Cant import any of the HuggingFaceEmbeddings because 'openssl' has no attribute 'ciphers'

[suvraadeep]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

from langchain_community.embeddings import HuggingFaceBgeEmbeddings

model_name = "BAAI/bge-small-en"
model_kwargs = {"device": "cpu"}
encode_kwargs = {"normalize_embeddings": True}
hf = HuggingFaceBgeEmbeddings(
    model_name=model_name, model_kwargs=model_kwargs, encode_kwargs=encode_kwargs
)

embedding = hf.embed_query("hi this is harrison")
embedding

or

from langchain_huggingface import HuggingFaceEmbeddings
embeddings=HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")

Error Message and Stack Trace (if applicable)

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
File /opt/conda/lib/python3.10/site-packages/transformers/utils/import_utils.py:1764, in _LazyModule._get_module(self, module_name)
   1763 try:
-> 1764     return importlib.import_module("." + module_name, self.__name__)
   1765 except Exception as e:

File /opt/conda/lib/python3.10/importlib/__init__.py:126, in import_module(name, package)
    125         level += 1
--> 126 return _bootstrap._gcd_import(name[level:], package, level)

File <frozen importlib._bootstrap>:1050, in _gcd_import(name, package, level)

File <frozen importlib._bootstrap>:1027, in _find_and_load(name, import_)

File <frozen importlib._bootstrap>:1006, in _find_and_load_unlocked(name, import_)

File <frozen importlib._bootstrap>:688, in _load_unlocked(spec)

File <frozen importlib._bootstrap_external>:883, in exec_module(self, module)

File <frozen importlib._bootstrap>:241, in _call_with_frames_removed(f, *args, **kwds)

File /opt/conda/lib/python3.10/site-packages/transformers/modeling_tf_utils.py:34
     33 import numpy as np
---> 34 import tensorflow as tf
     35 from packaging.version import parse

File /opt/conda/lib/python3.10/site-packages/tensorflow/__init__.py:45
     43 _tf2.enable()
---> 45 from tensorflow._api.v2 import __internal__
     46 from tensorflow._api.v2 import __operators__

File /opt/conda/lib/python3.10/site-packages/tensorflow/_api/v2/__internal__/__init__.py:11
     10 from tensorflow._api.v2.__internal__ import dispatch
---> 11 from tensorflow._api.v2.__internal__ import distribute
     12 from tensorflow._api.v2.__internal__ import eager_context

File /opt/conda/lib/python3.10/site-packages/tensorflow/_api/v2/__internal__/distribute/__init__.py:8
      6 import sys as _sys
----> 8 from tensorflow._api.v2.__internal__.distribute import combinations
      9 from tensorflow._api.v2.__internal__.distribute import interim

File /opt/conda/lib/python3.10/site-packages/tensorflow/_api/v2/__internal__/distribute/combinations/__init__.py:8
      6 import sys as _sys
----> 8 from tensorflow.python.distribute.combinations import env # line: 456
      9 from tensorflow.python.distribute.combinations import generate # line: 365

File /opt/conda/lib/python3.10/site-packages/tensorflow/python/distribute/combinations.py:33
     32 from tensorflow.python.client import session
---> 33 from tensorflow.python.distribute import collective_all_reduce_strategy
     34 from tensorflow.python.distribute import distribute_lib

File /opt/conda/lib/python3.10/site-packages/tensorflow/python/distribute/collective_all_reduce_strategy.py:32
     31 from tensorflow.python.distribute import input_util
---> 32 from tensorflow.python.distribute import mirrored_strategy
     33 from tensorflow.python.distribute import multi_worker_util

File /opt/conda/lib/python3.10/site-packages/tensorflow/python/distribute/mirrored_strategy.py:34
     33 from tensorflow.python.distribute import values_util
---> 34 from tensorflow.python.distribute.cluster_resolver import tfconfig_cluster_resolver
     35 from tensorflow.python.distribute.v1 import input_lib as input_lib_v1

File /opt/conda/lib/python3.10/site-packages/tensorflow/python/distribute/cluster_resolver/__init__.py:27
     26 from tensorflow.python.distribute.cluster_resolver.cluster_resolver import UnionClusterResolver
---> 27 from tensorflow.python.distribute.cluster_resolver.gce_cluster_resolver import GCEClusterResolver
     28 from tensorflow.python.distribute.cluster_resolver.kubernetes_cluster_resolver import KubernetesClusterResolver

