Pinecone TypeScript SDK - v9.2.0
    Preparing search index...

    Interface CreateEmbedConfig

    Dense embedding configuration for a string field. Pinecone embeds the field's text when documents are upserted or updated, and the query text when a search scores the field with an embed scoring method.

    Every key is optional; {} selects the default model at its default dimension and metric. Fixed at creation.

    CreateEmbedConfig

    interface CreateEmbedConfig {
        dimension?: number;
        metric?: string;
        model?: string;
        processingLocation?: string;
        readParameters?: object;
        writeParameters?: object;
    }
    Index
    dimension?: number

    The dimension of the embedding vectors. Defaults to the model's default dimension.

    Refer to the model guide for each model's supported dimensions.

    CreateEmbedConfig

    metric?: string

    The distance metric used for similarity search. Defaults to the model's default metric.

    Possible values: cosine, dotproduct, or euclidean.

    CreateEmbedConfig

    model?: string

    The name of a hosted dense embedding model. Defaults to llama-text-embed-v2.

    Refer to the model guide for available models.

    CreateEmbedConfig

    processingLocation?: string

    Where the model processes your data. Defaults to the model's default processing location.

    Supported processing locations depend on the model and your plan. See Processing locations.

    CreateEmbedConfig

    readParameters?: object

    Model-specific parameters applied when embedding search query text, such as truncate. Omitted parameters take the model's defaults.

    CreateEmbedConfig

    writeParameters?: object

    Model-specific parameters applied when embedding document text, such as truncate. Omitted parameters take the model's defaults.

    CreateEmbedConfig