hhddlmZddlmZmZmZddlmZ ddlm Z Gdde Z dS#e $rGddZ YdSwxYw) ) annotations)AnyDictOptional)ZepChatMessageHistory)ConversationBufferMemorycNeZdZUdZded< d d!fd Z d"d#dZxZS)$ ZepMemorya*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: .. code-block:: python 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=, # 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 r chat_memoryhttp://localhost:8000NFHumanAIhistory session_idstrurlapi_key Optional[str] output_key input_keyreturn_messagesbool human_prefix ai_prefix memory_keyc |t|||} t| |||||| dS)aInitialize ZepMemory. Args: 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. )rrr)r rrrrrrN)rsuper__init__) selfrrrrrrrrrchat_message_history __class__s b/var/www/FlaskApp/flask-venv/lib/python3.11/site-packages/langchain_community/memory/zep_memory.pyrzZepMemory.__init__8sfF$9%$$$ GG  0%# /)#%      inputsDict[str, Any]outputsDict[str, str]metadataOptional[Dict[str, Any]]returnNonec|||\}}|j|||j||dS)aSave context from this conversation to buffer. Args: 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 )r(N)_get_input_outputr add_user_messageadd_ai_message)rr$r&r( input_str output_strs r" save_contextzZepMemory.save_contextjs\"%)$:$:67$K$K !Iz   - -i( - K K K   + +J + J J J J Jr#)r NNNFr rr)rrrrrrrrrrrrrrrrrr)N)r$r%r&r'r(r)r*r+)__name__ __module__ __qualname____doc____annotations__rr2 __classcell__)r!s@r"r r s) ) V +*** /%)(,'+$) '!'0 0 0 0 0 0 0 l26  K K K K K K K K Kr#r ceZdZdS)r N)r3r4r5r#r"r r s r#N) __future__rtypingrrr*langchain_community.chat_message_historiesrlangchain.memoryrr ImportErrorr:r#r"r@s""""""&&&&&&&&&&LLLLLL{ 999999sKsKsKsKsK,sKsKsKsKsKj               s.AA