在 CPU 上发生 `pydantic.errors.PydanticUserError`

Trying to run a CPU-based model on Windows 11. A clean installation following this instruction (changed the name of the conda environment to avoid collisions): https://GitHub.com/h2oai/h2ogpt/blob/main/docs/README_WINDOWS.md Tried running any model from the instruction below: https://GitHub.com/h2oai/h2ogpt/blob/main/docs/README_CPU.md First, I got errors for missing libraries: pip install fire pip install LangChain pip install -U LangChain-Anthropic pip install LangChain-community pip install LangChain-experimental pip install LangChain-google-genai After I got just this message: C:\Users\Worker\miniconda3\envs\h2ogpt_cpu\lib\site-packages\pydantic\_internal\_config.py:345: UserWarning: Valid config keys have changed in V2: * 'allow_population_by_field_name' has been renamed to 'populate_by_name' warnings.warn(message, UserWarning) Traceback (most recent call last): File "C:\Users\Worker\Documents\AI\CPU_based\h2ogpt\generate.py", line 20, in <module> entrypoint_main() File "C:\Users\Worker\Documents\AI\CPU_based\h2ogpt\generate.py", line 16, in entrypoint_main H2O_Fire(main) File "C:\Users\Worker\Documents\AI\CPU_based\h2ogpt\src\\\\utils.py", line 79, in H2O_Fire fire.Fire(component=component, command=args) File "C:\Users\Worker\miniconda3\envs\h2ogpt_cpu\lib\site-packages\fire\core.py", line 135, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "C:\Users\Worker\miniconda3\envs\h2ogpt_cpu\lib\site-packages\fire\core.py", line 468, in _Fire component, remaining_args = _CallAndUpdateTrace( File "C:\Users\Worker\miniconda3\envs\h2ogpt_cpu\lib\site-packages\fire\core.py", line 684, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) File "C:\Users\Worker\Documents\AI\CPU_based\h2ogpt\src\gen.py", line 2058, in main from gpt_langchain import get_embedding File "C:\Users\Worker\Documents\AI\CPU_based\h2ogpt\src\gpt_langchain.py", line 60, in <module> from langchain_mistralai.chat_models import ChatMistralAI File "C:\Users\Worker\Documents\AI\CPU_based\h2ogpt\src\langchain_mistralai\chat_models.py", line 317, in <module> class ChatMistralAI(BaseChatModel): File "C:\Users\Worker\miniconda3\envs\h2ogpt_cpu\lib\site-packages\pydantic\_internal\_model_construction.py", line 224, in __new__ complete_model_class( File "C:\Users\Worker\miniconda3\envs\h2ogpt_cpu\lib\site-packages\pydantic\_internal\_model_construction.py", line 602, in complete_model_class schema = cls.__get_pydantic_core_schema__(cls, handler) File "C:\Users\Worker\miniconda3\envs\h2ogpt_cpu\lib\site-packages\pydantic\main.py", line 702, in __get_pydantic_core_schema__ return handler(source) File "C:\Users\Worker\miniconda3\envs\h2ogpt_cpu\lib\site-packages\pydantic\_internal\_schema_generation_shared.py", line 84, in __call__ schema = self._handler(source_type) File