langchain.memory.zep_memory.ZepMemory

class langchain.memory.zep_memory.ZepMemory[source]

Bases: ConversationBufferMemory

Persist your chain history to the Zep MemoryStore.

The number of messages returned by Zep and when the Zep server summarizes chat histories is configurable. See the Zep documentation for more details.

Documentation: https://docs.getzep.com

Example
memory = ZepMemory(

session_id=session_id, # Identifies your user or a user’s session url=ZEP_API_URL, # Your Zep server’s URL api_key=<your_api_key>, # Optional memory_key=”history”, # Ensure this matches the key used in

# chain’s prompt template

return_messages=True, # Does your prompt template expect a string

# or a list of Messages?

)

chain = LLMChain(memory=memory,…) # Configure your chain to use the ZepMemory

instance

Note

To persist metadata alongside your chat history, your will need to create a

custom Chain class that overrides the prep_outputs method to include the metadata in the call to self.memory.save_context.

Zep is an open source platform for productionizing LLM apps. Go from a prototype built in LangChain or LlamaIndex, or a custom app, to production in minutes without rewriting code.

For server installation instructions and more, see: https://docs.getzep.com/deployment/quickstart/

For more information on the zep-python package, see: https://github.com/getzep/zep-python

Initialize ZepMemory.

Parameters

  • session_id (str) – Identifies your user or a user’s session

  • url (str, optional) – Your Zep server’s URL. Defaults to “http://localhost:8000”.

  • api_key (Optional[str], optional) – Your Zep API key. Defaults to None.

  • output_key (Optional[str], optional) – The key to use for the output message. Defaults to None.

  • input_key (Optional[str], optional) – The key to use for the input message. Defaults to None.

  • return_messages (bool, optional) – Does your prompt template expect a string or a list of Messages? Defaults to False i.e. return a string.

  • human_prefix (str, optional) – The prefix to use for human messages. Defaults to “Human”.

  • ai_prefix (str, optional) – The prefix to use for AI messages. Defaults to “AI”.

  • memory_key (str, optional) – The key to use for the memory. Defaults to “history”. Ensure that this matches the key used in chain’s prompt template.

param ai_prefix: str = 'AI'
param chat_memory: ZepChatMessageHistory [Required]
param human_prefix: str = 'Human'
param input_key: Optional[str] = None
param output_key: Optional[str] = None
param return_messages: bool = False
clear() → None

Clear memory contents.

classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) → Model

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values

copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters

  • include – fields to include in new model

  • exclude – fields to exclude from new model, as with values this takes precedence over include

  • update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

  • deep – set to True to make a deep copy of the model

Returns

new model instance

dict(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) → DictStrAny

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

classmethod from_orm(obj: Any) → Model
classmethod get_lc_namespace() → List[str]

Get the namespace of the langchain object.

For example, if the class is langchain.llms.openai.OpenAI, then the namespace is [“langchain”, “llms”, “openai”]

classmethod is_lc_serializable() → bool

Is this class serializable?

json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) → unicode

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

classmethod lc_id() → List[str]

A unique identifier for this class for serialization purposes.

The unique identifier is a list of strings that describes the path to the object.

load_memory_variables(inputs: Dict[str, Any]) → Dict[str, Any]

Return history buffer.

classmethod parse_file(path: Union[str, Path], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model
classmethod parse_obj(obj: Any) → Model
classmethod parse_raw(b: Union[str, bytes], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model
save_context(inputs: Dict[str, Any], outputs: Dict[str, str], metadata: Optional[Dict[str, Any]] = None) → None[source]

Save context from this conversation to buffer.

Parameters

  • inputs (Dict[str, Any]) – The inputs to the chain.

  • outputs (Dict[str, str]) – The outputs from the chain.

  • metadata (Optional[Dict[str, Any]], optional) – Any metadata to save with the context. Defaults to None

Returns

None

classmethod schema(by_alias: bool = True, ref_template: unicode = '#/definitions/{model}') → DictStrAny
classmethod schema_json(*, by_alias: bool = True, ref_template: unicode = '#/definitions/{model}', **dumps_kwargs: Any) → unicode
to_json() → Union[SerializedConstructor, SerializedNotImplemented]
to_json_not_implemented() → SerializedNotImplemented
classmethod update_forward_refs(**localns: Any) → None

Try to update ForwardRefs on fields based on this Model, globalns and localns.

classmethod validate(value: Any) → Model
property buffer: Any

String buffer of memory.

property buffer_as_messages: List[langchain_core.messages.base.BaseMessage]

Exposes the buffer as a list of messages in case return_messages is False.

property buffer_as_str: str

Exposes the buffer as a string in case return_messages is True.

property lc_attributes: Dict

List of attribute names that should be included in the serialized kwargs.

These attributes must be accepted by the constructor.

property lc_secrets: Dict[str, str]

A map of constructor argument names to secret ids.

For example,

{“openai_api_key”: “OPENAI_API_KEY”}

Examples using ZepMemory