■ RecursiveCharacterTextSplitter 클래스를 사용해 create_documents 메소드를 사용해 PHP 소스 코드 문자열에서 문서 리스트를 구하는 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 |
from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain.text_splitter import Language codeString = """ <?php namespace foo; class Hello { public function __construct() { } } function hello() { echo "Hello World!"; } interface Human { public function breath(); } trait Foo { } enum Color { case Red; case Blue; } """ recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter.from_language(language = Language.PHP, chunk_size = 50, chunk_overlap = 0) documentList = recursiveCharacterTextSplitter.create_documents([codeString]) print(documentList) """ [Document(page_content='<?php\nnamespace foo;'), Document(page_content='class Hello {'), Document(page_content='public function __construct() { }\n}'), Document(page_content='function hello() {\n echo "Hello World!";\n}'), Document(page_content='interface Human {\n public function breath();\n}'), Document(page_content='trait Foo { }\nenum Color\n{\n case Red;'), Document(page_content='case Blue;\n}')] """ |
▶ 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 |
aiohttp==3.9.5 aiosignal==1.3.1 annotated-types==0.7.0 async-timeout==4.0.3 attrs==23.2.0 certifi==2024.6.2 charset-normalizer==3.3.2 frozenlist==1.4.1 greenlet==3.0.3 idna==3.7 jsonpatch==1.33 jsonpointer==3.0.0 langchain==0.2.6 langchain-core==0.2.10 langchain-text-splitters==0.2.2 langsmith==0.1.82 multidict==6.0.5 numpy==1.26.4 orjson==3.10.5 packaging==24.1 pydantic==2.7.4 pydantic_core==2.18.4 PyYAML==6.0.1 requests==2.32.3 SQLAlchemy==2.0.31 tenacity==8.4.2 typing_extensions==4.12.2 urllib3==2.2.2 yarl==1.9.4 |
※ pip install langchain langchain-text-splitters 명령을 실행했다.