Files
t6_mem0/embedchain/chunkers/pdf_file.py
cachho 0d4ad07d7b Feat/serialize deserialize (#508)
Co-authored-by: Taranjeet Singh <reachtotj@gmail.com>
2023-09-04 01:20:18 +05:30

23 lines
812 B
Python

from typing import Optional
from langchain.text_splitter import RecursiveCharacterTextSplitter
from embedchain.chunkers.base_chunker import BaseChunker
from embedchain.config.AddConfig import ChunkerConfig
from embedchain.helper_classes.json_serializable import register_deserializable
@register_deserializable
class PdfFileChunker(BaseChunker):
"""Chunker for PDF file."""
def __init__(self, config: Optional[ChunkerConfig] = None):
if config is None:
config = ChunkerConfig(chunk_size=1000, 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)