[PYTHON/LANGCHAIN] MultiQueryRetriever 클래스 : 생성자에서 retriever/llm_chain/parser

■ MultiQueryRetriever 클래스의 생성자에서 retriever/llm_chain/parser_key 인자를 사용해 MultiQueryRetriever 객체를 만드는 방법을 보여준다.

※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다.

▶ 예제 코드 (PY)


from dotenv import load_dotenv
from typing import List

from langchain_community.document_loaders import WebBaseLoader
from langchain_text_splitters             import RecursiveCharacterTextSplitter
from langchain_openai                     import OpenAIEmbeddings
from langchain_chroma                     import Chroma
from langchain_core.prompts               import PromptTemplate
from langchain_openai                     import ChatOpenAI
from langchain_core.output_parsers        import BaseOutputParser
from langchain.retrievers.multi_query     import MultiQueryRetriever

load_dotenv()

webBaseLoader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")

documentList = webBaseLoader.load()

recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 500, chunk_overlap = 0)

splitdocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

openAIEmbeddings = OpenAIEmbeddings()

chroma = Chroma.from_documents(documents = splitdocumentList, embedding = openAIEmbeddings)

promptTemplate = PromptTemplate(
    input_variables = ["question"],
    template        = """You are an AI language model assistant.
Your task is to generate five different versions of the given user question to retrieve relevant documents from a vector database.
By generating multiple perspectives on the user question, your goal is to help the user overcome some of the limitations of the distance-based similarity search.
Provide these alternative questions separated by newlines.
Original question : {question}"""
)

chatOpenAI = ChatOpenAI(temperature = 0)

class LineListOutputParser(BaseOutputParser[List[str]]):
    """Output parser for a list of lines."""

    def parse(self, text : str) -> List[str]:
        lineList = text.strip().split("\n")
        return list(filter(None, lineList))

lineListOutputParser = LineListOutputParser()

runnableSequence = promptTemplate | chatOpenAI | lineListOutputParser

rultiQueryRetriever = MultiQueryRetriever(retriever = chroma.as_retriever(), llm_chain = runnableSequence, parser_key = "lines")

from dotenv import load_dotenv

from typing import List

from langchain_community.document_loaders import WebBaseLoader

from langchain_text_splitters import RecursiveCharacterTextSplitter

from langchain_openai import OpenAIEmbeddings

from langchain_chroma import Chroma

from langchain_core.prompts import PromptTemplate

from langchain_openai import ChatOpenAI

from langchain_core.output_parsers import BaseOutputParser

from langchain.retrievers.multi_query import MultiQueryRetriever

load_dotenv()

webBaseLoader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")

documentList = webBaseLoader.load()

recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 500, chunk_overlap = 0)

splitdocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

openAIEmbeddings = OpenAIEmbeddings()

chroma = Chroma.from_documents(documents = splitdocumentList, embedding = openAIEmbeddings)

promptTemplate = PromptTemplate(

input_variables = ["question"],

template = """You are an AI language model assistant.

Your task is to generate five different versions of the given user question to retrieve relevant documents from a vector database.

By generating multiple perspectives on the user question, your goal is to help the user overcome some of the limitations of the distance-based similarity search.

Provide these alternative questions separated by newlines.

Original question : {question}"""

)

chatOpenAI = ChatOpenAI(temperature = 0)

class LineListOutputParser(BaseOutputParser[List[str]]):

"""Output parser for a list of lines."""

def parse(self, text : str) -> List[str]:

lineList = text.strip().split("\n")

return list(filter(None, lineList))

lineListOutputParser = LineListOutputParser()

runnableSequence = promptTemplate | chatOpenAI | lineListOutputParser

rultiQueryRetriever = MultiQueryRetriever(retriever = chroma.as_retriever(), llm_chain = runnableSequence, parser_key = "lines")