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-classicretrieversdocument_compressorscohere_rerankCohereRerankcompress_documents
    Method●Since v1.0

    compress_documents

    Compress documents using Cohere's rerank API.

    Copy
    compress_documents(
      self,
      documents: Sequence[Document],
      query: str,
      callbacks: Callbacks | None = None
    ) -> Sequence[Document]

    Parameters

    NameTypeDescription
    documents*Sequence[Document]

    A sequence of documents to compress.

    query*str

    The query to use for compressing the documents.

    callbacksCallbacks | None
    Default:None

    Callbacks to run during the compression process.

    View source on GitHub