【LangChain】概要(Summarization)

LangChain学习文档


概要

summarization chain可用于汇总多个文档。一种方法是输入多个较小的文档,将它们分为块后,并使用 MapReduceDocumentsChain 对它们进行操作。还可以选择将进行汇总的链改为 StuffDocumentsChainRefineDocumentsChain

准备数据

首先我们准备数据。在此示例中,我们从一个长文档创建多个文档,但可以以任何方式获取这些文档(本笔记本的重点是突出显示获取文档后要执行的操作)。

python 复制代码
from langchain import OpenAI, PromptTemplate, LLMChain
from langchain.text_splitter import CharacterTextSplitter
from langchain.chains.mapreduce import MapReduceChain
from langchain.prompts import PromptTemplate
# 大模型
llm = OpenAI(temperature=0)
# 初始化拆分器
text_splitter = CharacterTextSplitter()
# 加载长文本
with open("../../state_of_the_union.txt") as f:
    state_of_the_union = f.read()
texts = text_splitter.split_text(state_of_the_union)

from langchain.docstore.document import Document
# 将拆分后的文本转成文档
docs = [Document(page_content=t) for t in texts[:3]]

快速开始

如果您只是想尽快开始,建议采用以下方法:

python 复制代码
from langchain.chains.summarize import load_summarize_chain
# 注意这里是load_summarize_chain
chain = load_summarize_chain(llm, chain_type="map_reduce")
chain.run(docs)

结果:

python 复制代码
'问界M5是赛力斯与华为合力打造的高端品牌AITO的首款车,问界M5共推出两款车型,后驱标准版预售价格25万元,四驱性能版28万元。'

如果您想更好地控制和了解正在发生的事情,请参阅以下信息。

stuff Chain

本节展示使用 stuff Chain 进行汇总的结果。

python 复制代码
chain = load_summarize_chain(llm, chain_type="stuff")
chain.run(docs)

结果:

python 复制代码
    ' 问界M5是赛力斯与华为合力打造的高端品牌AITO的首款车,问界M5共推出两款车型,后驱标准版预售价格25万元,四驱性能版28万元。'

自定义提示(Custom Prompts

您还可以在该链上使用您自己的提示。在此示例中,我们将用意大利语回复。

python 复制代码
prompt_template = """Write a concise summary of the following:

{text}

CONCISE SUMMARY IN ITALIAN:"""
# 上面的prompt是要用意大利语做摘要
PROMPT = PromptTemplate(template=prompt_template, input_variables=["text"])
# summarize_chain
chain = load_summarize_chain(llm, chain_type="stuff", prompt=PROMPT)
chain.run(docs)

结果:就不打印了。

map_reduce Chain

本节展示使用map_reduce Chain进行汇总的结果。

python 复制代码
chain = load_summarize_chain(llm, chain_type="map_reduce")
chain.run(docs)
python 复制代码
    ' 问界M5是赛力斯与华为合力打造的高端品牌AITO的首款车,问界M5共推出两款车型,后驱标准版预售价格25万元,四驱性能版28万元。'

中间步骤

如果我们想检查它们,我们还可以返回 map_reduce 链的中间步骤。这是通过 return_map_steps 变量完成的。

python 复制代码
chain = load_summarize_chain(OpenAI(temperature=0), chain_type="map_reduce", return_intermediate_steps=True)

chain({"input_documents": docs}, return_only_outputs=True)

结果:

python 复制代码
    {'map_steps': [" In response to Russia's aggression in Ukraine, the United States has united with other freedom-loving nations to impose economic sanctions and hold Putin accountable. The U.S. Department of Justice is also assembling a task force to go after the crimes of Russian oligarchs and seize their ill-gotten gains.",
      ' The United States and its European allies are taking action to punish Russia for its invasion of Ukraine, including seizing assets, closing off airspace, and providing economic and military assistance to Ukraine. The US is also mobilizing forces to protect NATO countries and has released 30 million barrels of oil from its Strategic Petroleum Reserve to help blunt gas prices. The world is uniting in support of Ukraine and democracy, and the US stands with its Ukrainian-American citizens.',
      " President Biden and Vice President Harris ran for office with a new economic vision for America, and have since passed the American Rescue Plan and the Bipartisan Infrastructure Law to help struggling families and rebuild America's infrastructure. This includes creating jobs, modernizing roads, airports, ports, and waterways, replacing lead pipes, providing affordable high-speed internet, and investing in American products to support American jobs."],
     'output_text': " In response to Russia's aggression in Ukraine, the United States and its allies have imposed economic sanctions and are taking other measures to hold Putin accountable. The US is also providing economic and military assistance to Ukraine, protecting NATO countries, and passing legislation to help struggling families and rebuild America's infrastructure. The world is uniting in support of Ukraine and democracy, and the US stands with its Ukrainian-American citizens."}

自定义提示

您还可以在该链上使用您自己的prompt。在此示例中,我们将用意大利语回复。

python 复制代码
# 该prompt说:要用意大利语做摘要
prompt_template = """Write a concise summary of the following:

