Query filters

Restricts the query to one vertical core, skipping the routing step entirely.

Restricts results to a single host.

Drops one or more hosts from the result set.

Filters by crawl provenance: the batch corpus, or the delta crawler.

Bounds results by crawl time — when we fetched the page.

Bounds results by content date — when the page says it was published.

Requires an exact salient term to be present — the needle that semantic search would smooth away.

Sets a floor on the authority of the publishing host.

Sets a floor on the passage quality score assigned at admission.

Requires a minimum graph centrality — how load-bearing a passage is in its neighbourhood.

Requires the passage’s story to be carried by at least N distinct hosts.

Restricts results to one or more graph communities.

Filters by the institutional class of the domain.

Restricts results to one language; `langs[]` accepts several.

Restricts results to particular kinds of page.

Filters by topic tags assigned at index time.

Restricts results by top-level domain.

Drops explicit content. On by default.

Bounds passage length in words.

Chooses the retrieval strategy: lexical, vector, or both fused by reciprocal rank.

Orders results by relevance, time, authority, quality, length or graph centrality.

Deduplicates the result set by host, page or story cluster.

Returns counts by host, vertical, source, content type, authority, publication year and community.

Projects only the fields you need onto each hit.

Number of hits to return. Zero returns the count only.

Biases ranking toward newer passages without excluding older ones.

Biases ranking toward higher-authority hosts without excluding the rest.