高枕枕のBlog

Appearance

LangChain开发框架 ​

LangChain

安装 ​

  • pip install langchain
  • pip install openai
    • from langchain.llms import OpenAI
    • llm = OpenAI(openai_api_key="...")

LLMChain核心 ​

  • LLM模型
    • LLMs 输入字符串
      • from langchain.llms import OpenAI
      • llm = OpenAI()
    • ChatModels 输入消息列表
      • ChatMessage
        • content
        • role
          • HumanMessage 人类
          • AIMessage ai
          • SystemMessage 系统
          • FunctionMessage 函数
          • others
      • from langchain.chat_models import ChatOpenAI
      • chat_model = ChatOpenAI()
    • api
      • llm.predict("hi!")
      • llm.predict_messages(messages)
  • Prompt
    • from langchain.prompts import PromptTemplate
    • prompt = PromptTemplate.from_template("{product}")
    • prompt.format(product="hi")
  • Output
    • from langchain.schema import BaseOutputParser
    • def parse(self, text): 重写方法
python
from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
    ChatPromptTemplate,
    SystemMessagePromptTemplate,
    HumanMessagePromptTemplate,
)
from langchain.chains import LLMChain
from langchain.schema import BaseOutputParser

class CommaSeparatedListOutputParser(BaseOutputParser):
    """Parse the output of an LLM call to a comma-separated list."""


    def parse(self, text: str):
        """Parse the output of an LLM call."""
        return text.strip().split(", ")

template = """You are a helpful assistant who generates comma separated lists.
A user will pass in a category, and you should generate 5 objects in that category in a comma separated list.
ONLY return a comma separated list, and nothing more."""
system_message_prompt = SystemMessagePromptTemplate.from_template(template)
human_template = "{text}"
human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)

chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, human_message_prompt])
chain = LLMChain(
    llm=ChatOpenAI(),
    prompt=chat_prompt,
    output_parser=CommaSeparatedListOutputParser()
)
chain.run("colors")
# >> ['red', 'blue', 'green', 'yellow', 'orange']

LCEL ​

  • 基础
    • 相当于将原来的函数嵌套形式变成了流式处理
    • 每一步invoke的输出作为下一步的输入
    • prompt
    • model
    • output_parser
  • 统一接口
    • stream: 流式返回响应的块
    • invoke: 在输入上调用链
    • batch: 在输入列表上调用链
python
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI

prompt = ChatPromptTemplate.from_template("tell me a short joke about {topic}")
model = ChatOpenAI(model="gpt-4")
output_parser = StrOutputParser()

chain = prompt | model | output_parser

chain.invoke({"topic": "ice cream"})
python
# 需要安装：
# pip install langchain docarray tiktoken

from langchain_community.vectorstores import DocArrayInMemorySearch
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnableParallel, RunnablePassthrough
from langchain_openai.chat_models import ChatOpenAI
from langchain_openai.embeddings import OpenAIEmbeddings

vectorstore = DocArrayInMemorySearch.from_texts(
    ["harrison worked at kensho", "bears like to eat honey"],
    embedding=OpenAIEmbeddings(),
)
retriever = vectorstore.as_retriever()

template = """Answer the question based only on the following context:
{context}

Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)
model = ChatOpenAI()
output_parser = StrOutputParser()

setup_and_retrieval = RunnableParallel(
    {"context": retriever, "question": RunnablePassthrough()}
)
chain = setup_and_retrieval | prompt | model | output_parser

chain.invoke("where did harrison work?")
python
from langchain_core.runnables import RunnablePassthrough


prompt = ChatPromptTemplate.from_template(
    "Tell me a short joke about {topic}"
)
output_parser = StrOutputParser()
model = ChatOpenAI(model="gpt-3.5-turbo")
chain = (
    {"topic": RunnablePassthrough()} 
    | prompt
    | model
    | output_parser
)

chain.invoke("ice cream")
python
@chain
def custom_chain(text):
    prompt_val1 = prompt1.invoke({"topic": text})
    output1 = ChatOpenAI().invoke(prompt_val1)
    parsed_output1 = StrOutputParser().invoke(output1)
    chain2 = prompt2 | ChatOpenAI() | StrOutputParser()
    return chain2.invoke({"joke": parsed_output1})
python
from operator import itemgetter

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnableLambda
from langchain_openai import ChatOpenAI


def length_function(text):
    return len(text)


def _multiple_length_function(text1, text2):
    return len(text1) * len(text2)


def multiple_length_function(_dict):
    return _multiple_length_function(_dict["text1"], _dict["text2"])


prompt = ChatPromptTemplate.from_template("what is {a} + {b}")
model = ChatOpenAI()

chain1 = prompt | model

chain = (
    {
        "a": itemgetter("foo") | RunnableLambda(length_function),
        "b": {"text1": itemgetter("foo"), "text2": itemgetter("bar")}
        | RunnableLambda(multiple_length_function),
    }
    | prompt
    | model
)
python
from operator import itemgetter

from langchain_community.vectorstores import FAISS
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI, OpenAIEmbeddings

vectorstore = FAISS.from_texts(
    ["harrison worked at kensho"], embedding=OpenAIEmbeddings()
)
retriever = vectorstore.as_retriever()

template = """Answer the question based only on the following context:
{context}

Question: {question}

Answer in the following language: {language}
"""
prompt = ChatPromptTemplate.from_template(template)

chain = (
    {
        "context": itemgetter("question") | retriever,
        "question": itemgetter("question"),
        "language": itemgetter("language"),
    }
    | prompt
    | model
    | StrOutputParser()
)

chain.invoke({"question": "where did harrison work", "language": "italian"})
python

模块 ​

模型 ​

检索 ​

链式调用 ​

其它 ​

模板 ​

用例 ​

部署 ​

集成 ​