LangChain Reference home pageLangChain ReferenceLangChain Reference
  • GitHub
  • Main Docs
Deep Agents
LangChain
LangGraph
Integrations
LangSmith
  • Overview
    • Overview
    • Caches
    • Callbacks
    • Documents
    • Document loaders
    • Embeddings
    • Exceptions
    • Language models
    • Serialization
    • Output parsers
    • Prompts
    • Rate limiters
    • Retrievers
    • Runnables
    • Utilities
    • Vector stores
    MCP Adapters
    Standard Tests
    Text Splitters
    ⌘I

    LangChain Assistant

    Ask a question to get started

    Enter to send•Shift+Enter new line

    Menu

    OverviewCachesCallbacksDocumentsDocument loadersEmbeddingsExceptionsLanguage modelsSerializationOutput parsersPromptsRate limitersRetrieversRunnablesUtilitiesVector stores
    MCP Adapters
    Standard Tests
    Text Splitters
    Language
    Theme
    Pythonlangchain-corevectorstoresbaseVectorStoreamax_marginal_relevance_search
    Methodā—Since v0.2

    amax_marginal_relevance_search

    Copy
    amax_marginal_relevance_search(
      self,
      query: str,
      k: int = 4,
      fetch_k: int
    View source on GitHub
    =
    20
    ,
    lambda_mult
    :
    float
    =
    0.5
    ,
    **
    kwargs
    :
    Any
    =
    {
    }
    )
    ->
    list
    [
    Document
    ]

    Parameters

    NameTypeDescription
    query*str

    Text to look up documents similar to.

    kint
    Default:4

    Number of Document objects to return.

    fetch_kint
    Default:20

    Number of Document objects to fetch to pass to MMR algorithm.

    lambda_multfloat
    Default:0.5
    **kwargsAny
    Default:{}

    Async return docs selected using the maximal marginal relevance.

    Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

    Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity.

    Arguments to pass to the search method.