github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-08-18 08:17:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix:word embedding update

Browse Source 
1.use Docx2txtLoader replace UnstructuredWordDocumentLoader
This commit is contained in:
aries_ckt 2023-07-24 17:37:21 +08:00
parent dbf8b20c0b
commit 45fbcafbf6
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
pilot/embedding_engine/word_embedding.py
View File

@ -2,8 +2,8 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from typing import List, Optional from typing import List, Optional
from langchain.document_loaders import UnstructuredWordDocumentLoader
from langchain.schema import Document from langchain.schema import Document
from langchain.document_loaders import Docx2txtLoader
from langchain.text_splitter import ( from langchain.text_splitter import (
SpacyTextSplitter, SpacyTextSplitter,
RecursiveCharacterTextSplitter, RecursiveCharacterTextSplitter,
@ -36,7 +36,7 @@ class WordEmbedding(SourceEmbedding):
def read(self): def read(self):
"""Load from word path.""" """Load from word path."""
if self.source_reader is None: if self.source_reader is None:
self.source_reader = UnstructuredWordDocumentLoader(self.file_path) self.source_reader = Docx2txtLoader(self.file_path)
if self.text_splitter is None: if self.text_splitter is None:
try: try:
self.text_splitter = SpacyTextSplitter( self.text_splitter = SpacyTextSplitter(