[Feature] Google Drive Folder support as a data source (#1106)

This commit is contained in:
Joe Sleiman
2024-01-05 08:16:01 +02:00
committed by GitHub
parent 38ad57a22c
commit b4ec14382b
10 changed files with 185 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.helpers.json_serializable import register_deserializable
@register_deserializable
class GoogleDriveChunker(BaseChunker):
"""Chunker for google drive folder."""
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)