LangChain：打造自己的LLM应用

from langchain import PromptTemplate

prompt_template = '''作为一个资深编辑，请针对 >>> 和 <<< 中间的文本写一段摘要。
>>> {text} <<<
'''

prompt = PromptTemplate(template=prompt_template, input_variables=["text"])
print(prompt.format_prompt(text="我爱北京天安门"))

from langchain.text_splitter import RecursiveCharacterTextSplitter

text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
    model_name="gpt-3.5-turb
    allowed_special="all",
    separators=["\n\n", "\n", "。", "，"],
    chunk_size=7000,
    chunk_overlap=0
)
docs = text_splitter.create_documents(["文本在这里"])
print(docs)

#通过cache_folder加载本地模型
embeddings = HuggingFaceEmbeddings(model_name="text2vec-base-chinese", cache_folder="本地模型地址")

embeddings = embeddings_model.embed_documents(
    [
        "我爱北京天安门!",
        "Hello world!"
    ]
)

from langchain import FAISS
from langchain.document_loaders import WebBaseLoader
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter

loader = WebBaseLoader("https://in.m.jd.com/help/app/register_info.html")
data = loader.load()
text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
    model_name="gpt-3.5-turbo",
    allowed_special="all",
    separators=["\n\n", "\n", "。", "，"],
    chunk_size=800,
    chunk_overlap=0
)
docs = text_splitter.split_documents(data)
#通过cache_folder设置自己的本地模型路径
embeddings = HuggingFaceEmbeddings(model_name="text2vec-base-chinese", cache_folder="models")
vectorstore = FAISS.from_documents(docs, embeddings)
result = vectorstore.as_retriever().get_relevant_documents("用户注册资格")
print(result)
print(len(result))

from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate
from langchain.output_parsers import ResponseSchema, StructuredOutputParser
from azure_chat_llm import llm

#output parser
keyword_schema = ResponseSchema(name="keyword", description="评论的关键词列表")
emotion_schema = ResponseSchema(name="emotion", description="评论的情绪，正向为1，中性为0，负向为-1")
response_schemas = [keyword_schema, emotion_schema]
output_parser = StructuredOutputParser.from_response_schemas(response_schemas)
format_instructions = output_parser.get_format_instructions()

#prompt template
prompt_template_txt = '''
作为资深客服，请针对 >>> 和 <<< 中间的文本识别其中的关键词，以及包含的情绪是正向、负向还是中性。
>>> {text} <<<
RESPONSE:
{format_instructions}
'''

prompt = PromptTemplate(template=prompt_template_txt, input_variables=["text"],
                        partial_variables={"format_instructions": format_instructions})

#llmchain
llm_chain = LLMChain(prompt=prompt, llm=llm)
comment = "京东物流没的说，速度态度都是杠杠滴！这款路由器颜值贼高，怎么说呢，就是泰裤辣！这线条，这质感，这速度，嘎嘎快！以后妈妈再也不用担心家里的网速了！"
result = llm_chain.run(comment)
data = output_parser.parse(result)
print(f"type={type(data)}, keyword={data['keyword']}, emotion={data['emotion']}")

from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate
from langchain.chains import SimpleSequentialChain

first_prompt = PromptTemplate.from_template(
    "翻译下面的内容到中文:"
    "\n\n{content}"
)
# chain 1: 输入：Review 输出：英文的 Review
chain_trans = LLMChain(llm=llm, prompt=first_prompt, output_key="content_zh")

second_prompt = PromptTemplate.from_template(
    "一句话总结下面的内容:"
    "\n\n{content_zh}"
)

chain_summary = LLMChain(llm=llm, prompt=second_prompt)
overall_simple_chain = SimpleSequentialChain(chains=[chain_trans, chain_summary],verbose=True)
content = '''In a blog post authored back in 2011, Marc Andreessen warned that, “Software is eating the world.” Over a decade later, we are witnessing the emergence of a new type of technology that’s consuming the world with even greater voracity: generative artificial intelligence (AI). This innovative AI includes a unique class of large language models (LLM), derived from a decade of groundbreaking research, that are capable of out-performing humans at certain tasks. And you don’t have to have a PhD in machine learning to build with LLMs—developers are already building software with LLMs with basic HTTP requests and natural language prompts.
In this article, we’ll tell the story of GitHub’s work with LLMs to help other developers learn how to best make use of this technology. This post consists of two main sections: the first will describe at a high level how LLMs function and how to build LLM-based applications. The second will dig into an important example of an LLM-based application: GitHub Copilot code completions.
Others have done an impressive job of cataloging our work from the outside. Now, we’re excited to share some of the thought processes that have led to the ongoing success of GitHub Copilot.
'''
result = overall_simple_chain.run(content)
print(f'result={result}')

