Failed to import transformers.models.bert.modeling_bert

[cibernicola]

Describe the bug and how to reproduce it Error in initiating intake. Install requirements and start with python ingest.py log:

`Loading documents from source_documents Loaded 1 documents from source_documents Split into 90 chunks of text (max. 500 characters each) Traceback (most recent call last): File "C:\Python310\lib\site-packages\transformers\utils\import_utils.py", line 1126, in get_module return importlib.import_module("." + module_name, self.name) File "C:\Python310\lib\importlib_init.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "", line 1050, in _gcd_import File "", line 1027, in _find_and_load File "", line 1006, in _find_and_load_unlocked File "", line 688, in load_unlocked File "", line 883, in exec_module File "", line 241, in call_with_frames_removed File "C:\Python310\lib\site-packages\transformers\models\bert\modeling_bert.py", line 42, in from ...modeling_utils import PreTrainedModel File "C:\Python310\lib\site-packages\transformers\modeling_utils.py", line 83, in from accelerate import version as accelerate_version File "C:\Python310\lib\site-packages\accelerate_init.py", line 3, in from .accelerator import Accelerator File "C:\Python310\lib\site-packages\accelerate\accelerator.py", line 37, in from .tracking import LOGGER_TYPE_TO_CLASS, GeneralTracker, filter_trackers File "C:\Python310\lib\site-packages\accelerate\tracking.py", line 42, in from torch.utils import tensorboard File "C:\Python310\lib\site-packages\torch\utils\tensorboard_init.py", line 7, in raise ImportError("TensorBoard logging requires TensorBoard version 1.15 or above") ImportError: TensorBoard logging requires TensorBoard version 1.15 or above

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

Traceback (most recent call last): File "J:\gpt\privateGPT\ingest.py", line 97, in main() File "J:\gpt\privateGPT\ingest.py", line 88, in main embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name) File "C:\Python310\lib\site-packages\langchain\embeddings\huggingface.py", line 54, in init self.client = sentence_transformers.SentenceTransformer( File "C:\Python310\lib\site-packages\sentence_transformers\SentenceTransformer.py", line 95, in init modules = self._load_sbert_model(model_path) File "C:\Python310\lib\site-packages\sentence_transformers\SentenceTransformer.py", line 840, in _load_sbert_model module = module_class.load(os.path.join(model_path, module_config['path'])) File "C:\Python310\lib\site-packages\sentence_transformers\models\Transformer.py", line 137, in load return Transformer(model_name_or_path=input_path, **config) File "C:\Python310\lib\site-packages\sentence_transformers\models\Transformer.py", line 29, in init self._load_model(model_name_or_path, config, cache_dir) File "C:\Python310\lib\site-packages\sentence_transformers\models\Transformer.py", line 49, in _load_model self.auto_model = AutoModel.from_pretrained(model_name_or_path, config=config, cache_dir=cache_dir) File "C:\Python310\lib\site-packages\transformers\models\auto\auto_factory.py", line 470, in from_pretrained model_class = _get_model_class(config, cls._model_mapping) File "C:\Python310\lib\site-packages\transformers\models\auto\auto_factory.py", line 360, in _get_model_class supported_models = model_mapping[type(config)] File "C:\Python310\lib\site-packages\transformers\models\auto\auto_factory.py", line 602, in getitem return self._load_attr_from_module(model_type, model_name) File "C:\Python310\lib\site-packages\transformers\models\auto\auto_factory.py", line 616, in _load_attr_from_module return getattribute_from_module(self._modules[module_name], attr) File "C:\Python310\lib\site-packages\transformers\models\auto\auto_factory.py", line 561, in getattribute_from_module if hasattr(module, attr): File "C:\Python310\lib\site-packages\transformers\utils\import_utils.py", line 1116, in getattr module = self._get_module(self._class_to_module[name]) File "C:\Python310\lib\site-packages\transformers\utils\import_utils.py", line 1128, in _get_module raise RuntimeError( RuntimeError: Failed to import transformers.models.bert.modeling_bert because of the following error (look up to see its traceback): TensorBoard logging requires TensorBoard version 1.15 or above`

Expected behavior Document intake for further processing.

Environment (please complete the following information):

• OS / hardware: Win10Pro / 3090
• Python version :3.10
• Other relevant information

Additional context Add any other context about the problem here.

