[feat]: Add support for XML file format (#757)

This commit is contained in:
Ojuswi Rastogi
2023-10-07 04:09:32 +05:30
committed by GitHub
parent d2fd3ce434
commit 540a0a3685
8 changed files with 135 additions and 2 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 XmlChunker(BaseChunker):
"""Chunker for XML files."""
def __init__(self, config: Optional[ChunkerConfig] = None):
if config is None:
config = ChunkerConfig(chunk_size=500, chunk_overlap=50, 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)