File size: 374 Bytes
2e818da
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
from typing import List
from langchain_text_splitters import RecursiveCharacterTextSplitter


def chunk_text(text: str, chunk_size: int = 512, overlap: int = 64) -> List[str]:
    splitter = RecursiveCharacterTextSplitter(
        chunk_size=chunk_size,
        chunk_overlap=overlap,
        separators=["\n\n", "\n", ". ", " "],
    )
    return splitter.split_text(text)