[Bug]: 构建知识库，知识库文件注入 长时间未响应

### Installation Method | 安装方法与平台

Pip Install (I used latest requirements.txt)

### Version | 版本

Latest | 最新版

### OS | 操作系统

Windows

### Describe the bug | 简述

上传了一个pdf，然后选择“构建知识库（先上传文件，再运行此插件）”，运行插件后，控制台出现如下输出：
```
>> from langchain_community.embeddings import HuggingFaceEmbeddings
You can use the langchain cli to **automatically** upgrade many imports. Please see documentation here
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
14:27 | 知识库文件注入 :63 | Checking Text2vec ...
No sentence-transformers model found with name GanymedeNil/text2vec-large-chinese. Creating a new one with mean pooling.
```

### Screen Shot | 有帮助的截图

控制台截图如下：

gui截图如下：

### Terminal Traceback & Material to Help Reproduce Bugs | 终端traceback（如有） + 帮助我们复现的测试材料样本（如有）

_No response_

Start by reproducing the Windows workflow: upload a PDF, choose “构建知识库,” and run the plugin while watching the console around “Checking Text2vec ...”. Investigate the HuggingFaceEmbeddings model-loading step and determine whether the knowledge-base injection completes; done means the plugin finishes instead of remaining unresponsive.

Written by the indexing model from the issue text.