■ create_retriever_tool 함수를 사용해 FAISS 벡터 스토어 검색 도구를 만드는 방법을 보여준다.
▶ main.py
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
import ast import os import re from langchain_community.utilities import SQLDatabase from langchain_community.vectorstores import FAISS from langchain_openai import OpenAIEmbeddings from langchain.agents.agent_toolkits import create_retriever_tool os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>" # SQLITE 데이터베이스를 초기화한다. sqlDatabase = SQLDatabase.from_uri("sqlite:///chinook.db") # SQLite 데이터를 가져오는 함수를 정의한다. def getSQLiteData(sqlDatabase, sql): resultString = sqlDatabase.run(sql) resultTupleList = ast.literal_eval(resultString) resultList1 = [element for resultTuple in resultTupleList for element in resultTuple if element] resultList2 = [re.sub(r"\b\d+\b", "", result).strip() for result in resultList1] return list(set(resultList2)) # 아티스트명, 앨범 타이틀 리스트를 구한다. artistNameList = getSQLiteData(sqlDatabase, "SELECT Name FROM artists") albumTitleList = getSQLiteData(sqlDatabase, "SELECT Title FROM albums" ) # FAISS 벡터 스토어를 생성한다: faiss = FAISS.from_texts(artistNameList + albumTitleList, OpenAIEmbeddings()) # FAISS 벡터 스토어 검색기를 설정한다. faissVectorStoreRetriever = faiss.as_retriever(search_kwargs = {"k" : 5}) # FAISS 벡터 스토어 검색기 도구를 생성한다. faissVectorStoreRetrieverTool = create_retriever_tool( faissVectorStoreRetriever, name = "search_proper_nouns", description = "Use to look up values to filter on. Input is an approximate spelling of the proper noun, output is valid proper nouns. Use the noun most similar to the search." ) # FAISS 벡터 스토어 검색기 도구를 실행한다. resultString = faissVectorStoreRetrieverTool.invoke("Alice Chains") print(resultString) """ Alice In Chains Alanis Morissette Pearl Jam Pearl Jam Audioslave """ |
▶ requirements.txt
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
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 certifi==2024.6.2 charset-normalizer==3.3.2 dataclasses-json==0.6.7 distro==1.9.0 exceptiongroup==1.2.1 faiss-gpu==1.7.2 frozenlist==1.4.1 greenlet==3.0.3 h11==0.14.0 httpcore==1.0.5 httpx==0.27.0 idna==3.7 jsonpatch==1.33 jsonpointer==3.0.0 langchain==0.2.3 langchain-community==0.2.4 langchain-core==0.2.5 langchain-openai==0.1.8 langchain-text-splitters==0.2.1 langsmith==0.1.77 marshmallow==3.21.3 multidict==6.0.5 mypy-extensions==1.0.0 numpy==1.26.4 openai==1.33.0 orjson==3.10.4 packaging==23.2 pydantic==2.7.4 pydantic_core==2.18.4 PyYAML==6.0.1 regex==2024.5.15 requests==2.32.3 sniffio==1.3.1 SQLAlchemy==2.0.30 tenacity==8.3.0 tiktoken==0.7.0 tqdm==4.66.4 typing-inspect==0.9.0 typing_extensions==4.12.2 urllib3==2.2.1 yarl==1.9.4 |
※ pip install langchain langchain-community langchain-openai faiss-gpu 명령을 실행했다.
