NEWVectors or files. Pick a path.Start →
    Back to DiagramsRetrieval Mechanics

    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.

    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.
    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.

    Reconciling two catalogs sounds like one question with one score, and the score is the least useful part of the answer. The cross_compare stage walks a cascade of matching tiers, exact string, then fuzzy, then embedding similarity, stops at the first tier that hits, and reports which tier produced each match. A match earned by an identical string and a match earned by an embedding are different claims about the data, and keeping the tier keeps that difference.

    On this run, four items from a 118-product catalog were reconciled against a 13-item supplier list. Nylon Camping Tent matched an identical string at the exact tier. Copper Cast Iron Pan met the supplier's Copper Cast-Iron Pan at the fuzzy tier, one hyphen apart, at 0.95. Velvet Armchair met Armchair - Velvet at the vector tier, a reordered name, at 0.9528. The rug is the row that matters: there were rugs in the supplier list, and a nearest-neighbour search would have paired the jute rug with a wool one at a confident-looking 0.918. The stage reported not_in_supplier_catalog instead.

    The thresholds on the diagram are measured, not defaults. This catalog names products as material plus product type, which makes it structurally self-similar: at a permissive vector floor of 0.60 every source matched something and the no-match label never appeared, with Steel Cast Iron Pan matching Steel Floor Lamp at 0.879. The floor has to sit above what a deliberately wrong pair scores. Then check separately that a no-match is reachable at all: thirteen references cannot cover 118 products, so a run with zero unmatched items is assigning neighbours, and the count of the no-match label is the diagnostic.

    One more thing to be straight about. The reference list was designed so that each tier has a real case: the hyphen variant and the reordered name exist to exercise fuzzy and vector matching. That is a fair test of the mechanism. Tuning a threshold until a wrong match looked right would be a different thing, and it did not happen here.

    Everything on the diagram traces to one run on 2026-09-07 against the demo namespace, with the rows generated from the saved response.

    Where this diagram appears

    Run this on your own data

    Mixpeek turns video, images, audio, and documents in your object storage into searchable, timestamped results through one API.

    Search your own data

    Related diagrams

    A portrait diagram in two rails. The headline reads Filters exclude, what ranking would have shown, with the subline: a pre_filter drops rows before ranking is ever shown to you, useful, and it hides what it removed. A search bar holds the query yellow armchair, annotated: three of the top five are out of stock. Rail A, badged no filter, shows five armchair photos in rank order with prices and scores: 872 dollars at 0.080, 515 dollars at 0.065, 180 dollars at 0.060, 451 dollars at 0.060 and 506 dollars at 0.057; the second, third and fourth are greyed and stamped dropped, and the count chip reads 5 of 5. Rail B, badged pre_filter with in_stock equals true, shows the two survivors at 872 and 506 dollars followed by three new armchairs at 123 dollars 0.048, 446 dollars 0.047 and 606 dollars 0.046; its chip reads 2 kept plus 3 new. A bold line states that three of the top five were out of stock and all three were removed from the response entirely. A dark code window shows the execute request with the filters line in_stock true highlighted, and skip_cache true. The footer prints mxp.co/d/filters-exclude and the words real query, real ranking, mixpeek.

    Filters Exclude What Ranking Would Have Shown

    A portrait diagram in two rails. The headline reads Scope decides, what can be found at all, with the subline: the same question, asked of the whole catalog and then of one category. The search bar holds the query something to keep me warm outside, annotated: the query names no category. Rail A, badged whole catalog with the note semantic reach across every category, shows five photos in rank order: a lit tent at night for 543 dollars at 0.062, a snowy forest scene for 564 dollars at 0.060, a steaming pot on a stove for 444 dollars at 0.059, boots on a textured rug for 203 dollars at 0.052, and a tent under a starry sky for 100 dollars at 0.048; the second, third and fourth are greyed and stamped dropped, and the chip reads 5 of 5. Rail B, badged scoped with category equals tent and the note only one category can answer, shows the two surviving tents followed by three more tents at 592 dollars 0.046, 73 dollars 0.039 and 554 dollars 0.029; its chip reads 2 kept plus 3 new. A bold line states that unscoped, the index answered with tents, backpacks, rugs and pans, and that scope is a decision about what is allowed to be right. A code window shows the execute request with the filters line category tent highlighted. The footer prints mxp.co/d/scope-changes-candidates.

    Scope Decides What Can Be Found at All

    A portrait diagram in two rails. The headline reads A price ceiling, is not a price sort, with the subline: a price ceiling removes the expensive matches, it does not promote the cheap ones by price. The search bar holds the query premium floor lamp, annotated: premium is a word, not a number. Rail A, badged no ceiling with the note best matches, any price, shows five photos in rank order: floor lamps at 729 dollars 0.097, 299 dollars 0.093, 908 dollars 0.092 and 322 dollars 0.089, then an armchair at 451 dollars 0.086; four are greyed and stamped dropped, only the 299 dollar lamp survives, and the chip reads 5 of 5. Rail B, badged pre_filter with price less than 300 and the note best matches under the ceiling, shows the 299 dollar lamp first at 0.093, then lamps at 230 dollars 0.071, 104 dollars 0.068, 129 dollars 0.063 and 38 dollars 0.059; its chip reads 1 kept plus 4 new. A bold line states that rank order inside the filter is still semantic, so the cheapest item lands fourth. A code window shows the execute request with the filters line price lt 300 highlighted. The footer prints mxp.co/d/numeric-filter-reranks.

    A Price Ceiling Cuts the Set and Leaves the Order Semantic