[maozdemir]

ImportError: TensorBoard logging requires TensorBoard version 1.15 or above

can you run pip3 install tensorboard or make sure that your installed version is higher than 1.15?

[cibernicola]

`J:\gpt\privateGPT>pip3 install tensorboard Requirement already satisfied: tensorboard in c:\python310\lib\site-packages (2.12.1) Requirement already satisfied: absl-py>=0.4 in c:\python310\lib\site-packages (from tensorboard) (1.2.0) Requirement already satisfied: grpcio>=1.48.2 in c:\python310\lib\site-packages (from tensorboard) (1.49.1) Requirement already satisfied: google-auth<3,>=1.6.3 in c:\python310\lib\site-packages (from tensorboard) (2.17.2) Requirement already satisfied: google-auth-oauthlib<1.1,>=0.5 in c:\python310\lib\site-packages (from tensorboard) (1.0.0) Requirement already satisfied: markdown>=2.6.8 in c:\python310\lib\site-packages (from tensorboard) (3.4.3) Requirement already satisfied: numpy>=1.12.0 in c:\python310\lib\site-packages (from tensorboard) (1.23.5) Requirement already satisfied: protobuf>=3.19.6 in c:\python310\lib\site-packages (from tensorboard) (3.20.3) Requirement already satisfied: requests<3,>=2.21.0 in c:\python310\lib\site-packages (from tensorboard) (2.28.2) Requirement already satisfied: setuptools>=41.0.0 in c:\python310\lib\site-packages (from tensorboard) (59.8.0) Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in c:\python310\lib\site-packages (from tensorboard) (0.7.0) Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in c:\python310\lib\site-packages (from tensorboard) (1.8.1) Requirement already satisfied: werkzeug>=1.0.1 in c:\python310\lib\site-packages (from tensorboard) (1.0.1) Requirement already satisfied: wheel>=0.26 in c:\python310\lib\site-packages (from tensorboard) (0.37.1) Requirement already satisfied: cachetools<6.0,>=2.0.0 in c:\python310\lib\site-packages (from google-auth<3,>=1.6.3->tensorboard) (5.2.0) Requirement already satisfied: pyasn1-modules>=0.2.1 in c:\python310\lib\site-packages (from google-auth<3,>=1.6.3->tensorboard) (0.2.8) Requirement already satisfied: six>=1.9.0 in c:\python310\lib\site-packages (from google-auth<3,>=1.6.3->tensorboard) (1.16.0) Requirement already satisfied: rsa<5,>=3.1.4 in c:\python310\lib\site-packages (from google-auth<3,>=1.6.3->tensorboard) (4.9) Requirement already satisfied: requests-oauthlib>=0.7.0 in c:\python310\lib\site-packages (from google-auth-oauthlib<1.1,>=0.5->tensorboard) (1.3.1) Requirement already satisfied: charset-normalizer<4,>=2 in c:\python310\lib\site-packages (from requests<3,>=2.21.0->tensorboard) (2.1.1) Requirement already satisfied: idna<4,>=2.5 in c:\python310\lib\site-packages (from requests<3,>=2.21.0->tensorboard) (2.10) Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\python310\lib\site-packages (from requests<3,>=2.21.0->tensorboard) (1.26.6) Requirement already satisfied: certifi>=2017.4.17 in c:\python310\lib\site-packages (from requests<3,>=2.21.0->tensorboard) (2023.5.7) Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in c:\python310\lib\site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard) (0.4.8) Requirement already satisfied: oauthlib>=3.0.0 in c:\python310\lib\site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<1.1,>=0.5->tensorboard) (3.2.1)

J:\gpt\privateGPT>python ingest.py Loading documents from source_documents Loaded 1 documents from source_documents Split into 90 chunks of text (max. 500 characters each) Traceback (most recent call last): File "C:\Python310\lib\site-packages\transformers\utils\import_utils.py", line 1126, in get_module return importlib.import_module("." + module_name, self.name) File "C:\Python310\lib\importlib_init.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "", line 1050, in _gcd_import File "", line 1027, in _find_and_load File "", line 1006, in _find_and_load_unlocked File "", line 688, in load_unlocked File "", line 883, in exec_module File "", line 241, in call_with_frames_removed File "C:\Python310\lib\site-packages\transformers\models\bert\modeling_bert.py", line 42, in from ...modeling_utils import PreTrainedModel File "C:\Python310\lib\site-packages\transformers\modeling_utils.py", line 83, in from accelerate import version as accelerate_version File "C:\Python310\lib\site-packages\accelerate_init.py", line 3, in from .accelerator import Accelerator File "C:\Python310\lib\site-packages\accelerate\accelerator.py", line 37, in from .tracking import LOGGER_TYPE_TO_CLASS, GeneralTracker, filter_trackers File "C:\Python310\lib\site-packages\accelerate\tracking.py", line 42, in from torch.utils import tensorboard File "C:\Python310\lib\site-packages\torch\utils\tensorboard_init.py", line 7, in raise ImportError("TensorBoard logging requires TensorBoard version 1.15 or above") ImportError: TensorBoard logging requires TensorBoard version 1.15 or above

