[fix]: Fix sitemap loader (#753)

This commit is contained in:
Richard Awoyemi
2023-10-07 00:24:15 +01:00
committed by GitHub
parent 540a0a3685
commit 1741d3bef6
4 changed files with 34 additions and 3 deletions

View File

@@ -0,0 +1,22 @@
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.helper.json_serializable import register_deserializable
@register_deserializable
class SitemapChunker(BaseChunker):
"""Chunker for sitemap."""
def __init__(self, config: Optional[ChunkerConfig] = None):
if config is None:
config = ChunkerConfig(chunk_size=500, 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)