■ 단순 검색 증강 생성(RAG, Retrieval Augmented Generation) 애플리케이션을 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 58 59 60 61 62 |
import bs4 import os from langchain_community.document_loaders import WebBaseLoader from langchain_text_splitters import RecursiveCharacterTextSplitter from langchain_chroma import Chroma from langchain_openai import OpenAIEmbeddings from langchain import hub from langchain_core.runnables import RunnablePassthrough from langchain_openai import ChatOpenAI from langchain_core.output_parsers import StrOutputParser os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>" # 웹 문서를 로드한다. webBaseLoader = WebBaseLoader( web_paths = ("https://lilianweng.github.io/posts/2023-06-23-agent/",), bs_kwargs = dict(parse_only = bs4.SoupStrainer(class_ = ("post-content", "post-title", "post-header"))) ) documentList = webBaseLoader.load() # 문서 리스트 : 1건 # 문서를 분할한다. recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 1000, chunk_overlap = 200) splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList) # 분할 문서 리스트 : 66건 # 분할한 문서를 벡터 저장소에 저장한다. chroma = Chroma.from_documents(documents = splitDocumentList, embedding = OpenAIEmbeddings()) vectorStoreRetriever = chroma.as_retriever() # 벡터 저장소 검색기 # 문서 내용 병합 함수를 정의한다. def mergeDocumentContent(documentList): return "\n\n".join(document.page_content for document in documentList) # 랭체인 허브에서 프롬프트 템플리트를 가져온다. chatPromptTemplate = hub.pull("rlm/rag-prompt") # 질의응답 모델을 설정한다. chatOpenAI = ChatOpenAI(model = "gpt-3.5-turbo-0125") # 질의응답 체인을 설정한다. runnableSequence = ( {"context" : vectorStoreRetriever | mergeDocumentContent, "question" : RunnablePassthrough()} | chatPromptTemplate | chatOpenAI | StrOutputParser() ) # 질의응답을 실행한다. resultString = runnableSequence.invoke("What is Task Decomposition?") print(resultString) """ Task Decomposition is a technique that breaks down complex tasks into smaller and simpler steps to make them more manageable. It involves transforming big tasks into multiple smaller tasks to enhance model performance. This process can be done using prompting techniques, task-specific instructions, or with human inputs. """ |
▶ 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 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 |
aiohttp==3.9.5 aiosignal==1.3.1 annotated-types==0.7.0 anyio==4.4.0 asgiref==3.8.1 async-timeout==4.0.3 attrs==23.2.0 backoff==2.2.1 bcrypt==4.1.3 beautifulsoup4==4.12.3 bs4==0.0.2 build==1.2.1 cachetools==5.3.3 certifi==2024.6.2 charset-normalizer==3.3.2 chroma-hnswlib==0.7.3 chromadb==0.5.0 click==8.1.7 coloredlogs==15.0.1 dataclasses-json==0.6.7 Deprecated==1.2.14 distro==1.9.0 dnspython==2.6.1 email_validator==2.1.1 exceptiongroup==1.2.1 fastapi==0.111.0 fastapi-cli==0.0.4 filelock==3.14.0 flatbuffers==24.3.25 frozenlist==1.4.1 fsspec==2024.6.0 google-auth==2.30.0 googleapis-common-protos==1.63.1 greenlet==3.0.3 grpcio==1.64.1 h11==0.14.0 httpcore==1.0.5 httptools==0.6.1 httpx==0.27.0 huggingface-hub==0.23.3 humanfriendly==10.0 idna==3.7 importlib_metadata==7.1.0 importlib_resources==6.4.0 Jinja2==3.1.4 jsonpatch==1.33 jsonpointer==3.0.0 kubernetes==30.1.0 langchain==0.2.3 langchain-chroma==0.1.1 langchain-community==0.2.4 langchain-core==0.2.5 langchain-openai==0.1.8 langchain-text-splitters==0.2.1 langchainhub==0.1.18 langsmith==0.1.76 markdown-it-py==3.0.0 MarkupSafe==2.1.5 marshmallow==3.21.3 mdurl==0.1.2 mmh3==4.1.0 monotonic==1.6 mpmath==1.3.0 multidict==6.0.5 mypy-extensions==1.0.0 numpy==1.26.4 oauthlib==3.2.2 onnxruntime==1.18.0 openai==1.33.0 opentelemetry-api==1.25.0 opentelemetry-exporter-otlp-proto-common==1.25.0 opentelemetry-exporter-otlp-proto-grpc==1.25.0 opentelemetry-instrumentation==0.46b0 opentelemetry-instrumentation-asgi==0.46b0 opentelemetry-instrumentation-fastapi==0.46b0 opentelemetry-proto==1.25.0 opentelemetry-sdk==1.25.0 opentelemetry-semantic-conventions==0.46b0 opentelemetry-util-http==0.46b0 orjson==3.10.4 overrides==7.7.0 packaging==23.2 posthog==3.5.0 protobuf==4.25.3 pyasn1==0.6.0 pyasn1_modules==0.4.0 pydantic==2.7.3 pydantic_core==2.18.4 Pygments==2.18.0 PyPika==0.48.9 pyproject_hooks==1.1.0 python-dateutil==2.9.0.post0 python-dotenv==1.0.1 python-multipart==0.0.9 PyYAML==6.0.1 regex==2024.5.15 requests==2.32.3 requests-oauthlib==2.0.0 rich==13.7.1 rsa==4.9 shellingham==1.5.4 six==1.16.0 sniffio==1.3.1 soupsieve==2.5 SQLAlchemy==2.0.30 starlette==0.37.2 sympy==1.12.1 tenacity==8.3.0 tiktoken==0.7.0 tokenizers==0.19.1 tomli==2.0.1 tqdm==4.66.4 typer==0.12.3 types-requests==2.32.0.20240602 typing-inspect==0.9.0 typing_extensions==4.12.2 ujson==5.10.0 urllib3==2.2.1 uvicorn==0.30.1 uvloop==0.19.0 watchfiles==0.22.0 websocket-client==1.8.0 websockets==12.0 wrapt==1.16.0 yarl==1.9.4 zipp==3.19.2 |
※ pip install bs4 langchain langchain-chroma langchainhub langchain_community langchain-openai 명령을 실행했다.