{text}

CONCISE SUMMARY IN ITALIAN:"""
# 创建prompt的模板
PROMPT = PromptTemplate(template=prompt_template, input_variables=["text"])
chain = load_summarize_chain(OpenAI(temperature=0), chain_type="map_reduce", return_intermediate_steps=True, map_prompt=PROMPT, combine_prompt=PROMPT)
chain({"input_documents": docs}, return_only_outputs=True)

自定义MapReduceChain

多输入提示

您还可以使用多输入提示。在此示例中,我们将使用 MapReduce 链来回答有关我们代码的特定问题。

python 复制代码
from langchain.chains.combine_documents.map_reduce import MapReduceDocumentsChain
from langchain.chains.combine_documents.stuff import StuffDocumentsChain
# 第一个prompt
map_template_string = """Give the following python code information, generate a description that explains what the code does and also mention the time complexity.
Code:
{code}

Return the the description in the following format:
name of the function: description of the function
"""

# 第二个prompt
reduce_template_string = """Given the following python function names and descriptions, answer the following question
{code_description}
Question: {question}
Answer:
"""
# 第一个prompt模板
MAP_PROMPT = PromptTemplate(input_variables=["code"], template=map_template_string)
# 第二个prompt模板
REDUCE_PROMPT = PromptTemplate(input_variables=["code_description", "question"], template=reduce_template_string)
# 大模型
llm = OpenAI()
# map 链
map_llm_chain = LLMChain(llm=llm, prompt=MAP_PROMPT)
#reduce 链
reduce_llm_chain = LLMChain(llm=llm, prompt=REDUCE_PROMPT)

generative_result_reduce_chain = StuffDocumentsChain(
    llm_chain=reduce_llm_chain,
    document_variable_name="code_description",
)

combine_documents = MapReduceDocumentsChain(
    llm_chain=map_llm_chain,
    combine_document_chain=generative_result_reduce_chain,
    document_variable_name="code",
)

map_reduce = MapReduceChain(
    combine_documents_chain=combine_documents,
    text_splitter=CharacterTextSplitter(separator="\n##\n", chunk_size=100, chunk_overlap=0),
)

代码片段为:

python 复制代码
code = """
def bubblesort(list):
   for iter_num in range(len(list)-1,0,-1):
      for idx in range(iter_num):
         if list[idx]>list[idx+1]:
            temp = list[idx]
            list[idx] = list[idx+1]
            list[idx+1] = temp
    return list
##
def insertion_sort(InputList):
   for i in range(1, len(InputList)):
      j = i-1
      nxt_element = InputList[i]
   while (InputList[j] > nxt_element) and (j >= 0):
      InputList[j+1] = InputList[j]
      j=j-1
   InputList[j+1] = nxt_element
   return InputList
##
def shellSort(input_list):
   gap = len(input_list) // 2
   while gap > 0:
      for i in range(gap, len(input_list)):
         temp = input_list[i]
         j = i
   while j >= gap and input_list[j - gap] > temp:
      input_list[j] = input_list[j - gap]
      j = j-gap
      input_list[j] = temp
   gap = gap//2
   return input_list

"""
python 复制代码
# 哪个函数的时间复杂度更好
map_reduce.run(input_text=code, question="Which function has a better time complexity?")

结果:

python 复制代码
    Created a chunk of size 247, which is longer than the specified 100
    Created a chunk of size 267, which is longer than the specified 100

    'shellSort has a better time complexity than both bubblesort and insertion_sort, as it has a time complexity of O(n^2), while the other two have a time complexity of O(n^2).'

refine(提炼) Chain

本节显示使用refine链进行汇总的结果。

python 复制代码
chain = load_summarize_chain(llm, chain_type="refine")

chain.run(docs)

结果:

python 复制代码
问界M5是赛力斯与华为合力打造的高端品牌AITO的首款车,问界M5共推出两款车型,后驱标准版预售价格25万元,四驱性能版28万元。

中间步骤

如果我们想要检查它们,我们还可以返回refine链的中间步骤。这是通过 return_refine_steps 变量完成的。

python 复制代码
# 注意这里指定参数
chain = load_summarize_chain(OpenAI(temperature=0), chain_type="refine", return_intermediate_steps=True)

chain({"input_documents": docs}, return_only_outputs=True)
# 结果
'问界M5是赛力斯与华为合力打造的高端品牌AITO的首款车,问界M5共推出两款车型,后驱标准版预售价格25万元,四驱性能版28万元。'

自定义prompt

您还可以在该链上使用您自己的提示。在此示例中,我们将用意大利语回复。

python 复制代码
prompt_template = """写出以下内容的简洁摘要:

