Represents the model configuration including model type, supported parameters, and other model details.

ModelInfo

interface ModelInfo {
    defaultDimension?: number;
    maxBatchSize?: number;
    maxSequenceLength?: number;
    modality?: string;
    model: string;
    providerName?: string;
    shortDescription: string;
    supportedDimensions?: number[];
    supportedMetrics?: string[];
    supportedParameters: ModelInfoSupportedParameter[];
    type: string;
    vectorType?: string;
}

Properties

defaultDimension?: number

The default embedding model dimension (applies to dense embedding models only).

ModelInfo

maxBatchSize?: number

The maximum batch size (number of sequences) supported by the model.

ModelInfo

maxSequenceLength?: number

The maximum tokens per sequence supported by the model.

ModelInfo

modality?: string

The modality of the model (e.g. 'text').

ModelInfo

model: string

The name of the model.

ModelInfo

providerName?: string

The name of the provider of the model.

ModelInfo

shortDescription: string

A summary of the model.

ModelInfo

supportedDimensions?: number[]

The list of supported dimensions for the model (applies to dense embedding models only).

ModelInfo

supportedMetrics?: string[]

The distance metrics supported by the model for similarity search.

ModelInfo

supportedParameters: ModelInfoSupportedParameter[]

List of parameters supported by the model.

ModelInfo

type: string

The type of model (e.g. 'embed' or 'rerank').

ModelInfo

vectorType?: string

Whether the embedding model produces 'dense' or 'sparse' embeddings.

ModelInfo