Files
t6_mem0/embedchain/chunkers/web_page.py
2023-07-11 08:31:42 +05:30

22 lines
632 B
Python

from typing import Optional
from embedchain.chunkers.base_chunker import BaseChunker
from embedchain.config.AddConfig import ChunkerConfig
from langchain.text_splitter import RecursiveCharacterTextSplitter
TEXT_SPLITTER_CHUNK_PARAMS = {
"chunk_size": 500,
"chunk_overlap": 0,
"length_function": len,
}
class WebPageChunker(BaseChunker):
''' Chunker for web page. '''
def __init__(self, config: Optional[ChunkerConfig] = None):
if config is None:
config = TEXT_SPLITTER_CHUNK_PARAMS
text_splitter = RecursiveCharacterTextSplitter(**config)
super().__init__(text_splitter)