File /opt/conda/lib/python3.10/site-packages/tensorflow/python/distribute/cluster_resolver/gce_cluster_resolver.py:24
     23 try:
---> 24   from googleapiclient import discovery  # pylint: disable=g-import-not-at-top
     25   from oauth2client.client import GoogleCredentials  # pylint: disable=g-import-not-at-top

File /opt/conda/lib/python3.10/site-packages/googleapiclient/discovery.py:45
     44 from google.auth.transport import mtls
---> 45 from google.oauth2 import service_account
     47 # Third-party imports

File /opt/conda/lib/python3.10/site-packages/google/oauth2/service_account.py:77
     76 from google.auth import _helpers
---> 77 from google.auth import _service_account_info
     78 from google.auth import credentials

File /opt/conda/lib/python3.10/site-packages/google/auth/_service_account_info.py:20
     18 import json
---> 20 from google.auth import crypt
     21 from google.auth import exceptions

File /opt/conda/lib/python3.10/site-packages/google/auth/crypt/__init__.py:41
     40 from google.auth.crypt import base
---> 41 from google.auth.crypt import rsa
     43 try:

File /opt/conda/lib/python3.10/site-packages/google/auth/crypt/rsa.py:20
     18 try:
     19     # Prefer cryptograph-based RSA implementation.
---> 20     from google.auth.crypt import _cryptography_rsa
     22     RSASigner = _cryptography_rsa.RSASigner

File /opt/conda/lib/python3.10/site-packages/google/auth/crypt/_cryptography_rsa.py:25
     24 from cryptography.hazmat.primitives import hashes
---> 25 from cryptography.hazmat.primitives import serialization
     26 from cryptography.hazmat.primitives.asymmetric import padding

File /opt/conda/lib/python3.10/site-packages/cryptography/hazmat/primitives/serialization/__init__.py:25
     17 from cryptography.hazmat.primitives.serialization.base import (
     18     load_der_parameters,
     19     load_der_private_key,
   (...)
     23     load_pem_public_key,
     24 )
---> 25 from cryptography.hazmat.primitives.serialization.ssh import (
     26     SSHCertificate,
     27     SSHCertificateBuilder,
     28     SSHCertificateType,
     29     SSHCertPrivateKeyTypes,
     30     SSHCertPublicKeyTypes,
     31     SSHPrivateKeyTypes,
     32     SSHPublicKeyTypes,
     33     load_ssh_private_key,
     34     load_ssh_public_identity,
     35     load_ssh_public_key,
     36 )
     38 __all__ = [
     39     "BestAvailableEncryption",
     40     "Encoding",
   (...)
     62     "load_ssh_public_key",
     63 ]

File /opt/conda/lib/python3.10/site-packages/cryptography/hazmat/primitives/serialization/ssh.py:27
     26 from cryptography.hazmat.primitives.asymmetric import utils as asym_utils
---> 27 from cryptography.hazmat.primitives.ciphers import (
     28     AEADDecryptionContext,
     29     Cipher,
     30     algorithms,
     31     modes,
     32 )
     33 from cryptography.hazmat.primitives.serialization import (
     34     Encoding,
     35     KeySerializationEncryption,
   (...)
     39     _KeySerializationEncryption,
     40 )

File /opt/conda/lib/python3.10/site-packages/cryptography/hazmat/primitives/ciphers/__init__.py:11
      7 from cryptography.hazmat.primitives._cipheralgorithm import (
      8     BlockCipherAlgorithm,
      9     CipherAlgorithm,
     10 )
---> 11 from cryptography.hazmat.primitives.ciphers.base import (
     12     AEADCipherContext,
     13     AEADDecryptionContext,
     14     AEADEncryptionContext,
     15     Cipher,
     16     CipherContext,
     17 )
     19 __all__ = [
     20     "AEADCipherContext",
     21     "AEADDecryptionContext",
   (...)
     26     "CipherContext",
     27 ]

