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
    โŒ˜I

    Chat LangChain

    What can I help with?

    Enter to sendยทShift+Enter new line

    Menu

    OverviewCachesCallbacksDocumentsDocument loadersEmbeddingsExceptionsLanguage modelsSerializationOutput parsersPromptsRate limitersRetrieversRunnablesUtilitiesVector stores
    MCP Adapters
    Standard Tests
    Text Splitters
    Language
    Theme
    Pythonlangchain-coredecisionstypesClassifierResponse
    Classโ—Since v1.8

    ClassifierResponse

    Copy
    ClassifierResponse()

    Bases

    BaseModel

    Attributes

    View source on GitHub
    attribute
    model: str

    Model that answered the request.

    attribute
    answers: dict[str, Answer]

    All answers keyed by their original question IDs.

    attribute
    usage: UsageMetadata | None

    Token usage reported for the request, or None when not reported.

    Providers may supply only input_tokens and output_tokens. A missing count is treated as 0, and total_tokens defaults to their sum.

    attribute
    request_id: str | None

    Provider request ID, useful when diagnosing a request with provider support.

    attribute
    nouls: dict[str, NoulAnswer]

    Return binary answers keyed by their original question IDs.

    attribute
    choices: dict[str, ChoiceAnswer]

    Return categorical answers keyed by their original question IDs.

    attribute
    scores: dict[str, ScoreAnswer]

    Return ordinal answers keyed by their original question IDs.

    attribute
    boxes: dict[str, BoxAnswer]

    Return localization answers keyed by their original question IDs.

    Typed answers and metadata returned from one classification request.

    Access every answer through answers, or use nouls, choices, scores, and boxes for views filtered by answer type. Each mapping preserves the question IDs supplied to ClassifierRequest.questions.