Pinecone TypeScript SDK - v8.2.0
    Preparing search index...

    Interface ModelIndexEmbed

    The embedding model and document fields mapped to embedding inputs.

    ModelIndexEmbed

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

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

    ModelIndexEmbed

    fieldMap?: object

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

    ModelIndexEmbed

    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.

    ModelIndexEmbed

    model: string

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

    ModelIndexEmbed

    readParameters?: object

    The read parameters for the embedding model.

    ModelIndexEmbed

    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.

    ModelIndexEmbed

    writeParameters?: object

    The write parameters for the embedding model.

    ModelIndexEmbed

    Settings
    Member Visibility

    On This Page
    Properties