报错 - llama-index pydantic error | arbitrary_types_allowed

报错 - llama-index pydantic error | arbitrary_types_allowed | PydanticUserError

国庆节前使用 LiteLLMEmbedding 设置 llama-index Settings.embed_model 还好好的，回来后，就就报错，试着降级 llama-index 也无用；设置 Settings.llm 也是好好地。

解决方法：conda 重新创建环境后，在安装 llama-index 就好了

具体原因还没找到

我的报错信息如下：

1008

 As of langchain-core 0.3.0, LangChain uses pydantic v2 internally. The langchain_core.pydantic_v1 module was a compatibility shim for pydantic v1, and should no longer be used. Please update the code to import from Pydantic directly.For example, replace imports like: `from langchain_core.pydantic_v1 import BaseModel`
with: `from pydantic import BaseModel`
or the v1 compatibility namespace if you are working in a code base that has not been fully upgraded to pydantic 2 yet. 	from pydantic.v1 import BaseModelfrom langchain.agents.agent import (
Traceback (most recent call last):File "<stdin>", line 1, in <module>File "/Users/xx/miniconda3/lib/python3.11/site-packages/llama_index/core/settings.py", line 74, in embed_modelself._embed_model = resolve_embed_model(embed_model)^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/llama_index/core/embeddings/utils.py", line 39, in resolve_embed_modelfrom llama_index.core.bridge.langchain import Embeddings as LCEmbeddingsFile "/Users/xx/miniconda3/lib/python3.11/site-packages/llama_index/core/bridge/langchain.py", line 2, in <module>from langchain.agents import (File "/Users/xx/miniconda3/lib/python3.11/site-packages/langchain/agents/__init__.py", line 40, in <module>from langchain.agents.agent import (File "/Users/xx/miniconda3/lib/python3.11/site-packages/langchain/agents/agent.py", line 639, in <module>class LLMSingleActionAgent(BaseSingleActionAgent):File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/v1/main.py", line 197, in __new__fields[ann_name] = ModelField.infer(^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/v1/fields.py", line 504, in inferreturn cls(^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/v1/fields.py", line 434, in __init__self.prepare()File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/v1/fields.py", line 555, in prepareself.populate_validators()File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/v1/fields.py", line 829, in populate_validators*(get_validators() if get_validators else list(find_validators(self.type_, self.model_config))),^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/v1/validators.py", line 765, in find_validatorsraise RuntimeError(f'no validator found for {type_}, see `arbitrary_types_allowed` in Config')
RuntimeError: no validator found for <class 'langchain.chains.llm.LLMChain'>, see `arbitrary_types_allowed` in Config

升级 langchain 从 0.2 到 0.3 后，依然报错

/Users/xx/miniconda3/lib/python3.11/site-packages/langchain/chains/api/base.py:56: LangChainDeprecationWarning: As of langchain-core 0.3.0, LangChain uses pydantic v2 internally. The langchain_core.pydantic_v1 module was a compatibility shim for pydantic v1, and should no longer be used. Please update the code to import from Pydantic directly.For example, replace imports like: `from langchain_core.pydantic_v1 import BaseModel`
with: `from pydantic import BaseModel`
or the v1 compatibility namespace if you are working in a code base that has not been fully upgraded to pydantic 2 yet. 	from pydantic.v1 import BaseModelfrom langchain_community.utilities.requests import TextRequestsWrapper
/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_config.py:341: 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 "<stdin>", line 1, in <module>File "/Users/xx/miniconda3/lib/python3.11/site-packages/llama_index/core/settings.py", line 74, in embed_modelself._embed_model = resolve_embed_model(embed_model)^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/llama_index/core/embeddings/utils.py", line 39, in resolve_embed_modelfrom llama_index.core.bridge.langchain import Embeddings as LCEmbeddingsFile "/Users/xx/miniconda3/lib/python3.11/site-packages/llama_index/core/bridge/langchain.py", line 66, in <module>from langchain_community.chat_models import (File "<frozen importlib._bootstrap>", line 1229, in _handle_fromlistFile "/Users/xx/miniconda3/lib/python3.11/site-packages/langchain_community/chat_models/__init__.py", line 301, in __getattr__module = importlib.import_module(_module_lookup[name])^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/importlib/__init__.py", line 126, in import_modulereturn _bootstrap._gcd_import(name[level:], package, level)^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/langchain_community/chat_models/anyscale.py", line 31, in <module>class ChatAnyscale(ChatOpenAI):File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_model_construction.py", line 224, in __new__complete_model_class(File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_model_construction.py", line 577, in complete_model_classschema = cls.__get_pydantic_core_schema__(cls, handler)^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/main.py", line 671, in __get_pydantic_core_schema__return handler(source)^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_schema_generation_shared.py", line 83, in __call__schema = self._handler(source_type)^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_generate_schema.py", line 655, in generate_schemaschema = self._generate_schema_inner(obj)^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_generate_schema.py", line 924, in _generate_schema_innerreturn self._model_schema(obj)^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_generate_schema.py", line 739, in _model_schema{k: self._generate_md_field_schema(k, v, decorators) for k, v in fields.items()},^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_generate_schema.py", line 739, in <dictcomp>{k: self._generate_md_field_schema(k, v, decorators) for k, v in fields.items()},^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_generate_schema.py", line 1115, in _generate_md_field_schemacommon_field = self._common_field_schema(name, field_info, decorators)^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_generate_schema.py", line 1308, in _common_field_schemaschema = self._apply_annotations(^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_generate_schema.py", line 2107, in _apply_annotationsschema = get_inner_schema(source_type)^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_schema_generation_shared.py", line 83, in __call__schema = self._handler(source_type)^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_generate_schema.py", line 2091, in inner_handlermetadata_js_function = _extract_get_pydantic_json_schema(obj, schema)^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "/Users/xx/miniconda3/lib/python3.11/site-packages/pydantic/_internal/_generate_schema.py", line 2447, in _extract_get_pydantic_json_schemaraise PydanticUserError(
pydantic.errors.PydanticUserError: The `__modify_schema__` method is not supported in Pydantic v2. Use `__get_pydantic_json_schema__` instead in class `SecretStr`.For further information visit https://errors.pydantic.dev/2.9/u/custom-json-schema