调用langchain报错

Question

调用langchain.llms报错了，报错内容如下，如何解决：
{
“name”: “PydanticUserError”,
“message”: "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.

For further information visit https://errors.pydantic.dev/2.5/u/root-validator-pre-skip",
“stack”: "---------------------------------------------------------------------------
PydanticUserError Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_18008\3244751140.py in
1 #hello world
----> 2 from langchain.llms import OpenAI
3 import os
4
5 api_base = os.getenv(“OPENAI_API_BASE”)

d:\envs\langchain\lib\site-packages\langchain\init.py in
6 version = _f.read().strip()
7
----> 8 from langchain.agents import MRKLChain, ReActChain, SelfAskWithSearchChain
9 from langchain.chains import (
10 ConversationChain,

d:\envs\langchain\lib\site-packages\langchain\agents\init.py in
1 “”“Routing chains.”""
----> 2 from langchain.agents.agent import Agent
3 from langchain.agents.loading import initialize_agent
4 from langchain.agents.mrkl.base import MRKLChain, ZeroShotAgent
5 from langchain.agents.react.base import ReActChain, ReActTextWorldAgent

d:\envs\langchain\lib\site-packages\langchain\agents\agent.py in
8
9 from langchain.agents.tools import Tool
—> 10 from langchain.chains.base import Chain
11 from langchain.chains.llm import LLMChain
12 from langchain.input import ChainedInput, get_color_mapping

d:\envs\langchain\lib\site-packages\langchain\chains\init.py in
1 “”“Chains are easily reusable components which can be linked together.”""
----> 2 from langchain.chains.conversation.base import ConversationChain
3 from langchain.chains.llm import LLMChain
4 from langchain.chains.llm_math.base import LLMMathChain
5 from langchain.chains.pal.base import PALChain

d:\envs\langchain\lib\site-packages\langchain\chains\conversation\base.py in
5
6 from langchain.chains.base import Memory
----> 7 from langchain.chains.conversation.memory import ConversationBufferMemory
8 from langchain.chains.conversation.prompt import PROMPT
9 from langchain.chains.llm import LLMChain

d:\envs\langchain\lib\site-packages\langchain\chains\conversation\memory.py in
5
6 from langchain.chains.base import Memory
----> 7 from langchain.chains.conversation.prompt import SUMMARY_PROMPT
8 from langchain.chains.llm import LLMChain
9 from langchain.llms.base import LLM

d:\envs\langchain\lib\site-packages\langchain\chains\conversation\prompt.py in
1 # flake8: noqa
----> 2 from langchain.prompts.prompt import PromptTemplate
3
4 _DEFAULT_TEMPLATE = “”"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
5

d:\envs\langchain\lib\site-packages\langchain\prompts\init.py in
1 “”“Prompt template classes.”""
----> 2 from langchain.prompts.base import BasePromptTemplate
3 from langchain.prompts.few_shot import FewShotPromptTemplate
4 from langchain.prompts.loading import load_prompt
5 from langchain.prompts.prompt import Prompt, PromptTemplate

d:\envs\langchain\lib\site-packages\langchain\prompts\base.py in
33
34
—> 35 class BasePromptTemplate(BaseModel, ABC):
36 “”“Base prompt should expose the format method, returning a prompt.”""
37

d:\envs\langchain\lib\site-packages\langchain\prompts\base.py in BasePromptTemplate()
39 “”“A list of the names of the variables the prompt template expects.”"“
40
—> 41 @root_validator()
42 def validate_variable_names(cls, values: Dict) -> Dict:
43 “”“Validate variable names do not restricted names.””"

d:\envs\langchain\lib\site-packages\pydantic\deprecated\class_validators.py in root_validator(pre, skip_on_failure, allow_reuse, *__args)
238 'If you use @root_validator with pre=False (the default) you MUST specify skip_on_failure=True.‘
239 ’ Note that @root_validator is deprecated and should be replaced with @model_validator.’,
–> 240 code=‘root-validator-pre-skip’,
241 )
242

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.

For further information visit https://errors.pydantic.dev/2.5/u/root-validator-pre-skip"
}

Answer 1

tomiezhang 2024-09-05 16:55:25

版本的问题，卸载langchain和openai按照我这个版本安装

pip uninstall langchain openai -y
pip install openai==0.27.8 
pip install langchain==0.0.288

还不行的话可以在我搭建的在线环境里试试：
http://149.28.145.211:8000/hub/login?next=%2Fhub%2F
课程码在这个学习页面右侧申请