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

Traceback (most recent call last): File "J:\gpt\privateGPT\ingest.py", line 97, in main() File "J:\gpt\privateGPT\ingest.py", line 88, in main embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name) File "C:\Python310\lib\site-packages\langchain\embeddings\huggingface.py", line 54, in init self.client = sentence_transformers.SentenceTransformer( File "C:\Python310\lib\site-packages\sentence_transformers\SentenceTransformer.py", line 95, in init modules = self._load_sbert_model(model_path) File "C:\Python310\lib\site-packages\sentence_transformers\SentenceTransformer.py", line 840, in _load_sbert_model module = module_class.load(os.path.join(model_path, module_config['path'])) File "C:\Python310\lib\site-packages\sentence_transformers\models\Transformer.py", line 137, in load return Transformer(model_name_or_path=input_path, **config) File "C:\Python310\lib\site-packages\sentence_transformers\models\Transformer.py", line 29, in init self._load_model(model_name_or_path, config, cache_dir) File "C:\Python310\lib\site-packages\sentence_transformers\models\Transformer.py", line 49, in _load_model self.auto_model = AutoModel.from_pretrained(model_name_or_path, config=config, cache_dir=cache_dir) File "C:\Python310\lib\site-packages\transformers\models\auto\auto_factory.py", line 470, in from_pretrained model_class = _get_model_class(config, cls._model_mapping) File "C:\Python310\lib\site-packages\transformers\models\auto\auto_factory.py", line 360, in _get_model_class supported_models = model_mapping[type(config)] File "C:\Python310\lib\site-packages\transformers\models\auto\auto_factory.py", line 602, in getitem return self._load_attr_from_module(model_type, model_name) File "C:\Python310\lib\site-packages\transformers\models\auto\auto_factory.py", line 616, in _load_attr_from_module return getattribute_from_module(self._modules[module_name], attr) File "C:\Python310\lib\site-packages\transformers\models\auto\auto_factory.py", line 561, in getattribute_from_module if hasattr(module, attr): File "C:\Python310\lib\site-packages\transformers\utils\import_utils.py", line 1116, in getattr module = self._get_module(self._class_to_module[name]) File "C:\Python310\lib\site-packages\transformers\utils\import_utils.py", line 1128, in _get_module raise RuntimeError( RuntimeError: Failed to import transformers.models.bert.modeling_bert because of the following error (look up to see its traceback): TensorBoard logging requires TensorBoard version 1.15 or above`

[MadTinker]

I'm having a similar issue importing sentence_transformers, despite having installed it with pip already

Traceback (most recent call last): File "/home/dan/lab/ai/privateGPT/ingest.py", line 97, in <module> main() File "/home/dan/lab/ai/privateGPT/ingest.py", line 88, in main embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name) File "/home/dan/.local/lib/python3.10/site-packages/langchain/embeddings/huggingface.py", line 49, in __init__ raise ValueError( ValueError: Could not import sentence_transformers python package. Please install it with pip install sentence_transformers.

[MadTinker]

Seemlying also related:

➜ privateGPT pip uninstall scipy Found existing installation: scipy 1.3.3 Not uninstalling scipy at /usr/lib/python3/dist-packages, outside environment /usr Can't uninstall 'scipy'. No files were found to uninstall. ➜ privateGPT pip install scipy
Requirement already satisfied: scipy in /usr/lib/python3/dist-packages (1.3.3)

[MadTinker]

I fixed my problems by completely reinstalling into a new venv. ingest worked!

[Jeaudoir]

Yea boiii! Creating a new venv solved the issue for me as well. (Of course now I have another 1.4 GB of duplicated libraries filling up my hard drive ... oh well 😅)

[cibernicola]

same here,