[Bug]:

### Installation Method | 安装方法与平台

Others (Please Describe)

### Version | 版本

Latest | 最新版

### OS | 操作系统

Linux

### Describe the bug | 简述

**[Local Message] 从一批文件(txt, md, tex)中读取数据构建知识库, 然后进行问答。**

**[Local Message] 插件调用出错**:
Traceback (most recent call last):
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/utils/import_utils.py", line 1863, in _get_module
return importlib.import_module("." + module_name, self.__name__)
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/importlib/__init__.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1030, in _gcd_import
File "", line 1007, in _find_and_load
File "", line 986, in _find_and_load_unlocked
File "", line 680, in _load_unlocked
File "", line 850, in exec_module
File "", line 228, in _call_with_frames_removed
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/modeling_utils.py", line 53, in
from .loss.loss_utils import LOSS_MAPPING
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/loss/loss_utils.py", line 19, in
from .loss_deformable_detr import DeformableDetrForObjectDetectionLoss, DeformableDetrForSegmentationLoss
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/loss/loss_deformable_detr.py", line 4, in
from ..image_transforms import center_to_corners_format
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/image_transforms.py", line 22, in
from .image_utils import (
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/image_utils.py", line 65, in
from torchvision import io as torchvision_io
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/torchvision/__init__.py", line 10, in
from torchvision import _meta_registrations, datasets, io, models, ops, transforms, utils # usort:skip
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/torchvision/_meta_registrations.py", line 26, in
def meta_roi_align(input, rois, spatial_scale, pooled_height, pooled_width, sampling_ratio, aligned):
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/torchvision/_meta_registrations.py", line 18, in wrapper
if torchvision.extension._has_ops():
AttributeError: partially initialized module 'torchvision' has no attribute 'extension' (most likely due to a circular import)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/utils/import_utils.py", line 1863, in _get_module
return importlib.import_module("." + module_name, self.__name__)
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/importlib/__init__.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1030, in _gcd_import
File "", line 1007, in _find_and_load
File "", line 986, in _find_and_load_unlocked
File "", line 680, in _load_unlocked
File "", line 850, in exec_module
File "", line 228, in _call_with_frames_removed
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/integrations/integration_utils.py", line 36, in
from .. import PreTrainedModel, TFPreTrainedModel
File "", line 1055, in _handle_fromlist
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/utils/import_utils.py", line 1851, in __getattr__
module = self._get_module(self._class_to_module[name])
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/utils/import_utils.py", line 1865, in _get_module
raise RuntimeError(
RuntimeError: Failed to import transformers.modeling_utils because of the following error (look up to see its traceback):
partially initialized module 'torchvision' has no attribute 'extension' (most likely due to a circular import)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "./toolbox.py", line 229, in decorated
yield from f(main_input, llm_kwargs, plugin_kwargs, chatbot_with_cookie, history, *args, **kwargs)
File "./crazy_functions/知识库问答.py", line 66, in 知识库文件注入
HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/langchain_core/_api/deprecation.py", line 214, in warn_if_direct_instance
return wrapped(self, *args, **kwargs)
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/langchain_community/embeddings/huggingface.py", line 84, in __init__
import sentence_transformers
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/sentence_transformers/__init__.py", line 14, in
from sentence_transformers.cross_encoder.CrossEncoder import CrossEncoder
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/sentence_transformers/cross_encoder/__init__.py", line 3, in
from .CrossEncoder import CrossEncoder
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/sentence_transformers/cross_encoder/CrossEncoder.py", line 20, in
from sentence_transformers.SentenceTransformer import SentenceTransformer
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/sentence_transformers/SentenceTransformer.py", line 33, in
from sentence_transformers.model_card import SentenceTransformerModelCardData, generate_model_card
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/sentence_transformers/model_card.py", line 25, in
from transformers.integrations import CodeCarbonCallback
File "", line 1055, in _handle_fromlist
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/utils/import_utils.py", line 1851, in __getattr__
module = self._get_module(self._class_to_module[name])
File "/www/server/pyporject_evn/gpt_academic_venv/lib/python3.9/site-packages/transformers/utils/import_utils.py", line 1865, in _get_module
raise RuntimeError(
RuntimeError: Failed to import transformers.integrations.integration_utils because of the following error (look up to see its traceback):
Failed to import transformers.modeling_utils because of the following error (look up to see its traceback):
partially initialized module 'torchvision' has no attribute 'extension' (most likely due to a circular import)

如何处理

### Screen Shot | 有帮助的截图

当我上传一个测试txt进行构建知识库，出现上面的错误，我也重新安装相关依赖，仍有问题

### 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 with crazy_functions/知识库问答.py at line 66, where HuggingFaceEmbeddings is initialized, and inspect the import chain through sentence_transformers, transformers, and torchvision shown in the traceback. Reproduce with the reported text-file knowledge-base workflow and compare the installed dependency versions; done means the knowledge base is built without the reported import error.

Written by the indexing model from the issue text.