Pinecone TypeScript SDK - v9.1.0
    Preparing search index...

    Interface SemanticTextField

    The embedded text field of a legacy integrated index created via create-for-model, as returned when the index is described. The index's embedding configuration is reported on the field named by its field_map. Legacy integrated indexes require the legacy Records API.

    This is a read-only view: semantic_text is rejected when creating an index. A document index reports an integrated-embedding field as a string field carrying embed or sparse_embed instead.

    SemanticTextField

    interface SemanticTextField {
        description?: string | null;
        dimension?: number | null;
        metric?: string;
        model: string;
        readParameters?: object | null;
        type: "semantic_text";
        writeParameters?: object | null;
    }
    Index
    description? dimension? metric? model readParameters? type writeParameters?
    description?: string | null

    The field's description, or null when none was set.

    SemanticTextField

    dimension?: number | null

    The dimension of the vectors the model produces. null for models that produce sparse vectors.

    SemanticTextField

    metric?: string

    The distance metric the index uses.

    Possible values: cosine, dotproduct, or euclidean.

    SemanticTextField

    model: string

    The hosted embedding model that embeds the field's text.

    SemanticTextField

    readParameters?: object | null

    Model-specific parameters applied at query time, such as input_type.

    SemanticTextField

    type: "semantic_text"

    Identifies this as a semantic text field. Must be semantic_text.

    SemanticTextField

    writeParameters?: object | null

    Model-specific parameters applied at write time, such as input_type.

    SemanticTextField

    Settings
    Member Visibility

    On This Page
    Properties