From 45fbcafbf68c31da751a606b6ec4799ee69551e0 Mon Sep 17 00:00:00 2001
From: aries_ckt <916701291@qq.com>
Date: Mon, 24 Jul 2023 17:37:21 +0800
Subject: [PATCH] fix:word embedding update 1.use Docx2txtLoader replace
 UnstructuredWordDocumentLoader

---
 pilot/embedding_engine/word_embedding.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pilot/embedding_engine/word_embedding.py b/pilot/embedding_engine/word_embedding.py
index 24f1d0386..55a2b5079 100644
--- a/pilot/embedding_engine/word_embedding.py
+++ b/pilot/embedding_engine/word_embedding.py
@@ -2,8 +2,8 @@
 # -*- coding: utf-8 -*-
 from typing import List, Optional
 
-from langchain.document_loaders import UnstructuredWordDocumentLoader
 from langchain.schema import Document
+from langchain.document_loaders import Docx2txtLoader
 from langchain.text_splitter import (
     SpacyTextSplitter,
     RecursiveCharacterTextSplitter,
@@ -36,7 +36,7 @@ class WordEmbedding(SourceEmbedding):
     def read(self):
         """Load from word path."""
         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:
             try:
                 self.text_splitter = SpacyTextSplitter(