feat: add google doc support added (#155)

This commit is contained in:
Sahil Kumar Yadav
2023-07-06 14:04:27 +05:30
committed by GitHub
parent c6dbbf5dd3
commit 68e732a426
5 changed files with 70 additions and 27 deletions

View File

@@ -0,0 +1,16 @@
from embedchain.chunkers.base_chunker import BaseChunker
from langchain.text_splitter import RecursiveCharacterTextSplitter
TEXT_SPLITTER_CHUNK_PARAMS = {
"chunk_size": 500,
"chunk_overlap": 0,
"length_function": len,
}
class DocFileChunker(BaseChunker):
def __init__(self):
text_splitter = RecursiveCharacterTextSplitter(**TEXT_SPLITTER_CHUNK_PARAMS)
super().__init__(text_splitter)