Files
t6_mem0/embedchain/chunkers/rss_feed.py

23 lines
806 B
Python

from typing import Optional
from langchain.text_splitter import RecursiveCharacterTextSplitter
from embedchain.chunkers.base_chunker import BaseChunker
from embedchain.config.add_config import ChunkerConfig
from embedchain.helpers.json_serializable import register_deserializable
@register_deserializable
class RSSFeedChunker(BaseChunker):
"""Chunker for RSS Feed."""
def __init__(self, config: Optional[ChunkerConfig] = None):
if config is None:
config = ChunkerConfig(chunk_size=2000, chunk_overlap=0, length_function=len)
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=config.chunk_size,
chunk_overlap=config.chunk_overlap,
length_function=config.length_function,
)
super().__init__(text_splitter)