@root_validator error

[brainer3220]

System Info

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/local/lib/python3.8/dist-packages/langchain/__init__.py", line 8, in <module>
    from langchain.agents import MRKLChain, ReActChain, SelfAskWithSearchChain
  File "/usr/local/lib/python3.8/dist-packages/langchain/agents/__init__.py", line 2, in <module>
    from langchain.agents.agent import Agent
  File "/usr/local/lib/python3.8/dist-packages/langchain/agents/agent.py", line 10, in <module>
    from langchain.chains.base import Chain
  File "/usr/local/lib/python3.8/dist-packages/langchain/chains/__init__.py", line 2, in <module>
    from langchain.chains.conversation.base import ConversationChain
  File "/usr/local/lib/python3.8/dist-packages/langchain/chains/conversation/base.py", line 7, in <module>
    from langchain.chains.conversation.memory import ConversationBufferMemory
  File "/usr/local/lib/python3.8/dist-packages/langchain/chains/conversation/memory.py", line 7, in <module>
    from langchain.chains.conversation.prompt import SUMMARY_PROMPT
  File "/usr/local/lib/python3.8/dist-packages/langchain/chains/conversation/prompt.py", line 2, in <module>
    from langchain.prompts.prompt import PromptTemplate
  File "/usr/local/lib/python3.8/dist-packages/langchain/prompts/__init__.py", line 2, in <module>
    from langchain.prompts.base import BasePromptTemplate
  File "/usr/local/lib/python3.8/dist-packages/langchain/prompts/base.py", line 35, in <module>
    class BasePromptTemplate(BaseModel, ABC):
  File "/usr/local/lib/python3.8/dist-packages/langchain/prompts/base.py", line 41, in BasePromptTemplate
    @root_validator()
  File "/usr/local/lib/python3.8/dist-packages/pydantic/deprecated/class_validators.py", line 228, in root_validator
    raise PydanticUserError(
pydantic.errors.PydanticUserError: If you use `@root_validator` with pre=False (the default) you MUST specify `skip_on_failure=True`. Note that `@root_validator` is deprecated and should be replaced with `@model_validator`.

Who can help?

@agola11

import langchain

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

1. Install langchain latest version on Linux
2. import langchain

Expected behavior

Nothing.

[dosubot]

🤖

Hello @agola11,

Thank you for providing detailed information about the issue you're facing. The error message you're seeing is related to the Pydantic library, which is a dependency of LangChain.

Based on the traceback you've provided, it seems that the error is being raised because the @root_validator decorator is being used without specifying skip_on_failure=True. This is a requirement in newer versions of Pydantic. However, LangChain v0.0.313 is compatible with Pydantic versions 1 and 2, as specified in the pyproject.toml file of the LangChain repository.

There are a few similar issues that have been resolved in the past. The common solution in these issues was to downgrade the Pydantic library to version 1.10.9. This can be done by running the command pip install pydantic==1.10.9.

Here are the links to the similar issues for your reference:

• Issue: Can not import the Langchain modules.
• from ._pydantic_core import ( ModuleNotFoundError: No module named 'pydantic_core._pydantic_core'
• Issue: Can't import Langchain

Please try downgrading Pydantic to version 1.10.9 and let us know if the issue persists. If it does, we'll continue to investigate and find a solution.

Best,
Dosu

Sources

• Issue: Can not import the Langchain modules.
• from ._pydantic_core import ( ModuleNotFoundError: No module named 'pydantic_core._pydantic_core'
• Issue: Can't import Langchain
• libs/langchain/langchain/pydantic_v1/main.py
• libs/langchain/langchain/pydantic_v1/init.py
• libs/langchain/langchain/pydantic_v1/dataclasses.py
• docs/docs/guides/pydantic_compatibility.md
• libs/langchain/pyproject.toml

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

[shimilgithub]

@dosu-bot is there any other solution for this issue instead of downgrading pydantic to v1?

[devstein]

@shimilgithub As of now Dosu only responds to the issue author. Stay tuned for changes on this in the coming weeks.

Let me know if you have any ideas/feedback on Dosu in the meantime!