What is the Cross Compare stage used for?

Matching documents against a reference collection across several tiers, so exact and approximate matches are both reachable.

When should I not use Cross Compare?

Treating a no-match as evidence of absence without checking why. The vector tier previously reported no_match on EVERY failure path, so an infrastructure error and a genuine non-match were indistinguishable to the caller. Fixed, but the shape is worth knowing: when a matching stage can only say yes or no, a failure renders as a confident no. Reach for it when you need to know whether something in one collection already exists in another.

Apply

Cross Compare

Compare documents against a reference collection with multi-tier matching

cross_compare

Read Docs

Integrate Now

On one real run

Your Supplier Renamed It, One Stage Still Finds It: A Matching Cascade That Reports Its Tier

Four catalog items reconciled against a 13-item supplier list. An identical string matches at the exact tier, one hyphen falls through to fuzzy at 0.95, a reordered name falls through to vector at 0.9528, and a jute rug that has no counterpart is reported as not_in_supplier_catalog instead of being paired with the nearest wool rug.

See the full diagram

A portrait diagram. The headline reads Your supplier renamed it, one stage still finds it, with the subline that cross_compare walks a cascade, stops at the first tier that hits and reports which tier caught each item. A band shows the four tiers: exact (string identical), fuzzy (threshold 0.85), vector (threshold 0.94) and no match (falls through). A table pairs four catalog items with the supplier's name for them: Nylon Camping Tent matched exactly at 1.0000 as exact_match; Copper Cast Iron Pan matched Copper Cast-Iron Pan at the fuzzy tier, 0.9500, close_match; Velvet Armchair matched Armchair - Velvet at the vector tier, 0.9528, close_match; Jute Area Rug matched nothing and is labelled not_in_supplier_catalog. A footer shows the configured match_tiers and no_match_label over 13 reference documents.

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

reference_collection_idstring

Required

REQUIRED. Collection ID containing reference documents to compare against.

source_fieldstring

Field on source documents containing comparison elements.

reference_fieldstring

Field on reference documents containing comparison content.

extraction_modestring

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

match_tiersarray

Ordered matching cascade. Stops at first successful tier.

fuzzy_thresholdnumber

Minimum fuzzy score for a match.

semantic_thresholdnumber

Minimum semantic similarity for a match.

output_modestring

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

output_fieldstring

Field name for results in 'enrich' mode.

Output

No output yet

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