[PYTHON/LLAMA-INDEX] FAISS 벡터 데이터베이스를 사용해 질의 응답하기

■ FAISS 벡터 데이터베이스를 사용해 질의 응답하는 방법을 보여준다.

▶ main.py


import os

import faiss

from llama_index.core                import SimpleDirectoryReader, Settings, GPTVectorStoreIndex
from llama_index.vector_stores.faiss import FaissVectorStore
from llama_index.llms.openai         import OpenAI

os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>"

simpleDirectoryReader = SimpleDirectoryReader(input_dir = "/home/king/data")

documentList = simpleDirectoryReader.load_data()

Settings.llm          = OpenAI(model = "gpt-3.5-turbo", temperature = 0.1)
Settings.vector_store = FaissVectorStore(faiss_index = faiss.IndexFlatL2(1536))

vectorStoreIndex = GPTVectorStoreIndex.from_documents(documentList)

retrieverQueryEngine = vectorStoreIndex.as_query_engine()

responsea = retrieverQueryEngine.query("미코의 열정은? 한국어로")

print(responsea)

"""
미코의 열정은 네오 도쿄를 더 나은 도시로 바꾸어 나가는 것에 대한 다짐으로 나타납니다.
"""

import os

import faiss

from llama_index.core import SimpleDirectoryReader, Settings, GPTVectorStoreIndex

from llama_index.vector_stores.faiss import FaissVectorStore

from llama_index.llms.openai import OpenAI

os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>"

simpleDirectoryReader = SimpleDirectoryReader(input_dir = "/home/king/data")

documentList = simpleDirectoryReader.load_data()

Settings.llm = OpenAI(model = "gpt-3.5-turbo", temperature = 0.1)

Settings.vector_store = FaissVectorStore(faiss_index = faiss.IndexFlatL2(1536))

vectorStoreIndex = GPTVectorStoreIndex.from_documents(documentList)

retrieverQueryEngine = vectorStoreIndex.as_query_engine()

responsea = retrieverQueryEngine.query("미코의 열정은? 한국어로")

print(responsea)

"""

미코의 열정은 네오 도쿄를 더 나은 도시로 바꾸어 나가는 것에 대한 다짐으로 나타납니다.

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.4.0
async-timeout==4.0.3
attrs==23.2.0
beautifulsoup4==4.12.3
certifi==2024.6.2
charset-normalizer==3.3.2
click==8.1.7
dataclasses-json==0.6.6
Deprecated==1.2.14
dirtyjson==1.0.8
distro==1.9.0
exceptiongroup==1.2.1
faiss-gpu==1.7.2
frozenlist==1.4.1
fsspec==2024.6.0
greenlet==3.0.3
h11==0.14.0
httpcore==1.0.5
httpx==0.27.0
idna==3.7
joblib==1.4.2
jsonpatch==1.33
jsonpointer==2.4
langchain==0.2.3
langchain-core==0.2.5
langchain-text-splitters==0.2.1
langsmith==0.1.75
llama-index==0.10.43
llama-index-agent-openai==0.2.7
llama-index-cli==0.1.12
llama-index-core==0.10.43
llama-index-embeddings-openai==0.1.10
llama-index-indices-managed-llama-cloud==0.1.6
llama-index-legacy==0.9.48
llama-index-llms-openai==0.1.22
llama-index-multi-modal-llms-openai==0.1.6
llama-index-program-openai==0.1.6
llama-index-question-gen-openai==0.1.3
llama-index-readers-file==0.1.23
llama-index-readers-llama-parse==0.1.4
llama-index-vector-stores-faiss==0.1.2
llama-parse==0.4.4
llamaindex-py-client==0.1.19
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
nest-asyncio==1.6.0
networkx==3.3
nltk==3.8.1
numpy==1.26.4
openai==1.33.0
orjson==3.10.3
packaging==23.2
pandas==2.2.2
pillow==10.3.0
pydantic==2.7.3
pydantic_core==2.18.4
pypdf==4.2.0
python-dateutil==2.9.0.post0
pytz==2024.1
PyYAML==6.0.1
regex==2024.5.15
requests==2.32.3
six==1.16.0
sniffio==1.3.1
soupsieve==2.5
SQLAlchemy==2.0.30
striprtf==0.0.26
tenacity==8.3.0
tiktoken==0.7.0
tqdm==4.66.4
typing-inspect==0.9.0
typing_extensions==4.12.2
tzdata==2024.1
urllib3==2.2.1
wrapt==1.16.0
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

anyio==4.4.0

async-timeout==4.0.3

attrs==23.2.0

beautifulsoup4==4.12.3

certifi==2024.6.2

charset-normalizer==3.3.2

click==8.1.7

dataclasses-json==0.6.6

Deprecated==1.2.14

dirtyjson==1.0.8

distro==1.9.0

exceptiongroup==1.2.1

faiss-gpu==1.7.2

frozenlist==1.4.1

fsspec==2024.6.0

greenlet==3.0.3

h11==0.14.0

httpcore==1.0.5

httpx==0.27.0

idna==3.7

joblib==1.4.2

jsonpatch==1.33

jsonpointer==2.4

langchain==0.2.3

langchain-core==0.2.5

langchain-text-splitters==0.2.1

langsmith==0.1.75

llama-index==0.10.43

llama-index-agent-openai==0.2.7

llama-index-cli==0.1.12

llama-index-core==0.10.43

llama-index-embeddings-openai==0.1.10

llama-index-indices-managed-llama-cloud==0.1.6

llama-index-legacy==0.9.48

llama-index-llms-openai==0.1.22

llama-index-multi-modal-llms-openai==0.1.6

llama-index-program-openai==0.1.6

llama-index-question-gen-openai==0.1.3

llama-index-readers-file==0.1.23

llama-index-readers-llama-parse==0.1.4

llama-index-vector-stores-faiss==0.1.2

llama-parse==0.4.4

llamaindex-py-client==0.1.19

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

nest-asyncio==1.6.0

networkx==3.3

nltk==3.8.1

numpy==1.26.4

openai==1.33.0

orjson==3.10.3

packaging==23.2

pandas==2.2.2

pillow==10.3.0

pydantic==2.7.3

pydantic_core==2.18.4

pypdf==4.2.0

python-dateutil==2.9.0.post0

pytz==2024.1

PyYAML==6.0.1

regex==2024.5.15

requests==2.32.3

six==1.16.0

sniffio==1.3.1

soupsieve==2.5

SQLAlchemy==2.0.30

striprtf==0.0.26

tenacity==8.3.0

tiktoken==0.7.0

tqdm==4.66.4

typing-inspect==0.9.0

typing_extensions==4.12.2

tzdata==2024.1

urllib3==2.2.1

wrapt==1.16.0

yarl==1.9.4

※ pip install openai langchain llama-index faiss-gpu llama-index-vector-stores-faiss 명령을 실행했다.