Interface ModelIndexEmbed

The embedding model and document fields mapped to embedding inputs.

Export

ModelIndexEmbed

interface ModelIndexEmbed {
    dimension?: number;
    fieldMap?: object;
    metric?: string;
    model: string;
    readParameters?: object;
    vectorType?: string;
    writeParameters?: object;
}

Properties

dimension? fieldMap? metric? model readParameters? vectorType? writeParameters?

Properties

Optionaldimension

dimension?: number

The dimensions of the vectors to be inserted in the index.

Memberof

ModelIndexEmbed

OptionalfieldMap

fieldMap?: object

Identifies the name of the text field from your document model that is embedded.

Memberof

ModelIndexEmbed

Optionalmetric

metric?: string

The distance metric to be used for similarity search. You can use 'euclidean', 'cosine', or 'dotproduct'. If not specified, the metric will be defaulted according to the model. Cannot be updated once set. Possible values: cosine, euclidean, or dotproduct.

Memberof

ModelIndexEmbed

model

model: string

The name of the embedding model used to create the index.

Memberof

ModelIndexEmbed

OptionalreadParameters

readParameters?: object

The read parameters for the embedding model.

Memberof

ModelIndexEmbed

OptionalvectorType

vectorType?: string

The index vector type. You can use 'dense' or 'sparse'. If 'dense', the vector dimension must be specified. If 'sparse', the vector dimension should not be specified.

Memberof

ModelIndexEmbed

OptionalwriteParameters

writeParameters?: object

The write parameters for the embedding model.

Memberof

ModelIndexEmbed

Settings

Member Visibility

On This Page

Properties