LangChain基础知识入门

pip install openai==0.28
pip install langchain

# 导入OpenAI模型
from langchain.llms import OpenAI
import os
os.environ["OPENAI_API_KEY"] = "你的OpenAI API token"
llm = OpenAI(model_name="text-davinci-003", n=2, temperature=0.3)
llm("给我讲一个笑话")
# 答案：一个猴子去河里洗澡，洗完后他看见自己的影子，他觉得自己太瘦了，于是他又把头放进河里洗了一遍！

# 使用generate方法可以同时接收多个输入，并且返回token使用信息
llm.generate(["给我讲一个故事", "给我讲一个笑话"])
# 答案：# generations=[
#   [Generation(text='\n\n一个叫玛丽的小女孩，有一只叫毛毛的小猫。\n\n每天晚上，玛丽都会和毛毛一起玩耍，一起跳舞，一起唱歌，一起玩游戏。\n\n有一天，玛丽和毛毛一起去海边玩，突然，毛毛被一只海鸥抓走了。玛丽非常伤心，她跑到海边哭了起来，哭着喊着毛毛的', 
#       generation_info={'finish_reason': 'length', 'logprobs': None}),
#     Generation(text='\n\n一个叫小明的男孩，他很喜欢探险。有一天，他和他的朋友们一起去森林里玩，突然，他发现一个洞穴，他非常好奇，于是他决定去看看洞穴里面到底有什么。\n\n他走进洞穴，里面黑暗而又潮湿，他继续前行，突然，他看到一只大老虎，它正在吃一只小兔子。', 
#       generation_info={'finish_reason': 'length', 'logprobs': None})], 
#   [Generation(text='\n\n两个熊在森林里走，一个熊说：“嘿，你知道为什么树林里没有路吗？”另一个熊回答：“不知道，为什么？”第一个熊说：“因为它们都在绕树林跑！”', generation_info={'finish_reason': 'stop', 'logprobs': None}), Generation(text='\n\n两个熊在森林里拔萝卜，一个熊拔出一个萝卜，另一个熊说：“你拔的太慢了，我拔的快一点！”', 
#       generation_info={'finish_reason': 'stop', 'logprobs': None})]

from langchain.chat_models import ChatOpenAI
from langchain.schema import (
    AIMessage,
    HumanMessage,
    SystemMessage
)
import os
os.environ["OPENAI_API_KEY"] = "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"

chat = ChatOpenAI(temperature=0)

messages = [
        SystemMessage(content="返回json object，不要纯文本，按照每项参数拆分，不要说明和解释信息"),
        HumanMessage(content="告诉我model Y汽车的尺寸参数")
]

print(chat(messages))
# 答案：# content='{\n "车长": "4,750 mm",\n "车宽": "1,921 mm",\n "车高": "1,624 mm",\n "轴距": "2,890 mm",\n "最小离地间隙": "162 mm",\n "行李箱容积": "1,900 L"\n}' additional_kwargs={} example=False

from langchain.chat_models import ChatOpenAI
from langchain.prompts import (
    ChatPromptTemplate,
    PromptTemplate,
    SystemMessagePromptTemplate,
    AIMessagePromptTemplate,
    HumanMessagePromptTemplate,
)
from langchain.schema import (
    AIMessage,
    HumanMessage,
    SystemMessage
)

system_template="你是一个把{input_language}翻译成{output_language}的助手"
system_message_prompt = SystemMessagePromptTemplate.from_template(system_template)
human_template="{text}"
human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)

chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, human_message_prompt])
messages = chat_prompt.format_prompt(input_language="英语", output_language="汉语", text="I love programming.")

print(messages)
#messages=[SystemMessage(content='你是一个把英语翻译成汉语的助手', additional_kwargs={}), HumanMessage(content='I love programming.', additional_kwargs={}, example=False)]
chat = ChatOpenAI(temperature=0)

print(chat(messages.to_messages()))

# content='我喜欢编程。' additional_kwargs={} example=False

from langchain.embeddings import OpenAIEmbeddings
open_embed = OpenAIEmbeddings()
text = "这是一个测试文档。"

query_result = open_embed.embed_query(text)
doc_result = open_embed.embed_documents([text])

print(query_result)
# [-0.009422866627573967, 0.004315766040235758, 0.002380653750151396,  ...]

from langchain import PromptTemplate
from langchain.llms import OpenAI

template = "我的邻居姓{lastname}，他生了个儿子，给他儿子起个名字"

prompt = PromptTemplate(
    input_variables=["lastname"],
    template=template,
)

prompt_text = prompt.format(lastname="王")
# result: 我的邻居姓王，他生了个儿子，给他儿子起个名字

# 调用OpenAI
llm = OpenAI(temperature=0.9)
print(llm(prompt_text))

# 叫王爱慕。

from langchain import PromptTemplate, FewShotPromptTemplate
from langchain.llms import OpenAI

examples = [
    {"word": "开心", "antonym": "难过"},
    {"word": "高", "antonym": "矮"},
]

example_template = """
单词: {word}
反义词: {antonym}\\n
"""

example_prompt = PromptTemplate(
    input_variables=["word", "antonym"],
    template=example_template,
)

few_shot_prompt = FewShotPromptTemplate(
    examples=examples,
    example_prompt=example_prompt,
    prefix="给出每个单词的反义词",
    suffix="单词: {input}\\n反义词:",
    input_variables=["input"],
    example_separator="\\n",
)

prompt_text = few_shot_prompt.format(input="粗")
print(prompt_text)

