ConversationSummaryMemory#
- class langchain.memory.summary.ConversationSummaryMemory[source]#
Bases:
BaseChatMemory
,SummarizerMixin
Deprecated since version 0.3.1: Please see the migration guide at: https://python.langchain.com/docs/versions/migrating_memory/
Continually summarizes the conversation history.
The summary is updated after each conversation turn. The implementations returns a summary of the conversation history which can be used to provide context to the model.
- param ai_prefix: str = 'AI'#
- param buffer: str = ''#
- param chat_memory: BaseChatMessageHistory [Optional]#
- param human_prefix: str = 'Human'#
- param input_key: str | None = None#
- param llm: BaseLanguageModel [Required]#
- param output_key: str | None = None#
- param prompt: BasePromptTemplate = PromptTemplate(input_variables=['new_lines', 'summary'], input_types={}, partial_variables={}, template='Progressively summarize the lines of conversation provided, adding onto the previous summary returning a new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks of artificial intelligence. The AI thinks artificial intelligence is a force for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial intelligence is a force for good?\nAI: Because artificial intelligence will help humans reach their full potential.\n\nNew summary:\nThe human asks what the AI thinks of artificial intelligence. The AI thinks artificial intelligence is a force for good because it will help humans reach their full potential.\nEND OF EXAMPLE\n\nCurrent summary:\n{summary}\n\nNew lines of conversation:\n{new_lines}\n\nNew summary:')#
- param return_messages: bool = False#
- param summary_message_cls: Type[BaseMessage] = <class 'langchain_core.messages.system.SystemMessage'>#
- async aclear() None #
Clear memory contents.
- Return type:
None
- async aload_memory_variables(inputs: dict[str, Any]) dict[str, Any] #
Async return key-value pairs given the text input to the chain.
- Parameters:
inputs (dict[str, Any]) – The inputs to the chain.
- Returns:
A dictionary of key-value pairs.
- Return type:
dict[str, Any]
- async apredict_new_summary(messages: List[BaseMessage], existing_summary: str) str #
- Parameters:
messages (List[BaseMessage])
existing_summary (str)
- Return type:
str
- 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
- classmethod from_messages(llm: BaseLanguageModel, chat_memory: BaseChatMessageHistory, *, summarize_step: int = 2, **kwargs: Any) ConversationSummaryMemory [source]#
- Parameters:
llm (BaseLanguageModel)
chat_memory (BaseChatMessageHistory)
summarize_step (int)
kwargs (Any)
- Return type:
- load_memory_variables(inputs: Dict[str, Any]) Dict[str, Any] [source]#
Return history buffer.
- Parameters:
inputs (Dict[str, Any])
- Return type:
Dict[str, Any]
- predict_new_summary(messages: List[BaseMessage], existing_summary: str) str #
- Parameters:
messages (List[BaseMessage])
existing_summary (str)
- Return type:
str