ValidationError: 2 validation errors for LLMChain

[innat-asj]

Checked other resources

• [X] I added a very descriptive title to this issue.
• [X] I searched the LangChain documentation with the integrated search.
• [X] I used the GitHub search to find a similar question and didn't find it.
• [X] I am sure that this is a bug in LangChain rather than my code.
• [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

from langchain.chains.summarize import load_summarize_chain

client = AzureOpenAI(
    api_version=api_version,
    api_key=api_key,
    azure_endpoint=azure_endpoint,
)

chain = load_summarize_chain(client, chain_type="stuff")

--------------------------------------------------------------------------
ValidationError                           Traceback (most recent call last)
Cell In[13], line 1
----> 1 chain = load_summarize_chain(client, chain_type="stuff")

File /opt/conda/envs/pytorch/lib/python3.10/site-packages/langchain/chains/summarize/__init__.py:157, in load_summarize_chain(llm, chain_type, verbose, **kwargs)
    152 if chain_type not in loader_mapping:
    153     raise ValueError(
    154         f"Got unsupported chain type: {chain_type}. "
    155         f"Should be one of {loader_mapping.keys()}"
    156     )
--> 157 return loader_mapping[chain_type](llm, verbose=verbose, **kwargs)

File /opt/conda/envs/pytorch/lib/python3.10/site-packages/langchain/chains/summarize/__init__.py:33, in _load_stuff_chain(llm, prompt, document_variable_name, verbose, **kwargs)
     26 def _load_stuff_chain(
     27     llm: BaseLanguageModel,
     28     prompt: BasePromptTemplate = stuff_prompt.PROMPT,
   (...)
     31     **kwargs: Any,
     32 ) -> StuffDocumentsChain:
---> 33     llm_chain = LLMChain(llm=llm, prompt=prompt, verbose=verbose)
     34     # TODO: document prompt
     35     return StuffDocumentsChain(
     36         llm_chain=llm_chain,
     37         document_variable_name=document_variable_name,
     38         verbose=verbose,
     39         **kwargs,
     40     )

File /opt/conda/envs/pytorch/lib/python3.10/site-packages/langchain_core/load/serializable.py:120, in Serializable.__init__(self, **kwargs)
    119 def __init__(self, **kwargs: Any) -> None:
--> 120     super().__init__(**kwargs)
    121     self._lc_kwargs = kwargs

File /opt/conda/envs/pytorch/lib/python3.10/site-packages/pydantic/main.py:341, in pydantic.main.BaseModel.__init__()

ValidationError: 2 validation errors for LLMChain
llm
  instance of Runnable expected (type=type_error.arbitrary_type; expected_arbitrary_type=Runnable)
llm
  instance of Runnable expected (type=type_error.arbitrary_type; expected_arbitrary_type=Runnable)

Error Message and Stack Trace (if applicable)

No response

Description

I tried to insert the azure open ai to summarization pipeline, but it gives error.

System Info

latest langchain.

[faycaldjilali]

I installed the packages 'pydantic' and 'docarray' on PowerShell using the following commands:

pip install pydantic==1.10.13
pip install docarray==0.32.1

After that, I created a new virtual environment and activated it. My project worked smoothly within that virtual environment."