■ load_summarize_chain 함수를 사용해 PDF 문서를 요약하는 방법을 보여준다. (llama3.2:3b 모델)
▶ 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 |
from langchain_community.document_loaders import PyPDFLoader from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain_ollama import ChatOllama from langchain.chains.summarize import load_summarize_chain pyPDFLoader = PyPDFLoader("nke-10k-2023.pdf") documentList = pyPDFLoader.load() recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 1000, chunk_overlap = 0) splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList) chatOllama = ChatOllama(model = "llama3.2:3b") mapReduceDocumentsChain = load_summarize_chain(chatOllama, chain_type = "map_reduce") responseDictionary = mapReduceDocumentsChain.invoke(splitDocumentList) print("-" * 50) for document in responseDictionary["input_documents"]: print(document.page_content) print("-" * 50) |
※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다.
▶ 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 |
aiohappyeyeballs==2.4.4 aiohttp==3.11.11 aiosignal==1.3.2 annotated-types==0.7.0 anyio==4.8.0 attrs==24.3.0 certifi==2024.12.14 charset-normalizer==3.4.1 colorama==0.4.6 dataclasses-json==0.6.7 filelock==3.16.1 frozenlist==1.5.0 fsspec==2024.12.0 greenlet==3.1.1 h11==0.14.0 httpcore==1.0.7 httpx==0.27.2 httpx-sse==0.4.0 huggingface-hub==0.27.1 idna==3.10 jsonpatch==1.33 jsonpointer==3.0.0 langchain==0.3.14 langchain-community==0.3.14 langchain-core==0.3.29 langchain-ollama==0.2.2 langchain-text-splitters==0.3.5 langsmith==0.2.10 marshmallow==3.25.1 multidict==6.1.0 mypy-extensions==1.0.0 numpy==2.2.1 ollama==0.4.6 orjson==3.10.14 packaging==24.2 propcache==0.2.1 pydantic==2.10.5 pydantic-settings==2.7.1 pydantic_core==2.27.2 pypdf==5.1.0 python-dotenv==1.0.1 PyYAML==6.0.2 regex==2024.11.6 requests==2.32.3 requests-toolbelt==1.0.0 safetensors==0.5.2 sniffio==1.3.1 SQLAlchemy==2.0.37 tenacity==9.0.0 tokenizers==0.21.0 tqdm==4.67.1 transformers==4.48.0 typing-inspect==0.9.0 typing_extensions==4.12.2 urllib3==2.3.0 yarl==1.18.3 |
※ pip install langchain langchain-community langchain-ollama pypdf transformers 명령을 사용했다.
