NEWVectors or files. Pick a path.Start →
    Back to Videos

    The Retrieval Funnel: Why Your Reranker Sees 400 of 10 Million

    70
    Multimodal Search in Action
    Mixpeek Team
    July 29, 2026

    Summary

    Ten million documents could answer one query, and the model best qualified to judge them, a cross encoder that reads query and document together, is the one you can least afford to run across a corpus. That single constraint is why production retrieval is a ladder rather than a model. ANN search over embeddings goes first because it is cheap per document, so it runs against everything and returns a shortlist. Filters cut further, and the order matters: filtering after scoring and filtering before scoring are different operations with different recall. Only then does the cross encoder run, affordable precisely because it inherits a shortlist. Cheap stages absorb the volume, costly stages inherit a shortlist. Full breakdown: mixpeek.com/glossary/multi-stage-retrieval-pipeline

    multi-stage-retrievalrerankingcross-encodervector-searchinformation-retrievalrag

    About this video

    Ten million documents could answer one query, and the model best qualified to judge them, a cross encoder that reads query and document together, is the one you can least afford to run across a corpus. That single constraint is why production retrieval is a ladder rather than a model. ANN search over embeddings goes first because it is cheap per document, so it runs against everything and returns a shortlist. Filters cut further, and the order matters: filtering after scoring and filtering before scoring are different operations with different recall. Only then does the cross encoder run, affordable precisely because it inherits a shortlist. Cheap stages absorb the volume, costly stages inherit a shortlist. Full breakdown: mixpeek.com/glossary/multi-stage-retrieval-pipeline

    Frequently Asked Questions