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

    Your Search Can Return a Number

    "camping gear" against a 118 image index returns 60 documents. Add one aggregate stage and the same query returns $27,989 across 60 items at $466 average. The retrieval still runs; the aggregate computes over exactly what it found.

    A portrait diagram. The headline reads Your search can return a number, with the subline: one aggregate stage turns a result set into an answer, same retriever, same query, same index. A rail badged without it shows 60 documents, everything that matched for you to read, drawn as three rows of blank result tiles with the note and 30 more, correct, and not an answer; the chip reads 60 rows. A dark band reads query camping gear, stage aggregate, 60 to 1, with three large figures: 27,989 dollars total_value, 60 items, 466 dollars avg_price. Three smaller cards give the same pipeline on other queries: floor lamp 21,445 dollars across 43 items at 499 average, armchair 21,706 dollars across 50 items at 434 average, camping gear 27,989 dollars across 60 items at 466 average. A bold line states that the retrieval still happens and the aggregate runs on what it found, so the number answers the question you actually asked. A code window shows the execute request with query camping gear and a highlighted second stage, stage_id aggregate with aggregations count, sum and avg on price. The footer prints mxp.co/d/search-returns-a-number.
    "camping gear" against a 118 image index returns 60 documents. Add one aggregate stage and the same query returns $27,989 across 60 items at $466 average. The retrieval still runs; the aggregate computes over exactly what it found.

    Ask a 118 image index for camping gear and you get 60 documents. That is correct, and it is a list to read rather than an answer to the question you had.

    Add one aggregate stage to the same retriever and the same query returns a total of 27,989 dollars across 60 items, averaging 466 dollars. The stage config is one block: count, sum and average over price.

    The retrieval still happens first. Semantic search decides what matches, and the aggregation computes over exactly that set, so the number answers the question as asked instead of a category somebody had to define in advance. Three queries, three answers, one pipeline: floor lamp 21,445 dollars across 43 items, armchair 21,706 dollars across 50, camping gear 27,989 dollars across 60.

    This is the part of retrieval pipelines that gets missed. Every stage after the search is a transformation over the matched set, and the output of the last stage is whatever that stage produces. A ranked list is one choice. A count, a sum, a distribution or a single row are others, and they cost one config block each.

    What is real here: the photos are Pexels images with every photographer credited, the embeddings and executions ran against the live API, and the totals are the ones the aggregate stage returned. Prices are demo catalog data generated for this corpus, so the dollar figures describe the demo, and the mechanism is the point.

    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