File /opt/conda/lib/python3.10/site-packages/cryptography/hazmat/primitives/ciphers/base.py:143
    133 _CIPHER_TYPE = Cipher[
    134     typing.Union[
    135         modes.ModeWithNonce,
   (...)
    140     ]
    141 ]
--> 143 CipherContext.register(rust_openssl.ciphers.CipherContext)
    144 AEADEncryptionContext.register(rust_openssl.ciphers.AEADEncryptionContext)

AttributeError: module 'openssl' has no attribute 'ciphers'

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

RuntimeError                              Traceback (most recent call last)
File /opt/conda/lib/python3.10/site-packages/transformers/utils/import_utils.py:1764, in _LazyModule._get_module(self, module_name)
   1763 try:
-> 1764     return importlib.import_module("." + module_name, self.__name__)
   1765 except Exception as e:

File /opt/conda/lib/python3.10/importlib/__init__.py:126, in import_module(name, package)
    125         level += 1
--> 126 return _bootstrap._gcd_import(name[level:], package, level)

File <frozen importlib._bootstrap>:1050, in _gcd_import(name, package, level)

File <frozen importlib._bootstrap>:1027, in _find_and_load(name, import_)

File <frozen importlib._bootstrap>:1006, in _find_and_load_unlocked(name, import_)

File <frozen importlib._bootstrap>:688, in _load_unlocked(spec)

File <frozen importlib._bootstrap_external>:883, in exec_module(self, module)

File <frozen importlib._bootstrap>:241, in _call_with_frames_removed(f, *args, **kwds)

File /opt/conda/lib/python3.10/site-packages/transformers/integrations/integration_utils.py:36
     34 import packaging.version
---> 36 from .. import PreTrainedModel, TFPreTrainedModel
     37 from .. import __version__ as version

File <frozen importlib._bootstrap>:1075, in _handle_fromlist(module, fromlist, import_, recursive)

File /opt/conda/lib/python3.10/site-packages/transformers/utils/import_utils.py:1754, in _LazyModule.__getattr__(self, name)
   1753 elif name in self._class_to_module.keys():
-> 1754     module = self._get_module(self._class_to_module[name])
   1755     value = getattr(module, name)

File /opt/conda/lib/python3.10/site-packages/transformers/utils/import_utils.py:1766, in _LazyModule._get_module(self, module_name)
   1765 except Exception as e:
-> 1766     raise RuntimeError(
   1767         f"Failed to import {self.__name__}.{module_name} because of the following error (look up to see its"
   1768         f" traceback):\n{e}"
   1769     ) from e

RuntimeError: Failed to import transformers.modeling_tf_utils because of the following error (look up to see its traceback):
module 'openssl' has no attribute 'ciphers'

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

RuntimeError                              Traceback (most recent call last)
Cell In[5], line 9
      7 model_kwargs = {"device": "cpu"}
      8 encode_kwargs = {"normalize_embeddings": True}
----> 9 hf = HuggingFaceBgeEmbeddings(
     10     model_name=model_name, model_kwargs=model_kwargs, encode_kwargs=encode_kwargs
     11 )
     13 embedding = hf.embed_query("hi this is harrison")
     14 embedding

File /opt/conda/lib/python3.10/site-packages/langchain_community/embeddings/huggingface.py:320, in HuggingFaceBgeEmbeddings.__init__(self, **kwargs)
    310     warn_deprecated(
    311         since=since,
    312         removal=removal,
   (...)
    316         + f" {self.__class__.__name__} constructor instead.",
    317     )
    319 try:
--> 320     import sentence_transformers
    322 except ImportError as exc:
    323     raise ImportError(
    324         "Could not import sentence_transformers python package. "
    325         "Please install it with `pip install sentence_transformers`."
    326     ) from exc

File /opt/conda/lib/python3.10/site-packages/sentence_transformers/__init__.py:10
      7 import os
      9 from sentence_transformers.backend import export_dynamic_quantized_onnx_model, export_optimized_onnx_model
---> 10 from sentence_transformers.cross_encoder.CrossEncoder import CrossEncoder
     11 from sentence_transformers.datasets import ParallelSentencesDataset, SentencesDataset
     12 from sentence_transformers.LoggingHandler import LoggingHandler

File /opt/conda/lib/python3.10/site-packages/sentence_transformers/cross_encoder/__init__.py:3
      1 from __future__ import annotations
----> 3 from .CrossEncoder import CrossEncoder
      5 __all__ = ["CrossEncoder"]

