NEWVectors or files. Pick a path.Start →
    Apply

    Cross Compare

    Compare documents against a reference collection with multi-tier matching

    cross_compare
    Read Docs
    Integrate Now
    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. Collection ID containing reference documents to compare against.

    string

    Field on source documents containing comparison elements.

    string

    Field on reference documents containing comparison content.

    string

    Element extraction: 'raw', 'lines', 'labels', or 'list'.

    array

    Ordered matching cascade. Stops at first successful tier.

    number

    Minimum fuzzy score for a match.

    number

    Minimum semantic similarity for a match.

    string

    Output: 'findings' (one doc per comparison) or 'enrich' (add results to source).

    string

    Field name for results in 'enrich' mode.

    Output

    No output yet

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