I'm trying to do the following simple code:
from langchain.schema import HumanMessage, SystemMessage
from langchain_openai import ChatOpenAI
1] If I use it just after installing langchain
and langchain_openai
I get the following error:
- ERROR:
TypeError: issubclass() arg 1 must be a class
- LINE:
from langchain.schema import HumanMessage, SystemMessage
2] I found multiple answers online that are similar to this: import langchain => Error : TypeError: issubclass() arg 1 must be a class but when I add to my cluster the following installations:
typing-inspect==0.8.0
typing_extensions==4.5.0
Then I get the following:
- ERROR:
ImportError: cannot import name 'Iterator' from 'typing_extensions' (/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/typing_extensions.py)
- LINE:
from langchain_openai import ChatOpenAI
I'm using Databricks with the following:
- Cluster 1:
- Runtime: 13.2 ML (includes Apache Spark 3.4.0, GPU, Scala 2.12)
- Worker & Driver type: Standard_NC21s_v3 224 GB Memory, 2 GPUs
- Cluster 2:
- Runtime: 12.2 LTS ML (includes Apache Spark 3.3.2, Scala 2.12)
- Node type: Standard_DS5_v2 56 GB Memory, 16 Cores
pip install -r requirement.txt
requirement.txt, when i tried with these, i received no error(on mac).