NEWVectors or files. Pick a path.Start →
    Apply

    Unwind

    Decompose array fields into separate documents for per-element processing

    On one real run

    Three Results Went In. Seven Rows Came Out: What Unwind Actually Does to a Result Set

    One search for a nylon hiking backpack returns three documents. Two carry no edges and are dropped entirely by the unwind stage; the third carries seven edges and becomes seven rows. input_count 3, output_count 7, and the two dropped documents never appear as empty rows because preserve_null_and_empty defaults to false.

    See the full diagram
    A portrait diagram showing the unwind retriever stage on one real run. Three input documents are shown: Ripstop Hiking Backpack and Canvas Hiking Backpack are dashed and greyed with an x mark, each carrying zero edges, while Nylon Hiking Backpack is solid with a check mark and seven edges. A config divider shows the unwind stage on the edges field. Below it, seven output rows each carry a rose index badge numbered 0 through 6, all labelled same_material, each paired with a SKU from MXP-TEN-1060 through MXP-TEN-1078. A footer reads input_count 3, output_count 7, preserve_null_and_empty false.
    Note: This playground provides simulated output to showcase functionality. No data is processed on our servers. Use this demo to explore the stage's configuration options before integrating it into your retriever pipeline.

    Configuration

    string
    Required

    REQUIRED. Array field to unwind.

    boolean

    Keep documents where the field is null or missing.

    boolean

    Add an index field tracking the element's position.

    Output

    No output yet

    Configure the stage parameters and click "Run Stage" to see the simulated output.