ChunkMetadata: {
    chunk_html?: string | null;
    created_at: string;
    dataset_id: string;
    id: string;
    image_urls?: (string | null)[] | null;
    link?: string | null;
    location?: GeoInfo | null;
    metadata?: unknown;
    num_value?: number | null;
    tag_set?: (string | null)[] | null;
    time_stamp?: string | null;
    tracking_id?: string | null;
    updated_at: string;
    weight: number;
}

Type declaration

  • Optionalchunk_html?: string | null

    HTML content of the chunk, can also be an arbitrary string which is not HTML

  • created_at: string

    Timestamp of the creation of the chunk

  • dataset_id: string

    ID of the dataset which the chunk belongs to

  • id: string

    Unique identifier of the chunk, auto-generated uuid created by Trieve

  • Optionalimage_urls?: (string | null)[] | null

    Image URLs of the chunk, can be any list of strings. Used for image search and RAG.

  • Optionallink?: string | null

    Link to the chunk, should be a URL

  • Optionallocation?: GeoInfo | null
  • Optionalmetadata?: unknown

    Metadata of the chunk, can be any JSON object

  • Optionalnum_value?: number | null

    Numeric value of the chunk, can be any float. Can represent the most relevant numeric value of the chunk, such as a price, quantity in stock, rating, etc.

  • Optionaltag_set?: (string | null)[] | null

    Tag set of the chunk, can be any list of strings. Used for tag-filtered searches.

  • Optionaltime_stamp?: string | null

    Timestamp of the chunk, can be any timestamp. Specified by the user.

  • Optionaltracking_id?: string | null

    Tracking ID of the chunk, can be any string, determined by the user. Tracking ID's are unique identifiers for chunks within a dataset. They are designed to match the unique identifier of the chunk in the user's system.

  • updated_at: string

    Timestamp of the last update of the chunk

  • weight: number

    Weight of the chunk, can be any float. Used as a multiplier on a chunk's relevance score for ranking purposes.