }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Example 0:\n", "Question: Do the Cozy Comfort Pullover Set have side pockets?\n", "Real Answer: Yes\n", "Predicted Answer: The Cozy Comfort Pullover Set, Stripe does have side pockets.\n", "Predicted Grade: CORRECT\n", "\n", "Example 1:\n", "Question: What collection is the Ultra-Lofty 850 Stretch Down Hooded Jacket from?\n", "Real Answer: The DownTek collection\n", "Predicted Answer: The Ultra-Lofty 850 Stretch Down Hooded Jacket is from the DownTek collection.\n", "Predicted Grade: CORRECT\n", "\n", "Example 2:\n", "Question: What is the weight of each pair of Women's Campside Oxfords?\n", "Real Answer: The approximate weight of each pair of Women's Campside Oxfords is 1 lb. 1 oz.\n", "Predicted Answer: The weight of each pair of Women's Campside Oxfords is approximately 1 lb. 1 oz.\n", "Predicted Grade: CORRECT\n", "\n", "Example 3:\n", "Question: What are the dimensions of the small and medium Recycled Waterhog Dog Mat?\n", "Real Answer: The dimensions of the small Recycled Waterhog Dog Mat are 18\" x 28\" and the dimensions of the medium Recycled Waterhog Dog Mat are 22.5\" x 34.5\".\n", "Predicted Answer: The small Recycled Waterhog Dog Mat has dimensions of 18\" x 28\" and the medium size has dimensions of 22.5\" x 34.5\".\n", "Predicted Grade: CORRECT\n", "\n", "Example 4:\n", "Question: What are some features of the Infant and Toddler Girls' Coastal Chill Swimsuit?\n", "Real Answer: The swimsuit features bright colors, ruffles, and exclusive whimsical prints. It is made of four-way-stretch and chlorine-resistant fabric, ensuring that it keeps its shape and resists snags. The swimsuit is also UPF 50+ rated, providing the highest rated sun protection possible by blocking 98% of the sun's harmful rays. The crossover no-slip straps and fully lined bottom ensure a secure fit and maximum coverage. Finally, it can be machine washed and line dried for best results.\n", "Predicted Answer: The Infant and Toddler Girls' Coastal Chill Swimsuit is a two-piece swimsuit with bright colors, ruffles, and exclusive whimsical prints. It is made of four-way-stretch and chlorine-resistant fabric that keeps its shape and resists snags. The swimsuit has UPF 50+ rated fabric that provides the highest rated sun protection possible, blocking 98% of the sun's harmful rays. The crossover no-slip straps and fully lined bottom ensure a secure fit and maximum coverage. It is machine washable and should be line dried for best results.\n", "Predicted Grade: CORRECT\n", "\n", "Example 5:\n", "Question: What is the fabric composition of the Refresh Swimwear V-Neck Tankini Contrasts?\n", "Real Answer: The body of the Refresh Swimwear V-Neck Tankini Contrasts is made of 82% recycled nylon and 18% Lycra® spandex, while the lining is made of 90% recycled nylon and 10% Lycra® spandex.\n", "Predicted Answer: The Refresh Swimwear V-Neck Tankini Contrasts is made of 82% recycled nylon with 18% Lycra® spandex for the body and 90% recycled nylon with 10% Lycra® spandex for the lining.\n", "Predicted Grade: CORRECT\n", "\n", "Example 6:\n", "Question: What is the fabric composition of the EcoFlex 3L Storm Pants?\n", "Real Answer: The EcoFlex 3L Storm Pants are made of 100% nylon, exclusive of trim.\n", "Predicted Answer: The fabric composition of the EcoFlex 3L Storm Pants is 100% nylon, exclusive of trim.\n", "Predicted Grade: CORRECT\n", "\n" ] } ], "source": [ "#我们将传入示例和预测，得到一堆分级输出，循环遍历它们打印答案\n", "for i, eg in enumerate(examples):\n", " print(f\"Example {i}:\")\n", " print(\"Question: \" + predictions[i]['query'])\n", " print(\"Real Answer: \" + predictions[i]['answer'])\n", " print(\"Predicted Answer: \" + predictions[i]['result'])\n", " print(\"Predicted Grade: \" + graded_outputs[i]['text'])\n", " print()" ] }, { "attachments": {}, "cell_type": "markdown", "id": "87ecb476", "metadata": {}, "source": [ "#### 结果分析\n", "对于每个示例，它看起来都是正确的，让我们看看第一个例子。\n", "这里的问题是，舒适的套头衫套装，有侧口袋吗？真正的答案，我们创建了这个，是肯定的。模型预测的答案是舒适的套头衫套装条纹，确实有侧口袋。因此，我们可以理解这是一个正确的答案。它将其评为正确。 \n", "#### 使用模型评估的优势\n", "\n", "你有这些答案，它们是任意的字符串。没有单一的真实字符串是最好的可能答案，有许多不同的变体，只要它们具有相同的语义，它们应该被评为相似。如果使用正则进行精准匹配就会丢失语义信息，到目前为止存在的许多评估指标都不够好。目前最有趣和最受欢迎的之一就是使用语言模型进行评估。" ] } ], "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 }