LangChain Reference home pageLangChain ReferenceLangChain Reference
  • GitHub
  • Main Docs
Deep Agents
LangChain
LangGraph
Integrations
LangSmith
  • Overview
  • MCP Adapters
    • Overview
    • Agents
    • Callbacks
    • Chains
    • Chat models
    • Embeddings
    • Evaluation
    • Globals
    • Hub
    • Memory
    • Output parsers
    • Retrievers
    • Runnables
    • LangSmith
    • Storage
    Standard Tests
    Text Splitters
    ⌘I

    LangChain Assistant

    Ask a question to get started

    Enter to send•Shift+Enter new line

    Menu

    MCP Adapters
    OverviewAgentsCallbacksChainsChat modelsEmbeddingsEvaluationGlobalsHubMemoryOutput parsersRetrieversRunnablesLangSmithStorage
    Standard Tests
    Text Splitters
    Language
    Theme
    Pythonlangchain-classicmemorysummaryConversationSummaryMemoryfrom_messages
    Method●Since v1.0

    from_messages

    Create a ConversationSummaryMemory from a list of messages.

    Copy
    from_messages(
      cls,
      llm: BaseLanguageModel,
      chat_memory: BaseChatMessageHistory,
      *,
      summarize_step: int = 2,
      **kwargs: Any = {}
    ) -> ConversationSummaryMemory

    Parameters

    NameTypeDescription
    llm*BaseLanguageModel

    The language model to use for summarization.

    chat_memory*BaseChatMessageHistory

    The chat history to summarize.

    summarize_stepint
    Default:2

    Number of messages to summarize at a time.

    **kwargsAny
    Default:{}

    Additional keyword arguments to pass to the class.

    View source on GitHub