File /opt/conda/lib/python3.10/site-packages/sentence_transformers/cross_encoder/CrossEncoder.py:20
     18 from sentence_transformers.evaluation.SentenceEvaluator import SentenceEvaluator
     19 from sentence_transformers.readers import InputExample
---> 20 from sentence_transformers.SentenceTransformer import SentenceTransformer
     21 from sentence_transformers.util import fullname, get_device_name, import_from_string
     23 logger = logging.getLogger(__name__)

File /opt/conda/lib/python3.10/site-packages/sentence_transformers/SentenceTransformer.py:32
     29 from transformers import is_torch_npu_available
     30 from transformers.dynamic_module_utils import get_class_from_dynamic_module, get_relative_import_files
---> 32 from sentence_transformers.model_card import SentenceTransformerModelCardData, generate_model_card
     33 from sentence_transformers.similarity_functions import SimilarityFunction
     35 from . import __MODEL_HUB_ORGANIZATION__, __version__

File /opt/conda/lib/python3.10/site-packages/sentence_transformers/model_card.py:25
     23 from tqdm.autonotebook import tqdm
     24 from transformers import TrainerCallback
---> 25 from transformers.integrations import CodeCarbonCallback
     26 from transformers.modelcard import make_markdown_table
     27 from transformers.trainer_callback import TrainerControl, TrainerState

File <frozen importlib._bootstrap>:1075, in _handle_fromlist(module, fromlist, import_, recursive)

File /opt/conda/lib/python3.10/site-packages/transformers/utils/import_utils.py:1754, in _LazyModule.__getattr__(self, name)
   1752     value = Placeholder
   1753 elif name in self._class_to_module.keys():
-> 1754     module = self._get_module(self._class_to_module[name])
   1755     value = getattr(module, name)
   1756 else:

File /opt/conda/lib/python3.10/site-packages/transformers/utils/import_utils.py:1766, in _LazyModule._get_module(self, module_name)
   1764     return importlib.import_module("." + module_name, self.__name__)
   1765 except Exception as e:
-> 1766     raise RuntimeError(
   1767         f"Failed to import {self.__name__}.{module_name} because of the following error (look up to see its"
   1768         f" traceback):\n{e}"
   1769     ) from e

RuntimeError: Failed to import transformers.integrations.integration_utils because of the following error (look up to see its traceback):
Failed to import transformers.modeling_tf_utils because of the following error (look up to see its traceback):
module 'openssl' has no attribute 'ciphers'

Failed to import transformers.integrations.integration_utils because of the following error (look up to see its traceback): Failed to import transformers.modeling_tf_utils because of the following error (look up to see its traceback): module 'openssl' has no attribute 'ciphers'

Description

I cant import HuggingFaceBgeEmbeddings and huggingfaceembeddings for any of the available models

System Info

System Information

OS: Linux
OS Version: #1 SMP Thu Jun 27 20:43:36 UTC 2024
Python Version: 3.10.14 | packaged by conda-forge | (main, Mar 20 2024, 12:45:18) [GCC 12.3.0]

Package Information

langchain_core: 0.3.12
langchain: 0.3.4
langchain_community: 0.3.3
langsmith: 0.1.137
langchain_cohere: 0.3.1
langchain_experimental: 0.3.2
langchain_groq: 0.2.0
langchain_openai: 0.2.3
langchain_text_splitters: 0.3.0

Optional packages not installed

langgraph
langserve

Other Dependencies

aiohttp: 3.9.5
async-timeout: 4.0.3
cohere: 5.11.1
dataclasses-json: 0.6.7
groq: 0.11.0
httpx: 0.27.0
jsonpatch: 1.33
numpy: 1.26.4
openai: 1.52.2
orjson: 3.10.4
packaging: 24.1
pandas: 2.2.3
pydantic: 2.9.2
pydantic-settings: 2.6.0
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.36
tabulate: 0.9.0
tenacity: 9.0.0
tiktoken: 0.7.0
typing-extensions: 4.12.2

[giuliaguglielmi123]

I've been trying to replicate your error without success, I can indeed correctly extract the vector embedding without error. However I noticed that you have python 3.10 whereas mine is 3.12.3 version.

Besides, why it tries to import transformers ? When I tried to replicate the issue it instead used sentence_transformers, did you install it ?