NEWVectors or files. Pick a path.Start →
    Reduce

    Sample

    Sample a subset of documents using random or stratified sampling

    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

    integer
    Required

    REQUIRED. Number of documents to sample.

    string

    Sampling strategy: 'random', 'stratified', or 'reservoir'.

    string | null

    Field to stratify on (required when strategy='stratified').

    integer | null

    Random seed for reproducible sampling.

    integer

    Always keep top K documents by score, sample from remainder.

    Output

    No output yet

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