PydanticUserError: ConversationSummaryBufferMemory is not fully defined; you should define BaseCache, then call ConversationSummaryBufferMemory.model_rebuild().

[LeadsiftAI]

Checked other resources

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

Example Code

from langchain.memory import ConversationSummaryBufferMemory

memory = ConversationSummaryBufferMemory(
    llm=chat,
    input_key="input",
    output_key="output",
    max_token_limit=1024,
    memory_key="chat_history",
)

Error Message and Stack Trace (if applicable)

{
"name": "PydanticUserError",
"message": "ConversationSummaryBufferMemory is not fully defined; you should define BaseCache, then call ConversationSummaryBufferMemory.model_rebuild().

For further information visit https://errors.pydantic.dev/2.10/u/class-not-fully-defined",
"stack": "---------------------------------------------------------------------------
PydanticUserError Traceback (most recent call last)
Cell In[45], line 3
1 from langchain.memory import ConversationSummaryBufferMemory
----> 3 memory = ConversationSummaryBufferMemory(
4 llm=chat,
5 input_key="input",
6 output_key="output",
7 max_token_limit=1024,
8 memory_key="chat_history",
9 )

File c:\xxxx\site-packages\langchain_core\_api\deprecation.py:216, in deprecated..deprecate..finalize..warn_if_direct_instance(self, *args, **kwargs)
214 warned = True
215 emit_warning()
--> 216 return wrapped(self, *args, **kwargs)

File xxxx\site-packages\langchain_core\_api\deprecation.py:216, in deprecated..deprecate..finalize..warn_if_direct_instance(self, *args, **kwargs)
214 warned = True
215 emit_warning()
--> 216 return wrapped(self, *args, **kwargs)

File xxxx\site-packages\langchain_core\_api\deprecation.py:216, in deprecated..deprecate..finalize..warn_if_direct_instance(self, *args, **kwargs)
214 warned = True
215 emit_warning()
--> 216 return wrapped(self, *args, **kwargs)

File xxxx\site-packages\langchain_core\load\serializable.py:125, in Serializable.init(self, *args, **kwargs)
123 def init(self, *args: Any, **kwargs: Any) -> None:
124 """"""
--> 125 super().init(*args, **kwargs)

File xxxx\site-packages\langchain_core\_api\deprecation.py:216, in deprecated..deprecate..finalize..warn_if_direct_instance(self, *args, **kwargs)
214 warned = True
215 emit_warning()
--> 216 return wrapped(self, *args, **kwargs)

[... skipping hidden 1 frame]

File xxxx\site-packages\pydantic\_internal\_mock_val_ser.py:100, in MockValSer.getattr(self, item)
98 # raise an AttributeError if item doesn't exist
99 getattr(self._val_or_ser, item)
--> 100 raise PydanticUserError(self._error_message, code=self._code)

PydanticUserError: ConversationSummaryBufferMemory is not fully defined; you should define BaseCache, then call ConversationSummaryBufferMemory.model_rebuild().

For further information visit https://errors.pydantic.dev/2.10/u/class-not-fully-defined"
}

Description

I've upgrade my project's langchain package to latest, and when i create ConversationSummaryBufferMemory, encountered the PydanticUserError

System Info

System Information

OS: Windows
OS Version: 10.0.22631
Python Version: 3.11.10 | packaged by Anaconda, Inc. | (main, Oct 3 2024, 07:22:26) [MSC v.1929 64 bit (AMD64)]

Package Information

langchain_core: 0.3.19
langchain: 0.3.7
langchain_community: 0.3.7
langsmith: 0.1.144
langchain_openai: 0.2.9
langchain_text_splitters: 0.3.2

Optional packages not installed

langgraph
langserve

Other Dependencies

aiohttp: 3.11.6
async-timeout: Installed. No version info available.
dataclasses-json: 0.6.7
httpx: 0.27.2
httpx-sse: 0.4.0
jsonpatch: 1.33
numpy: 1.26.4
openai: 1.55.0
orjson: 3.10.11
packaging: 24.2
pydantic: 2.10.0
pydantic-settings: 2.6.1
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.35
tenacity: 9.0.0
tiktoken: 0.8.0
typing-extensions: 4.12.2

[miguelrgonzalez]

I had the same issue, but in my case the error was raised when instantiating a custom Retriever.
The underlying issue is with the pydantic-settings version 2.6.1.
Downgrading fixed the problem for me.

"pydantic-core==2.23.4",
"pydantic-settings==2.6.0",

[LeadsiftAI]

I had the same issue, but in my case the error was raised when instantiating a custom Retriever. The underlying issue is with the pydantic-settings version 2.6.1. Downgrading fixed the problem for me.

"pydantic-core==2.23.4",
"pydantic-settings==2.6.0",

@miguelrgonzalez thanks, i've downgrade my project's pydantic version to 2.9.2 and fixed

[coolbeevip]

same issue

"pydantic==2.10.1",
"pydantic_core==2.27.1",
"pydantic-settings==2.6.0",

[ahmed33033]

I got a similar issue as well, but with SQLDatabaseToolkit.

If you're using poetry, I simply changed my pydantic dependency to: pydantic = "2.9.2", and I ran the following command:

> poetry update

Updating dependencies
Resolving dependencies... (7.3s)

Package operations: 0 installs, 2 updates, 0 removals

  - Downgrading pydantic-core (2.27.1 -> 2.23.4)
  - Downgrading pydantic (2.10.1 -> 2.9.2)

[kuangdai]

Same here.

pydantic 2.10.0
pydantic_core 2.27.0
pydantic-settings 2.6.1

[thecodemancer]

Same here:

pydantic==2.9.2
    # via
    #   google-cloud-aiplatform
    #   google-generativeai
    #   langchain
    #   langchain-core
    #   langchain-google-genai
    #   langsmith
    #   openai
    #   pydantic-settings
pydantic-core==2.23.4
    # via pydantic
pydantic-settings==2.6.1
    # via langchain-community