@microsoft/opentelemetry
    Preparing search index...

    Interface InferenceDetails

    Details for an inference call.

    interface InferenceDetails {
        endpoint?: ServiceEndpoint;
        finishReasons?: string[];
        inputTokens?: number;
        model: string;
        operationName: InferenceOperationType;
        outputTokens?: number;
        providerName?: string;
        thoughtProcess?: string;
    }
    Index
    endpoint? finishReasons? inputTokens? model operationName outputTokens? providerName? thoughtProcess?
    endpoint?: ServiceEndpoint

    Endpoint the model is hosted on.

    finishReasons?: string[]

    Finish reasons returned by the model.

    inputTokens?: number

    Number of input (prompt) tokens.

    model: string

    Name of the model used for inference.

    operationName: InferenceOperationType

    The inference operation type (e.g. chat, text completion).

    outputTokens?: number

    Number of output (completion) tokens.

    providerName?: string

    Name of the provider serving the model.

    thoughtProcess?: string

    The model's thought process / reasoning trace.

    Settings
    Member Visibility

    On This Page
    Properties