from langchain.chains import ConversationChain
from langchain.memory import ConversationBufferMemory

from azure_chat_llm import llm

memory = ConversationBufferMemory()
conversation = ConversationChain(llm=llm, memory=memory, verbose=True)
print(conversation.prompt)
print(conversation.predict(input="我的姓名是tiger"))
print(conversation.predict(input="1+1=?"))
print(conversation.predict(input="我的姓名是什么"))

agent = initialize_agent(agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
                tools=tools,
                llm=llm,
                verbose=True)
print(agent.agent.llm_chain.prompt.template)

from azure_chat_llm import llm
from langchain.agents import load_tools, initialize_agent, tool
from langchain.agents.agent_types import AgentType
from datetime import date

@tool
def time(text: str) -> str:
    """
    返回今天的日期。
    """
    return str(date.today())


tools = load_tools(['llm-math'], llm=llm)
tools.append(time)
agent_math = initialize_agent(agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
                                   tools=tools,
                                   llm=llm,
                                   verbose=True)
print(agent_math("计算45 * 54"))
print(agent_math("今天是哪天？"))

from langchain.prompts import PromptTemplate
from langchain.document_loaders import PlaywrightURLLoader
from langchain.chains.summarize import load_summarize_chain
from langchain.text_splitter import RecursiveCharacterTextSplitter
from azure_chat_llm import llm

loader = PlaywrightURLLoader(urls=["https://content.jr.jd.com/article/index.html?pageId=708258989"])
data = loader.load()

text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
    model_name="gpt-3.5-turbo",
    allowed_special="all",
    separators=["\n\n", "\n", "。", "，"],
    chunk_size=7000,
    chunk_overlap=0
)

prompt_template = '''
作为一个资深编辑，请针对 >>> 和 <<< 中间的文本写一段摘要。
>>> {text} <<<
'''
refine_template = '''
作为一个资深编辑，基于已有的一段摘要：{existing_answer}，针对 >>> 和 <<< 中间的文本完善现有的摘要。
>>> {text} <<<
'''

PROMPT = PromptTemplate(template=prompt_template, input_variables=["text"])
REFINE_PROMPT = PromptTemplate(
    template=refine_template, input_variables=["existing_answer", "text"]
)

chain = load_summarize_chain(llm, chain_type="refine", question_prompt=PROMPT, refine_prompt=REFINE_PROMPT, verbose=False)

docs = text_splitter.split_documents(data)
result = chain.run(docs)
print(result)

from langchain.chains import RetrievalQA
from langchain.document_loaders import WebBaseLoader
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
from langchain.prompts import PromptTemplate
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import FAISS

from azure_chat_llm import llm

loader = WebBaseLoader("https://in.m.jd.com/help/app/register_info.html")
data = loader.load()
text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
    model_name="gpt-3.5-turbo",
    allowed_special="all",
    separators=["\n\n", "\n", "。", "，"],
    chunk_size=800,
    chunk_overlap=0
)
docs = text_splitter.split_documents(data)
#设置自己的模型路径
embeddings = HuggingFaceEmbeddings(model_name="text2vec-base-chinese", cache_folder="model")
vectorstore = FAISS.from_documents(docs, embeddings)

template = """请使用下面提供的背景信息来回答最后的问题。 如果你不知道答案，请直接说不知道，不要试图凭空编造答案。
回答时最多使用三个句子，保持回答尽可能简洁。 回答结束时，请一定要说"谢谢你的提问！"
{context}
问题: {question}
有用的回答:"""
QA_CHAIN_PROMPT = PromptTemplate(input_variables=["context", "question"], template=template)

qa_chain = RetrievalQA.from_chain_type(llm, retriever=vectorstore.as_retriever(),
                                       return_source_documents=True,
                                       chain_type_kwargs={"prompt": QA_CHAIN_PROMPT})

result = qa_chain({"query": "用户注册资格"})
print(result["result"])
print(len(result['source_documents']))