# 给出每个单词的反义词
# 单词: 开心
# 反义词: 难过

# 单词: 高
# 反义词: 矮

# 单词: 粗
# 反义词:

# 调用OpenAI
llm = OpenAI(temperature=0.9)
print(llm(prompt_text))

# 细

from langchain import PromptTemplate
from langchain.llms import OpenAI
from langchain.chains import LLMChain
# 定义模板
template = "我的邻居姓{lastname}，他生了个儿子，给他儿子起个名字"

prompt = PromptTemplate(
    input_variables=["lastname"],
    template=template,
)
llm = OpenAI(temperature=0.9)

chain = LLMChain(llm = llm, 
                  prompt = prompt)
# 执行链
print(chain.run("王"))
# 可以叫王子，也可以叫小王或者小王子等。。

from langchain import PromptTemplate
from langchain.llms import OpenAI
from langchain.chains import LLMChain, SimpleSequentialChain
# 创建第一条链
template = "我的邻居姓{lastname}，他生了个儿子，给他儿子起个名字"

first_prompt = PromptTemplate(
    input_variables=["lastname"],
    template=template,
)
llm = OpenAI(temperature=0.9)

first_chain = LLMChain(llm = llm, prompt = first_prompt)

# 创建第二条链
second_prompt = PromptTemplate(
    input_variables=["child_name"],
    template="邻居的儿子名字叫{child_name}，给他起一个小名",
)

second_chain = LLMChain(llm=llm, prompt=second_prompt)


# 链接两条链 
overall_chain = SimpleSequentialChain(chains=[first_chain, second_chain], verbose=True)

# 执行链，只需要传入第一个参数
catchphrase = overall_chain.run("王")

from langchain.agents import create_csv_agent
from langchain.llms import OpenAI
agent = create_csv_agent(OpenAI(temperature=0), 'data.csv', verbose=True)
agent.run("一共有多少行数据?")

from langchain.agents import load_tools
from langchain.agents import initialize_agent
from langchain.agents import AgentType
from langchain.llms import OpenAI

llm = OpenAI(temperature=0)
tools = load_tools(["serpapi"], llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)

agent.run("明天在北京穿什么衣服合适?")

from langchain.memory import ChatMessageHistory

history = ChatMessageHistory()
history.add_user_message("在吗？")
history.add_ai_message("有什么事?")

print(history.messages)

# [HumanMessage(content='在吗？', additional_kwargs={}), AIMessage(content='有什么事?', additional_kwargs={})]

from langchain import ConversationChain
from langchain.llms import OpenAI

llm = OpenAI(temperature=0)
conversation = ConversationChain(llm=llm, verbose=True)
conversation.predict(input="小明有1只猫")
conversation.predict(input="小刚有2只狗")
conversation.predict(input="小明和小刚一共有几只宠物?")

from langchain.memory import ChatMessageHistory
from langchain.schema import messages_from_dict, messages_to_dict

history = ChatMessageHistory()
history.add_user_message("hi!")
history.add_ai_message("whats up?")

dicts = messages_to_dict(history.messages)

print(dicts)
# [{'type': 'human', 'data': {'content': 'hi!', 'additional_kwargs': {}}},
# {'type': 'ai', 'data': {'content': 'whats up?', 'additional_kwargs': {}}}]
# 读取历史消息
new_messages = messages_from_dict(dicts)

print(new_messages)
#[HumanMessage(content='hi!', additional_kwargs={}),
# AIMessage(content='whats up?', additional_kwargs={})]

from langchain.document_loaders import TextLoader
loader = TextLoader('../state_of_the_union.txt', encoding='utf8')
documents = loader.load()

from langchain.text_splitter import CharacterTextSplitter

# 初始字符串
state_of_the_union = "..."

text_splitter = CharacterTextSplitter(        
    separator = "\\n\\n",
    chunk_size = 1000,
    chunk_overlap  = 200,
    length_function = len,
)

texts = text_splitter.create_documents([state_of_the_union])

from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import Chroma

# pku.txt内容：<https://www.pku.edu.cn/about.html>
with open('./pku.txt') as f:
    state_of_the_union = f.read()
text_splitter = CharacterTextSplitter(chunk_size=100, chunk_overlap=0)
texts = text_splitter.split_text(state_of_the_union)

embeddings = OpenAIEmbeddings()

docsearch = Chroma.from_texts(texts, embeddings)

query = "1937年北京大学发生了什么？"
docs = docsearch.similarity_search(query)
print(docs)

from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.embeddings import OpenAIEmbeddings

loader = TextLoader('../../../state_of_the_union.txt')
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()

db = FAISS.from_documents(texts, embeddings)
retriever = db.as_retriever()
docs = retriever.get_relevant_documents("what did he say about ketanji brown jackson")