NEWVectors or files. Pick a path.Start →
    Reduce

    Deduplicate

    Remove duplicate documents by field match or content similarity

    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

    Field to deduplicate on.

    string

    Dedup strategy: 'exact' (field match) or 'similarity' (embedding-based).

    number

    Similarity threshold for 'similarity' strategy.

    Output

    No output yet

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