langchain: AttributeError: module 'langchain' has no attribute 'verbose'
System Info
langchain==0.0.157
Who can help?
No response
Information
- The official example notebooks/scripts
- My own modified scripts
Related Components
- LLMs/Chat Models
- Embedding Models
- Prompts / Prompt Templates / Prompt Selectors
- Output Parsers
- Document Loaders
- Vector Stores / Retrievers
- Memory
- Agents / Agent Executors
- Tools / Toolkits
- Chains
- Callbacks/Tracing
- Async
Reproduction
When I try to run llm = OpenAI(temperature=0)
AttributeError Traceback (most recent call last)
Cell In[11], line 1
----> 1 llm = OpenAI(temperature=0)
3 # Initialize a ConversationBufferMemory object to store the chat history
4 memory = ConversationBufferMemory(memory_key="chat_history")
File ~/anaconda3/envs/python3/lib/python3.10/site-packages/pydantic/main.py:339, in pydantic.main.BaseModel.__init__()
File ~/anaconda3/envs/python3/lib/python3.10/site-packages/pydantic/main.py:1066, in pydantic.main.validate_model()
File ~/anaconda3/envs/python3/lib/python3.10/site-packages/pydantic/fields.py:439, in pydantic.fields.ModelField.get_default()
File ~/anaconda3/envs/python3/lib/python3.10/site-packages/langchain/llms/base.py:26, in _get_verbosity()
25 def _get_verbosity() -> bool:
---> 26 return langchain.verbose
AttributeError: module 'langchain' has no attribute 'verbose'
Expected behavior
Don’t get the error
About this issue
- Original URL
- State: closed
- Created a year ago
- Reactions: 6
- Comments: 18
This issue seems to have resurfaced in version 0.0.234 of langchain. The suggested solution in the issue works only temporarily, meaning the issue popped up after some time again.
Some kind of race condition bug?
Seems to be fixable by explicitly
before trying to initialize llm.
I also faced this issue. In my case it was my folder structure messing with the imports. I had a folder called
langchainwithin my project. After I renamed it it worked fine.Just in case someone gets this error now, the only thing that worked for me was updating langchain’s version. In my case I’m using poetry as my package manager and did:
poetry update langchainIf you’re using pip just use:
pip install --upgrade langchainI tried using the
langchain.verbose = Falseworkaround that was mentioned here but it ended up triggering the same error later.