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

    One Photo In, Twenty Listings Out: Reverse Image Search as a Retriever Stage

    One product photo from a 118-image demo catalog, run through the external_reverse_image stage, came back as 20 ranked retail listings across 13 domains in a single call. Google Lens returns visual matches, so every row is a product that looks like this chair.

    A portrait diagram. The headline reads One photo in, twenty listings out, with the subline explaining that Google Lens reverse image search runs as a stage inside the retriever and returns where a visual match of an asset is listed across the open web. The top band shows the catalog row for a fabric armchair, SKU MXP-CHA-1000 at $446.05, category chair, material fabric, photographed by Pușcaș Adryan on Pexels. Below it one stage labelled external_reverse_image with engine google_lens returns 20 numbered rows of retailers, among them Target, Macy's, Bed Bath & Beyond, Lowe's, The Citizenry, Walmart, World Market, Overstock, Wayfair, Key Home Furnishings, The Home Depot and Castlery, marked as 13 domains. A footer shows the four-line stage config and the live-run date 2026-09-06.
    One product photo from a 118-image demo catalog, run through the external_reverse_image stage, came back as 20 ranked retail listings across 13 domains in a single call. Google Lens returns visual matches, so every row is a product that looks like this chair.

    Point a retriever at one photo of a product you sell and ask where a visual match of it is listed on the open web. In this run the answer was 20 listings across 13 retail domains: Target, Walmart, Wayfair, The Home Depot, Macy's, Lowe's, Overstock, Bed Bath & Beyond, World Market, Castlery, The Citizenry and Key Home Furnishings. The query image was a fabric armchair from our 118-image demo catalog, and every row on the diagram is a live listing returned by the provider, in the provider's rank order.

    The stage is called external_reverse_image. It wraps Google Lens reverse image search and runs inside the retriever pipeline, in the same position as a vector search or a filter. The whole configuration is an image_url templated from the input, the engine name and a top_k of 20. Because it is a stage, you can compose it: find the catalog items that match a text query, reverse-image each result, then filter to the domains you care about, all in one retriever call, with your own data and the open web ranked in the same response.

    Leak detection, licensing enforcement, competitor price monitoring and counterfeit hunting all start from the same question: where else does this asset appear on the open web. This stage answers that question once, so one retriever definition serves all four jobs.

    Google Lens returns visual matches, so the results are products that look like this chair. For competitor monitoring that is the behaviour you want. To prove that a specific file was copied, pair this stage with a perceptual or exact hash check, because a visual match says nothing about whether the pixels are identical.

    Everything on the diagram traces to one live run on 2026-09-06 against a retriever with a single external_reverse_image stage. The rows were generated from the saved response, so they cannot drift from what the API returned.

    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