Reranking is a second, slower pass over search results: a cross-encoder model reads each candidate together with the query and rescores it for true relevance, so the top results are the actually-right ones, not just the roughly-similar ones.
No jargon, no math
Vector search is fast because it compresses the query and the documents separately: fast, but shallow. Reranking adds a second read. First pass: an embedding search pulls the top 50 candidates in a few milliseconds, tuned for recall. Second pass: a cross-encoder reads the query and each candidate together, pair by pair, and assigns a precise relevance score; the list is reordered and only the top 5 reach the model that writes the answer. The cost: joint reading is slow, which is why you reserve it for a shortlist. The limit: if the right document was not in the first-pass 50, reranking never sees it, so the first pass is tuned to avoid losing it.
First pass. A fast embedding search pulls the top 50 candidates.
Joint reading. The cross-encoder reads the query and each candidate together, pair by pair.
Rescoring. Each pair gets a precise relevance score and the list is reordered.
Hand-off. Only the top 5 reach the model, quick to read and cite.
Semantic search finds content by meaning instead of exact words: the query and the documents are converted into embeddings, and the closest matches are returned even when no keyword overlaps.
ReadAn embedding is a list of numbers that captures the meaning of a piece of text, image or audio, so that content with similar meaning gets similar numbers and the computer can measure closeness with plain arithmetic.
ReadA vector database is a database built to store numeric fingerprints of content (embeddings) and find the closest ones to any query in milliseconds, powering semantic search, recommendations and AI retrieval.
Read§ 04
We design and ship AI systems with permissions, logs and human approval. It starts with a 30-minute scoping call.