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 - Fast, scalable building blocks for LLM Apps

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.

param session_id

Identifies your user or a user’s session

type session_id

str

param url

Your Zep server’s URL. Defaults to “http://localhost:8000”.

type url

str, optional

param api_key

Your Zep API key. Defaults to None.

type api_key

Optional[str], optional

param output_key

The key to use for the output message. Defaults to None.

type output_key

Optional[str], optional

param input_key

The key to use for the input message. Defaults to None.

type input_key

Optional[str], optional

param return_messages

Does your prompt template expect a string or a list of Messages? Defaults to False i.e. return a string.

type return_messages

bool, optional

param human_prefix

The prefix to use for human messages. Defaults to “Human”.

type human_prefix

str, optional

param ai_prefix

The prefix to use for AI messages. Defaults to “AI”.

type ai_prefix

str, optional

param memory_key

The key to use for the memory. Defaults to “history”. Ensure that this matches the key used in chain’s prompt template.

type memory_key

str, optional

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
async abuffer() → Any

String buffer of memory.

Return type

Any

async abuffer_as_messages() → List[BaseMessage]

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

Return type

List[BaseMessage]

async abuffer_as_str() → str

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

Return type

str

async aclear() → None

Clear memory contents.

Return type

None

async aload_memory_variables(inputs: Dict[str, Any]) → Dict[str, Any]

Return key-value pairs given the text input to the chain.

Parameters

inputs (Dict[str, Any]) –

Return type

Dict[str, Any]

async asave_context(inputs: Dict[str, Any], outputs: Dict[str, str]) → None

Save context from this conversation to buffer.

Parameters

  • inputs (Dict[str, Any]) –

  • outputs (Dict[str, str]) –

Return type

None

clear() → None

Clear memory contents.

Return type

None

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

Parameters

  • _fields_set (Optional[SetStr]) –

  • values (Any) –

Return type

Model

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 (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) – fields to include in new model

  • exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) – fields to exclude from new model, as with values this takes precedence over include

  • update (Optional[DictStrAny]) – 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 (bool) – set to True to make a deep copy of the model

  • self (Model) –

Returns

new model instance

Return type

Model

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.

Parameters

  • include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) –

  • exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) –

  • by_alias (bool) –

  • skip_defaults (Optional[bool]) –

  • exclude_unset (bool) –

  • exclude_defaults (bool) –

  • exclude_none (bool) –

Return type

DictStrAny

classmethod from_orm(obj: Any) → Model
Parameters

obj (Any) –

Return type

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”]

Return type

List[str]

classmethod is_lc_serializable() → bool

Is this class serializable?

Return type

bool

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().

Parameters

  • include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) –

  • exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) –

  • by_alias (bool) –

  • skip_defaults (Optional[bool]) –

  • exclude_unset (bool) –

  • exclude_defaults (bool) –

  • exclude_none (bool) –

  • encoder (Optional[Callable[[Any], Any]]) –

  • models_as_dict (bool) –

  • dumps_kwargs (Any) –

Return type

unicode

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.

Return type

List[str]

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

Return history buffer.

Parameters

inputs (Dict[str, Any]) –

Return type

Dict[str, Any]

classmethod parse_file(path: Union[str, Path], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model
Parameters

  • path (Union[str, Path]) –

  • content_type (unicode) –

  • encoding (unicode) –

  • proto (Protocol) –

  • allow_pickle (bool) –

Return type

Model

classmethod parse_obj(obj: Any) → Model
Parameters

obj (Any) –

Return type

Model

classmethod parse_raw(b: Union[str, bytes], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model
Parameters

  • b (Union[str, bytes]) –

  • content_type (unicode) –

  • encoding (unicode) –

  • proto (Protocol) –

  • allow_pickle (bool) –

Return type

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

Return type

None

classmethod schema(by_alias: bool = True, ref_template: unicode = '#/definitions/{model}') → DictStrAny
Parameters

  • by_alias (bool) –

  • ref_template (unicode) –

Return type

DictStrAny

classmethod schema_json(*, by_alias: bool = True, ref_template: unicode = '#/definitions/{model}', **dumps_kwargs: Any) → unicode
Parameters

  • by_alias (bool) –

  • ref_template (unicode) –

  • dumps_kwargs (Any) –

Return type

unicode

to_json() → Union[SerializedConstructor, SerializedNotImplemented]
Return type

Union[SerializedConstructor, SerializedNotImplemented]

to_json_not_implemented() → SerializedNotImplemented
Return type

SerializedNotImplemented

classmethod update_forward_refs(**localns: Any) → None

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

Parameters

localns (Any) –

Return type

None

classmethod validate(value: Any) → Model
Parameters

value (Any) –

Return type

Model

property buffer: Any

String buffer of memory.

property buffer_as_messages: List[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