{text}

意大利语简洁摘要:"""
PROMPT = PromptTemplate(template=prompt_template, input_variables=["text"])
refine_template = (
    "你的工作是编写最终摘要\n"
    "我们已经提供了一定程度的现有摘要: {existing_answer}\n"
    "我们有机会完善现有的摘要"
    "(only if needed) 下面有更多背景信息.\n"
    "------------\n"
    "{text}\n"
    "------------\n"
    "鉴于新的背景,完善意大利语的原始摘要"
    "如果上下文没有用,则返回原始摘要。"
)
refine_prompt = PromptTemplate(
    input_variables=["existing_answer", "text"],
    template=refine_template,
)
chain = load_summarize_chain(OpenAI(temperature=0), chain_type="refine", return_intermediate_steps=True, question_prompt=PROMPT, refine_prompt=refine_prompt)
chain({"input_documents": docs}, return_only_outputs=True)

结果:

python 复制代码
    {'intermediate_steps': ["\n\nQuesta sera, ci incontriamo come democratici, repubblicani e indipendenti, ma soprattutto come americani. La Russia di Putin ha cercato di scuotere le fondamenta del mondo libero, ma ha sottovalutato la forza della gente ucraina. Insieme ai nostri alleati, stiamo imponendo sanzioni economiche, tagliando l'accesso della Russia alla tecnologia e bloccando i suoi più grandi istituti bancari dal sistema finanziario internazionale. Il Dipartimento di Giustizia degli Stati Uniti sta anche assemblando una task force dedicata per andare dopo i crimini degli oligarchi russi.",
      "\n\nQuesta sera, ci incontriamo come democratici, repubblicani e indipendenti, ma soprattutto come americani. La Russia di Putin ha cercato di scuotere le fondamenta del mondo libero, ma ha sottovalutato la forza della gente ucraina. Insieme ai nostri alleati, stiamo imponendo sanzioni economiche, tagliando l'accesso della Russia alla tecnologia, bloccando i suoi più grandi istituti bancari dal sistema finanziario internazionale e chiudendo lo spazio aereo americano a tutti i voli russi. Il Dipartimento di Giustizia degli Stati Uniti sta anche assemblando una task force dedicata per andare dopo i crimini degli oligarchi russi. Stiamo fornendo più di un miliardo di dollari in assistenza diretta all'Ucraina e fornendo assistenza militare,",
      "\n\nQuesta sera, ci incontriamo come democratici, repubblicani e indipendenti, ma soprattutto come americani. La Russia di Putin ha cercato di scuotere le fondamenta del mondo libero, ma ha sottovalutato la forza della gente ucraina. Insieme ai nostri alleati, stiamo imponendo sanzioni economiche, tagliando l'accesso della Russia alla tecnologia, bloccando i suoi più grandi istituti bancari dal sistema finanziario internazionale e chiudendo lo spazio aereo americano a tutti i voli russi. Il Dipartimento di Giustizia degli Stati Uniti sta anche assemblando una task force dedicata per andare dopo i crimini degli oligarchi russi. Stiamo fornendo più di un miliardo di dollari in assistenza diretta all'Ucraina e fornendo assistenza militare."],
     'output_text': "\n\nQuesta sera, ci incontriamo come democratici, repubblicani e indipendenti, ma soprattutto come americani. La Russia di Putin ha cercato di scuotere le fondamenta del mondo libero, ma ha sottovalutato la forza della gente ucraina. Insieme ai nostri alleati, stiamo imponendo sanzioni economiche, tagliando l'accesso della Russia alla tecnologia, bloccando i suoi più grandi istituti bancari dal sistema finanziario internazionale e chiudendo lo spazio aereo americano a tutti i voli russi. Il Dipartimento di Giustizia degli Stati Uniti sta anche assemblando una task force dedicata per andare dopo i crimini degli oligarchi russi. Stiamo fornendo più di un miliardo di dollari in assistenza diretta all'Ucraina e fornendo assistenza militare."}

参考地址:

https://python.langchain.com/docs/modules/chains/popular/summarize

相关推荐
waiting不是违停1 天前
LangChain Ollama实战文献检索助手(二)少样本提示FewShotPromptTemplate示例选择器
langchain·llm·ollama
Y24834908911 天前
05LangChain实战课 - 提示工程与FewShotPromptTemplate的应用
人工智能·langchain
科研小达人2 天前
Langchain调用模型使用FAISS
python·chatgpt·langchain·faiss
小陈phd4 天前
大语言模型及LangChain介绍
人工智能·语言模型·langchain
写程序的小火箭5 天前
如何评估一个RAG系统(RAGas评测框架)-下篇
人工智能·gpt·语言模型·chatgpt·langchain
Stitch .5 天前
小北的字节跳动青训营与 LangChain 实战课:探索 AI 技术的新边界(持续更新中~~~)
人工智能·python·gpt·ai·语言模型·chatgpt·langchain
黑金IT6 天前
掌握AI Prompt的艺术:如何有效引导智能助手
人工智能·langchain·prompt·ai编程
科研小达人6 天前
langchain调用chatgpt对文本进行编码
服务器·langchain
智兔唯新6 天前
【AIGC】COT思维链:让AI学会拆解问题,像人一样思考
人工智能·python·langchain·prompt·aigc
wyh_1116 天前
windows下xinference无法加载本地大模型问题解决
langchain·xinference