在Google Colab运行Llama Index代码遇PydanticUserError求解决

用户在Google Colab中执行以下代码时出现错误：

from llama_index.prompts.prompts import SimpleInputPrompt

# Create a system prompt 
system_prompt = """[INST] <>
more string here.<>
"""

query_wrapper_prompt = SimpleInputPrompt("{query_str} [/INST]")

错误信息如下：

/usr/local/lib/python3.10/dist-packages/pydantic/_internal/_config.py:269: UserWarning: Valid config keys have changed in V2:
* 'allow_population_by_field_name' has been renamed to 'populate_by_name'
  warnings.warn(message, UserWarning)
---------------------------------------------------------------------------
PydanticUserError                         Traceback (most recent call last)
<ipython-input-36-c45796b371fe> in <cell line: 3>()
      1 # Import the prompt wrapper...
      2 # but for llama index
----> 3 from llama_index.prompts.prompts import SimpleInputPrompt
      4 # Create a system prompt
      5 system_prompt = """[INST] <>

6 frames
/usr/local/lib/python3.10/dist-packages/pydantic/deprecated/class_validators.py in root_validator(pre, skip_on_failure, allow_reuse, *__args)
    226     mode: Literal['before', 'after'] = 'before' if pre is True else 'after'
    227     if pre is False and skip_on_failure is not True:
--> 228         raise PydanticUserError(
    229             'If you use `@root_validator` with pre=False (the default) you MUST specify `skip_on_failure=True`.'
    230             ' Note that `@root_validator` is deprecated and should be replaced with `@model_validator`.',

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/2.1.1/u/root-validator-pre-skip

解决方案 #

这个错误是旧版Llama Index与Pydantic V2不兼容导致的——Pydantic V2废弃了@root_validator的旧用法（默认pre=False时必须指定skip_on_failure=True），而旧版Llama Index仍在使用不符合V2规范的代码。

有两种解决方式：

方式一：降级Pydantic到V1版本

在Colab的代码单元格中执行以下命令，然后重启运行时：

!pip install pydantic==1.10.13

重启后重新导入模块并执行原有代码即可。

方式二：升级Llama Index到兼容Pydantic V2的版本

执行命令升级Llama Index：

!pip install --upgrade llama-index

升级后，SimpleInputPrompt的导入路径需要调整为：

from llama_index.core.prompts import SimpleInputPrompt

之后再运行你的代码就不会报错了。

内容的提问来源于stack exchange，提问作者Christian01