Source code for langchain_text_splitters.konlpy
from __future__ import annotations
from typing import Any, List
from langchain_text_splitters.base import TextSplitter
[docs]class KonlpyTextSplitter(TextSplitter):
"""δ½Ώη¨Konlpyε
ζ₯εε²ζζ¬γ
ιη¨δΊεε²ι©ζζζ¬γ
"""
[docs] def __init__(
self,
separator: str = "\n\n",
**kwargs: Any,
) -> None:
"""εε§εKonlpyζζ¬εε²ε¨γ"""
super().__init__(**kwargs)
self._separator = separator
try:
from konlpy.tag import Kkma
except ImportError:
raise ImportError(
"""
Konlpy is not installed, please install it with
`pip install konlpy`
"""
)
self.kkma = Kkma()
[docs] def split_text(self, text: str) -> List[str]:
"""εε²δΌ ε
₯ηζζ¬εΉΆθΏεεεγ"""
splits = self.kkma.sentences(text)
return self._merge_splits(splits, self._separator)