[Feature]: Unstructured File Loader Support - USF (#815)
This commit is contained in:
committed by
GitHub
parent
c8846e0e93
commit
8b64deab40
22
embedchain/chunkers/unstructured_file.py
Normal file
22
embedchain/chunkers/unstructured_file.py
Normal 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 UnstructuredFileChunker(BaseChunker):
|
||||
"""Chunker for Unstructured 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)
|
||||
Reference in New Issue
Block a user