[PYTHON/LANGCHAIN] EnsembleRetriever 클래스 : 생성자에서 retrievers/weights 인자를 사용해 EnsembleRetriever 객체 만들기

■ EnsembleRetriever 클래스의 생성자에서 retrievers/weights 인자를 사용해 EnsembleRetriever 객체를 만드는 방법을 보여준다.

▶ main.py


from langchain_community.retrievers   import BM25Retriever
from langchain_openai                 import OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.retrievers             import EnsembleRetriever

stringList1 = [
    "I like apples",
    "I like oranges",
    "Apples and oranges are fruits"
]

bm25Retriever = BM25Retriever.from_texts(stringList1, metadatas = [{"source" : 1}] * len(stringList1))

bm25Retriever.k = 2

stringList2 = [
    "You like apples",
    "You like oranges"
]

openAIEmbeddings = OpenAIEmbeddings()

faiss = FAISS.from_texts(stringList2, openAIEmbeddings, metadatas = [{"source" : 2}] * len(stringList2))

vectorStoreRetriever = faiss.as_retriever(search_kwargs = {"k" : 2})

ensembleRetriever = EnsembleRetriever(retrievers = [bm25Retriever, vectorStoreRetriever], weights = [0.5, 0.5])

documentList = ensembleRetriever.invoke("apples")

for document in documentList:
    print(document.page_content)

from langchain_community.retrievers import BM25Retriever

from langchain_openai import OpenAIEmbeddings

from langchain_community.vectorstores import FAISS

from langchain.retrievers import EnsembleRetriever

stringList1 = [

"I like apples",

"I like oranges",

"Apples and oranges are fruits"

]

bm25Retriever = BM25Retriever.from_texts(stringList1, metadatas = [{"source" : 1}] * len(stringList1))

bm25Retriever.k = 2

stringList2 = [

"You like apples",

"You like oranges"

]

openAIEmbeddings = OpenAIEmbeddings()

faiss = FAISS.from_texts(stringList2, openAIEmbeddings, metadatas = [{"source" : 2}] * len(stringList2))

vectorStoreRetriever = faiss.as_retriever(search_kwargs = {"k" : 2})

ensembleRetriever = EnsembleRetriever(retrievers = [bm25Retriever, vectorStoreRetriever], weights = [0.5, 0.5])

documentList = ensembleRetriever.invoke("apples")

for document in documentList:

print(document.page_content)

▶ requirements.txt


aiohappyeyeballs==2.4.0
aiohttp==3.10.5
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.4.0
attrs==24.2.0
certifi==2024.8.30
charset-normalizer==3.3.2
colorama==0.4.6
dataclasses-json==0.6.7
distro==1.9.0
faiss-cpu==1.8.0.post1
frozenlist==1.4.1
greenlet==3.1.0
h11==0.14.0
httpcore==1.0.5
httpx==0.27.2
idna==3.8
jiter==0.5.0
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.16
langchain-community==0.2.16
langchain-core==0.2.39
langchain-openai==0.1.23
langchain-text-splitters==0.2.4
langsmith==0.1.120
marshmallow==3.22.0
multidict==6.1.0
mypy-extensions==1.0.0
numpy==1.26.4
openai==1.45.0
orjson==3.10.7
packaging==24.1
pydantic==2.9.1
pydantic_core==2.23.3
PyYAML==6.0.2
rank-bm25==0.2.2
regex==2024.9.11
requests==2.32.3
sniffio==1.3.1
SQLAlchemy==2.0.34
tenacity==8.5.0
tiktoken==0.7.0
tqdm==4.66.5
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.3
yarl==1.11.1

aiohappyeyeballs==2.4.0

aiohttp==3.10.5

aiosignal==1.3.1

annotated-types==0.7.0

anyio==4.4.0

attrs==24.2.0

certifi==2024.8.30

charset-normalizer==3.3.2

colorama==0.4.6

dataclasses-json==0.6.7

distro==1.9.0

faiss-cpu==1.8.0.post1

frozenlist==1.4.1

greenlet==3.1.0

h11==0.14.0

httpcore==1.0.5

httpx==0.27.2

idna==3.8

jiter==0.5.0

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.16

langchain-community==0.2.16

langchain-core==0.2.39

langchain-openai==0.1.23

langchain-text-splitters==0.2.4

langsmith==0.1.120

marshmallow==3.22.0

multidict==6.1.0

mypy-extensions==1.0.0

numpy==1.26.4

openai==1.45.0

orjson==3.10.7

packaging==24.1

pydantic==2.9.1

pydantic_core==2.23.3

PyYAML==6.0.2

rank-bm25==0.2.2

regex==2024.9.11

requests==2.32.3

sniffio==1.3.1

SQLAlchemy==2.0.34

tenacity==8.5.0

tiktoken==0.7.0

tqdm==4.66.5

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.3

yarl==1.11.1

※ install langchain-community langchain-openai faiss-cpu rank_bm25 명령을 실행했다.