[Feature] Discourse Loader (#948)

Co-authored-by: Deven Patel <deven298@yahoo.com>
This commit is contained in:
Deven Patel
2023-11-13 16:39:11 -08:00
committed by GitHub
parent 919cc74e94
commit 95c0d47236
12 changed files with 324 additions and 4 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 DiscourseChunker(BaseChunker):
"""Chunker for discourse."""
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)