[PYTHON/LANGCHAIN] TimeWeightedVectorStoreRetriever 클래스 : 높은 감쇠율로 문서 검색하기

■ TimeWeightedVectorStoreRetriever 클래스를 사용해 높은 감쇠율로 문서를 검색하는 방법을 보여준다.

※ 높은 감소율(예 : 9가 여러 개)에서는 최근성 점수가 빠르게 0으로 떨어진다!
※ 이 값을 1로 설정하면 모든 객체에 대한 최근성은 0이 되며, 이는 다시 벡터 조회와 동일하다.

▶ main.py


import faiss

from langchain_openai                 import OpenAIEmbeddings
from langchain_community.docstore     import InMemoryDocstore
from langchain_community.vectorstores import FAISS
from langchain.retrievers             import TimeWeightedVectorStoreRetriever
from datetime                         import datetime
from datetime                         import timedelta
from langchain_core.documents         import Document

openAIEmbeddings = OpenAIEmbeddings()

embeddingSize = 1536

indexFlatL2 = faiss.IndexFlatL2(embeddingSize)

inMemoryDocstore = InMemoryDocstore({})

faiss = FAISS(openAIEmbeddings, indexFlatL2, inMemoryDocstore, {})

timeWeightedVectorStoreRetriever = TimeWeightedVectorStoreRetriever(vectorstore = faiss, decay_rate = 0.999, k = 1)

yesterday = datetime.now() - timedelta(days = 1)

timeWeightedVectorStoreRetriever.add_documents([Document(page_content = "hello world", metadata = {"last_accessed_at" : yesterday})])
timeWeightedVectorStoreRetriever.add_documents([Document(page_content = "hello foo")])

resultDocumentList = timeWeightedVectorStoreRetriever.get_relevant_documents("hello world")

for resultDocument in resultDocumentList:
    print(resultDocument)

import faiss

from langchain_openai import OpenAIEmbeddings

from langchain_community.docstore import InMemoryDocstore

from langchain_community.vectorstores import FAISS

from langchain.retrievers import TimeWeightedVectorStoreRetriever

from datetime import datetime

from datetime import timedelta

from langchain_core.documents import Document

openAIEmbeddings = OpenAIEmbeddings()

embeddingSize = 1536

indexFlatL2 = faiss.IndexFlatL2(embeddingSize)

inMemoryDocstore = InMemoryDocstore({})

faiss = FAISS(openAIEmbeddings, indexFlatL2, inMemoryDocstore, {})

timeWeightedVectorStoreRetriever = TimeWeightedVectorStoreRetriever(vectorstore = faiss, decay_rate = 0.999, k = 1)

yesterday = datetime.now() - timedelta(days = 1)

timeWeightedVectorStoreRetriever.add_documents([Document(page_content = "hello world", metadata = {"last_accessed_at" : yesterday})])

timeWeightedVectorStoreRetriever.add_documents([Document(page_content = "hello foo")])

resultDocumentList = timeWeightedVectorStoreRetriever.get_relevant_documents("hello world")

for resultDocument in resultDocumentList:

print(resultDocument)

▶ 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==3.10
jiter==0.5.0
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.3.0
langchain-community==0.3.0
langchain-core==0.3.0
langchain-openai==0.2.0
langchain-text-splitters==0.3.0
langsmith==0.1.121
marshmallow==3.22.0
multidict==6.1.0
mypy-extensions==1.0.0
numpy==1.26.4
openai==1.45.1
orjson==3.10.7
packaging==24.1
pydantic==2.9.1
pydantic-settings==2.5.2
pydantic_core==2.23.3
python-dotenv==1.0.1
PyYAML==6.0.2
regex==2024.9.11
requests==2.32.3
sniffio==1.3.1
SQLAlchemy==2.0.35
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==3.10

jiter==0.5.0

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.3.0

langchain-community==0.3.0

langchain-core==0.3.0

langchain-openai==0.2.0

langchain-text-splitters==0.3.0

langsmith==0.1.121

marshmallow==3.22.0

multidict==6.1.0

mypy-extensions==1.0.0

numpy==1.26.4

openai==1.45.1

orjson==3.10.7

packaging==24.1

pydantic==2.9.1

pydantic-settings==2.5.2

pydantic_core==2.23.3

python-dotenv==1.0.1

PyYAML==6.0.2

regex==2024.9.11

requests==2.32.3

sniffio==1.3.1

SQLAlchemy==2.0.35

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

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