Documentation

The main query surface: returns metadata-only passage hits — url, host, title, snippet, score and world-model signals — but never the page body.

More-like-this: given a passage id, returns its semantic neighbours from the same embedding space the index was built in.

Query-free browsing: the most recent or highest-ranked passages, optionally within a single vertical.

Fetches the full cleaned text of one passage by id — the only endpoint that returns page content.

Coverage graph traversal: the connected neighbourhood of a passage, up to k hops — the edges are what to read next.

The anti-hallucination check: how many distinct hosts independently carry a story, and which ones.

The top passages on a topic ranked by graph centrality, so an agent can triage a field before reading into it.

A one-hop brief on an entity: where it is mentioned, which hosts cover it, and which entities co-occur with it.

The shortest chain of edges linking two passages — reasoning-path retrieval, or connect-the-dots.

GraphRAG as a single call: a corroborated, story-deduplicated, trust-ranked context pack fitted to a token budget, with a reason attached to every passage.

Coverage transparency: explains whether a URL is present in the index, was removed and why, or was never admitted.

A self-describing capability catalog: the filter grammar and every controlled vocabulary, so an agent can discover the query surface instead of guessing it.

Your tenant’s current plan, usage against quota and remaining allowance for this billing period.

Unauthenticated liveness probe. Returns 200 while the process is up.

Unauthenticated readiness probe: 200 once the index is loaded and non-empty, 503 while it is not.

Prometheus metrics: per-status request counters, a latency histogram and an in-flight gauge.