Member Junction
    Preparing search index...

    Metadata stored alongside every vector in the shared index. Used for post-hoc filtering and provenance tracking.

    interface SharedVectorMetadata {
        ChunkIndex: number;
        ContentType: string;
        EntityDocumentID: string;
        EntityName: string;
        IndexedAt: string;
        RecordID: string;
        SourceType: VectorSourceType;
        Tags: string[];
    }
    Index

    Properties

    ChunkIndex: number

    Integer for multi-chunk documents

    ContentType: string

    MIME-like content category (e.g., "text/plain", "text/html", "application/pdf")

    EntityDocumentID: string

    The Entity Document template used for vectorization

    EntityName: string

    The MJ entity the vector came from (e.g., "Contacts", "Content Items")

    IndexedAt: string

    ISO date when this vector was indexed

    RecordID: string

    Composite key serialized string pointing back to the source record

    SourceType: VectorSourceType

    Origin classification

    Tags: string[]

    Human-readable tags produced by the autotagging pipeline